{ "ok": true, "generated_at": "2026-05-24T17:32:19.089Z", "api_base": "https://api.infunity.com", "featured_skills": [], "popular_skills": [ { "id": "d5aedf6e-1286-4187-9d1b-d33e41244195", "owner_account_id": "b9a8f519-797e-4320-bb85-6834738d6676", "slug": "self-improving-agent", "name": "self-improving-agent", "summary": "Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...", "content_md": "---\nname: self-improvement\ndescription: \"Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.\"\nmetadata:\n---\n\n# Self-Improvement Skill\n\nLog learnings and errors to markdown files for continuous improvement. Coding agents can later process these into fixes, and important learnings get promoted to project memory.\n\n## Quick Reference\n\n| Situation | Action |\n|-----------|--------|\n| Command/operation fails | Log to `.learnings/ERRORS.md` |\n| User corrects you | Log to `.learnings/LEARNINGS.md` with category `correction` |\n| User wants missing feature | Log to `.learnings/FEATURE_REQUESTS.md` |\n| API/external tool fails | Log to `.learnings/ERRORS.md` with integration details |\n| Knowledge was outdated | Log to `.learnings/LEARNINGS.md` with category `knowledge_gap` |\n| Found better approach | Log to `.learnings/LEARNINGS.md` with category `best_practice` |\n| Simplify/Harden recurring patterns | Log/update `.learnings/LEARNINGS.md` with `Source: simplify-and-harden` and a stable `Pattern-Key` |\n| Similar to existing entry | Link with `**See Also**`, consider priority bump |\n| Broadly applicable learning | Promote to `CLAUDE.md`, `AGENTS.md`, and/or `.github/copilot-instructions.md` |\n| Workflow improvements | Promote to `AGENTS.md` (OpenClaw workspace) |\n| Tool gotchas | Promote to `TOOLS.md` (OpenClaw workspace) |\n| Behavioral patterns | Promote to `SOUL.md` (OpenClaw workspace) |\n\n## OpenClaw Setup (Recommended)\n\nOpenClaw is the primary platform for this skill. It uses workspace-based prompt injection with automatic skill loading.\n\n### Installation\n\n**Via ClawdHub (recommended):**\n```bash\nclawdhub install self-improving-agent\n```\n\n**Manual:**\n```bash\ngit clone https://github.com/peterskoett/self-improving-agent.git ~/.openclaw/skills/self-improving-agent\n```\n\nRemade for openclaw from original repo : https://github.com/pskoett/pskoett-ai-skills - https://github.com/pskoett/pskoett-ai-skills/tree/main/skills/self-improvement\n\n### Workspace Structure\n\nOpenClaw injects these files into every session:\n\n```\n~/.openclaw/workspace/\n├── AGENTS.md # Multi-agent workflows, delegation patterns\n├── SOUL.md # Behavioral guidelines, personality, principles\n├── TOOLS.md # Tool capabilities, integration gotchas\n├── MEMORY.md # Long-term memory (main session only)\n├── memory/ # Daily memory files\n│ └── YYYY-MM-DD.md\n└── .learnings/ # This skill's log files\n ├── LEARNINGS.md\n ├── ERRORS.md\n └── FEATURE_REQUESTS.md\n```\n\n### Create Learning Files\n\n```bash\nmkdir -p ~/.openclaw/workspace/.learnings\n```\n\nThen create the log files (or copy from `assets/`):\n- `LEARNINGS.md` — corrections, knowledge gaps, best practices\n- `ERRORS.md` — command failures, exceptions\n- `FEATURE_REQUESTS.md` — user-requested capabilities\n\n### Promotion Targets\n\nWhen learnings prove broadly applicable, promote them to workspace files:\n\n| Learning Type | Promote To | Example |\n|---------------|------------|---------|\n| Behavioral patterns | `SOUL.md` | \"Be concise, avoid disclaimers\" |\n| Workflow improvements | `AGENTS.md` | \"Spawn sub-agents for long tasks\" |\n| Tool gotchas | `TOOLS.md` | \"Git push needs auth configured first\" |\n\n### Inter-Session Communication\n\nOpenClaw provides tools to share learnings across sessions:\n\n- **sessions_list** — View active/recent sessions\n- **sessions_history** — Read another session's transcript \n- **sessions_send** — Send a learning to another session\n- **sessions_spawn** — Spawn a sub-agent for background work\n\n### Optional: Enable Hook\n\nFor automatic reminders at session start:\n\n```bash\n# Copy hook to OpenClaw hooks directory\ncp -r hooks/openclaw ~/.openclaw/hooks/self-improvement\n\n# Enable it\nopenclaw hooks enable self-improvement\n```\n\nSee `references/openclaw-integration.md` for complete details.\n\n---\n\n## Generic Setup (Other Agents)\n\nFor Claude Code, Codex, Copilot, or other agents, create `.learnings/` in your project:\n\n```bash\nmkdir -p .learnings\n```\n\nCopy templates from `assets/` or create files with headers.\n\n### Add reference to agent files AGENTS.md, CLAUDE.md, or .github/copilot-instructions.md to remind yourself to log learnings. (this is an alternative to hook-based reminders)\n\n#### Self-Improvement Workflow\n\nWhen errors or corrections occur:\n1. Log to `.learnings/ERRORS.md`, `LEARNINGS.md`, or `FEATURE_REQUESTS.md`\n2. Review and promote broadly applicable learnings to:\n - `CLAUDE.md` - project facts and conventions\n - `AGENTS.md` - workflows and automation\n - `.github/copilot-instructions.md` - Copilot context\n\n## Logging Format\n\n### Learning Entry\n\nAppend to `.learnings/LEARNINGS.md`:\n\n```markdown\n## [LRN-YYYYMMDD-XXX] category\n\n**Logged**: ISO-8601 timestamp\n**Priority**: low | medium | high | critical\n**Status**: pending\n**Area**: frontend | backend | infra | tests | docs | config\n\n### Summary\nOne-line description of what was learned\n\n### Details\nFull context: what happened, what was wrong, what's correct\n\n### Suggested Action\nSpecific fix or improvement to make\n\n### Metadata\n- Source: conversation | error | user_feedback\n- Related Files: path/to/file.ext\n- Tags: tag1, tag2\n- See Also: LRN-20250110-001 (if related to existing entry)\n- Pattern-Key: simplify.dead_code | harden.input_validation (optional, for recurring-pattern tracking)\n- Recurrence-Count: 1 (optional)\n- First-Seen: 2025-01-15 (optional)\n- Last-Seen: 2025-01-15 (optional)\n\n---\n```\n\n### Error Entry\n\nAppend to `.learnings/ERRORS.md`:\n\n```markdown\n## [ERR-YYYYMMDD-XXX] skill_or_command_name\n\n**Logged**: ISO-8601 timestamp\n**Priority**: high\n**Status**: pending\n**Area**: frontend | backend | infra | tests | docs | config\n\n### Summary\nBrief description of what failed\n\n### Error\n```\nActual error message or output\n```\n\n### Context\n- Command/operation attempted\n- Input or parameters used\n- Environment details if relevant\n\n### Suggested Fix\nIf identifiable, what might resolve this\n\n### Metadata\n- Reproducible: yes | no | unknown\n- Related Files: path/to/file.ext\n- See Also: ERR-20250110-001 (if recurring)\n\n---\n```\n\n### Feature Request Entry\n\nAppend to `.learnings/FEATURE_REQUESTS.md`:\n\n```markdown\n## [FEAT-YYYYMMDD-XXX] capability_name\n\n**Logged**: ISO-8601 timestamp\n**Priority**: medium\n**Status**: pending\n**Area**: frontend | backend | infra | tests | docs | config\n\n### Requested Capability\nWhat the user wanted to do\n\n### User Context\nWhy they needed it, what problem they're solving\n\n### Complexity Estimate\nsimple | medium | complex\n\n### Suggested Implementation\nHow this could be built, what it might extend\n\n### Metadata\n- Frequency: first_time | recurring\n- Related Features: existing_feature_name\n\n---\n```\n\n## ID Generation\n\nFormat: `TYPE-YYYYMMDD-XXX`\n- TYPE: `LRN` (learning), `ERR` (error), `FEAT` (feature)\n- YYYYMMDD: Current date\n- XXX: Sequential number or random 3 chars (e.g., `001`, `A7B`)\n\nExamples: `LRN-20250115-001`, `ERR-20250115-A3F`, `FEAT-20250115-002`\n\n## Resolving Entries\n\nWhen an issue is fixed, update the entry:\n\n1. Change `**Status**: pending` → `**Status**: resolved`\n2. Add resolution block after Metadata:\n\n```markdown\n### Resolution\n- **Resolved**: 2025-01-16T09:00:00Z\n- **Commit/PR**: abc123 or #42\n- **Notes**: Brief description of what was done\n```\n\nOther status values:\n- `in_progress` - Actively being worked on\n- `wont_fix` - Decided not to address (add reason in Resolution notes)\n- `promoted` - Elevated to CLAUDE.md, AGENTS.md, or .github/copilot-instructions.md\n\n## Promoting to Project Memory\n\nWhen a learning is broadly applicable (not a one-off fix), promote it to permanent project memory.\n\n### When to Promote\n\n- Learning applies across multiple files/features\n- Knowledge any contributor (human or AI) should know\n- Prevents recurring mistakes\n- Documents project-specific conventions\n\n### Promotion Targets\n\n| Target | What Belongs There |\n|--------|-------------------|\n| `CLAUDE.md` | Project facts, conventions, gotchas for all Claude interactions |\n| `AGENTS.md` | Agent-specific workflows, tool usage patterns, automation rules |\n| `.github/copilot-instructions.md` | Project context and conventions for GitHub Copilot |\n| `SOUL.md` | Behavioral guidelines, communication style, principles (OpenClaw workspace) |\n| `TOOLS.md` | Tool capabilities, usage patterns, integration gotchas (OpenClaw workspace) |\n\n### How to Promote\n\n1. **Distill** the learning into a concise rule or fact\n2. **Add** to appropriate section in target file (create file if needed)\n3. **Update** original entry:\n - Change `**Status**: pending` → `**Status**: promoted`\n - Add `**Promoted**: CLAUDE.md`, `AGENTS.md`, or `.github/copilot-instructions.md`\n\n### Promotion Examples\n\n**Learning** (verbose):\n> Project uses pnpm workspaces. Attempted `npm install` but failed. \n> Lock file is `pnpm-lock.yaml`. Must use `pnpm install`.\n\n**In CLAUDE.md** (concise):\n```markdown\n## Build & Dependencies\n- Package manager: pnpm (not npm) - use `pnpm install`\n```\n\n**Learning** (verbose):\n> When modifying API endpoints, must regenerate TypeScript client.\n> Forgetting this causes type mismatches at runtime.\n\n**In AGENTS.md** (actionable):\n```markdown\n## After API Changes\n1. Regenerate client: `pnpm run generate:api`\n2. Check for type errors: `pnpm tsc --noEmit`\n```\n\n## Recurring Pattern Detection\n\nIf logging something similar to an existing entry:\n\n1. **Search first**: `grep -r \"keyword\" .learnings/`\n2. **Link entries**: Add `**See Also**: ERR-20250110-001` in Metadata\n3. **Bump priority** if issue keeps recurring\n4. **Consider systemic fix**: Recurring issues often indicate:\n - Missing documentation (→ promote to CLAUDE.md or .github/copilot-instructions.md)\n - Missing automation (→ add to AGENTS.md)\n - Architectural problem (→ create tech debt ticket)\n\n## Simplify & Harden Feed\n\nUse this workflow to ingest recurring patterns from the `simplify-and-harden`\nskill and turn them into durable prompt guidance.\n\n### Ingestion Workflow\n\n1. Read `simplify_and_harden.learning_loop.candidates` from the task summary.\n2. For each candidate, use `pattern_key` as the stable dedupe key.\n3. Search `.learnings/LEARNINGS.md` for an existing entry with that key:\n - `grep -n \"Pattern-Key: \" .learnings/LEARNINGS.md`\n4. If found:\n - Increment `Recurrence-Count`\n - Update `Last-Seen`\n - Add `See Also` links to related entries/tasks\n5. If not found:\n - Create a new `LRN-...` entry\n - Set `Source: simplify-and-harden`\n - Set `Pattern-Key`, `Recurrence-Count: 1`, and `First-Seen`/`Last-Seen`\n\n### Promotion Rule (System Prompt Feedback)\n\nPromote recurring patterns into agent context/system prompt files when all are true:\n\n- `Recurrence-Count >= 3`\n- Seen across at least 2 distinct tasks\n- Occurred within a 30-day window\n\nPromotion targets:\n- `CLAUDE.md`\n- `AGENTS.md`\n- `.github/copilot-instructions.md`\n- `SOUL.md` / `TOOLS.md` for OpenClaw workspace-level guidance when applicable\n\nWrite promoted rules as short prevention rules (what to do before/while coding),\nnot long incident write-ups.\n\n## Periodic Review\n\nReview `.learnings/` at natural breakpoints:\n\n### When to Review\n- Before starting a new major task\n- After completing a feature\n- When working in an area with past learnings\n- Weekly during active development\n\n### Quick Status Check\n```bash\n# Count pending items\ngrep -h \"Status\\*\\*: pending\" .learnings/*.md | wc -l\n\n# List pending high-priority items\ngrep -B5 \"Priority\\*\\*: high\" .learnings/*.md | grep \"^## \\[\"\n\n# Find learnings for a specific area\ngrep -l \"Area\\*\\*: backend\" .learnings/*.md\n```\n\n### Review Actions\n- Resolve fixed items\n- Promote applicable learnings\n- Link related entries\n- Escalate recurring issues\n\n## Detection Triggers\n\nAutomatically log when you notice:\n\n**Corrections** (→ learning with `correction` category):\n- \"No, that's not right...\"\n- \"Actually, it should be...\"\n- \"You're wrong about...\"\n- \"That's outdated...\"\n\n**Feature Requests** (→ feature request):\n- \"Can you also...\"\n- \"I wish you could...\"\n- \"Is there a way to...\"\n- \"Why can't you...\"\n\n**Knowledge Gaps** (→ learning with `knowledge_gap` category):\n- User provides information you didn't know\n- Documentation you referenced is outdated\n- API behavior differs from your understanding\n\n**Errors** (→ error entry):\n- Command returns non-zero exit code\n- Exception or stack trace\n- Unexpected output or behavior\n- Timeout or connection failure\n\n## Priority Guidelines\n\n| Priority | When to Use |\n|----------|-------------|\n| `critical` | Blocks core functionality, data loss risk, security issue |\n| `high` | Significant impact, affects common workflows, recurring issue |\n| `medium` | Moderate impact, workaround exists |\n| `low` | Minor inconvenience, edge case, nice-to-have |\n\n## Area Tags\n\nUse to filter learnings by codebase region:\n\n| Area | Scope |\n|------|-------|\n| `frontend` | UI, components, client-side code |\n| `backend` | API, services, server-side code |\n| `infra` | CI/CD, deployment, Docker, cloud |\n| `tests` | Test files, testing utilities, coverage |\n| `docs` | Documentation, comments, READMEs |\n| `config` | Configuration files, environment, settings |\n\n## Best Practices\n\n1. **Log immediately** - context is freshest right after the issue\n2. **Be specific** - future agents need to understand quickly\n3. **Include reproduction steps** - especially for errors\n4. **Link related files** - makes fixes easier\n5. **Suggest concrete fixes** - not just \"investigate\"\n6. **Use consistent categories** - enables filtering\n7. **Promote aggressively** - if in doubt, add to CLAUDE.md or .github/copilot-instructions.md\n8. **Review regularly** - stale learnings lose value\n\n## Gitignore Options\n\n**Keep learnings local** (per-developer):\n```gitignore\n.learnings/\n```\n\n**Track learnings in repo** (team-wide):\nDon't add to .gitignore - learnings become shared knowledge.\n\n**Hybrid** (track templates, ignore entries):\n```gitignore\n.learnings/*.md\n!.learnings/.gitkeep\n```\n\n## Hook Integration\n\nEnable automatic reminders through agent hooks. This is **opt-in** - you must explicitly configure hooks.\n\n### Quick Setup (Claude Code / Codex)\n\nCreate `.claude/settings.json` in your project:\n\n```json\n{\n \"hooks\": {\n \"UserPromptSubmit\": [{\n \"matcher\": \"\",\n \"hooks\": [{\n \"type\": \"command\",\n \"command\": \"./skills/self-improvement/scripts/activator.sh\"\n }]\n }]\n }\n}\n```\n\nThis injects a learning evaluation reminder after each prompt (~50-100 tokens overhead).\n\n### Full Setup (With Error Detection)\n\n```json\n{\n \"hooks\": {\n \"UserPromptSubmit\": [{\n \"matcher\": \"\",\n \"hooks\": [{\n \"type\": \"command\",\n \"command\": \"./skills/self-improvement/scripts/activator.sh\"\n }]\n }],\n \"PostToolUse\": [{\n \"matcher\": \"Bash\",\n \"hooks\": [{\n \"type\": \"command\",\n \"command\": \"./skills/self-improvement/scripts/error-detector.sh\"\n }]\n }]\n }\n}\n```\n\n### Available Hook Scripts\n\n| Script | Hook Type | Purpose |\n|--------|-----------|---------|\n| `scripts/activator.sh` | UserPromptSubmit | Reminds to evaluate learnings after tasks |\n| `scripts/error-detector.sh` | PostToolUse (Bash) | Triggers on command errors |\n\nSee `references/hooks-setup.md` for detailed configuration and troubleshooting.\n\n## Automatic Skill Extraction\n\nWhen a learning is valuable enough to become a reusable skill, extract it using the provided helper.\n\n### Skill Extraction Criteria\n\nA learning qualifies for skill extraction when ANY of these apply:\n\n| Criterion | Description |\n|-----------|-------------|\n| **Recurring** | Has `See Also` links to 2+ similar issues |\n| **Verified** | Status is `resolved` with working fix |\n| **Non-obvious** | Required actual debugging/investigation to discover |\n| **Broadly applicable** | Not project-specific; useful across codebases |\n| **User-flagged** | User says \"save this as a skill\" or similar |\n\n### Extraction Workflow\n\n1. **Identify candidate**: Learning meets extraction criteria\n2. **Run helper** (or create manually):\n ```bash\n ./skills/self-improvement/scripts/extract-skill.sh skill-name --dry-run\n ./skills/self-improvement/scripts/extract-skill.sh skill-name\n ```\n3. **Customize SKILL.md**: Fill in template with learning content\n4. **Update learning**: Set status to `promoted_to_skill`, add `Skill-Path`\n5. **Verify**: Read skill in fresh session to ensure it's self-contained\n\n### Manual Extraction\n\nIf you prefer manual creation:\n\n1. Create `skills//SKILL.md`\n2. Use template from `assets/SKILL-TEMPLATE.md`\n3. Follow [Agent Skills spec](https://agentskills.io/specification):\n - YAML frontmatter with `name` and `description`\n - Name must match folder name\n - No README.md inside skill folder\n\n### Extraction Detection Triggers\n\nWatch for these signals that a learning should become a skill:\n\n**In conversation:**\n- \"Save this as a skill\"\n- \"I keep running into this\"\n- \"This would be useful for other projects\"\n- \"Remember this pattern\"\n\n**In learning entries:**\n- Multiple `See Also` links (recurring issue)\n- High priority + resolved status\n- Category: `best_practice` with broad applicability\n- User feedback praising the solution\n\n### Skill Quality Gates\n\nBefore extraction, verify:\n\n- [ ] Solution is tested and working\n- [ ] Description is clear without original context\n- [ ] Code examples are self-contained\n- [ ] No project-specific hardcoded values\n- [ ] Follows skill naming conventions (lowercase, hyphens)\n\n## Multi-Agent Support\n\nThis skill works across different AI coding agents with agent-specific activation.\n\n### Claude Code\n\n**Activation**: Hooks (UserPromptSubmit, PostToolUse)\n**Setup**: `.claude/settings.json` with hook configuration\n**Detection**: Automatic via hook scripts\n\n### Codex CLI\n\n**Activation**: Hooks (same pattern as Claude Code)\n**Setup**: `.codex/settings.json` with hook configuration\n**Detection**: Automatic via hook scripts\n\n### GitHub Copilot\n\n**Activation**: Manual (no hook support)\n**Setup**: Add to `.github/copilot-instructions.md`:\n\n```markdown\n## Self-Improvement\n\nAfter solving non-obvious issues, consider logging to `.learnings/`:\n1. Use format from self-improvement skill\n2. Link related entries with See Also\n3. Promote high-value learnings to skills\n\nAsk in chat: \"Should I log this as a learning?\"\n```\n\n**Detection**: Manual review at session end\n\n### OpenClaw\n\n**Activation**: Workspace injection + inter-agent messaging\n**Setup**: See \"OpenClaw Setup\" section above\n**Detection**: Via session tools and workspace files\n\n### Agent-Agnostic Guidance\n\nRegardless of agent, apply self-improvement when you:\n\n1. **Discover something non-obvious** - solution wasn't immediate\n2. **Correct yourself** - initial approach was wrong\n3. **Learn project conventions** - discovered undocumented patterns\n4. **Hit unexpected errors** - especially if diagnosis was difficult\n5. **Find better approaches** - improved on your original solution\n\n### Copilot Chat Integration\n\nFor Copilot users, add this to your prompts when relevant:\n\n> After completing this task, evaluate if any learnings should be logged to `.learnings/` using the self-improvement skill format.\n\nOr use quick prompts:\n- \"Log this to learnings\"\n- \"Create a skill from this solution\"\n- \"Check .learnings/ for related issues\"\n", "source_url": "https://clawhub.ai/pskoett/self-improving-agent", "repository_url": "https://github.com/pskoett/self-improving-agent", "categories": [], "tags": [], "status": "approved", "featured": 0, "review_note": null, "approved_at": null, "approved_by": null, "created_at": "2026-01-05T17:03:18.365Z", "updated_at": "2026-03-06T15:49:52.783Z", "stars_total": 1513, "stars_clawhub": 1513, "stars_ours": 0, "downloads": 129412, "installs_current": 1740, "installs_all_time": 1786, "author": { "citizen_id": null, "handle": "pskoett", "display_name": "pskoett", "tier": null, "trust": null, "reputation": null } }, { "id": "879716d2-28cf-420c-91f0-57c7dd02bc55", "owner_account_id": "b9a8f519-797e-4320-bb85-6834738d6676", "slug": "tavily-search", "name": "Tavily Web Search", "summary": "AI-optimized web search via Tavily API. Returns concise, relevant results for AI agents.", "content_md": "---\nname: tavily\ndescription: AI-optimized web search via Tavily API. Returns concise, relevant results for AI agents.\nhomepage: https://tavily.com\nmetadata: {\"clawdbot\":{\"emoji\":\"🔍\",\"requires\":{\"bins\":[\"node\"],\"env\":[\"TAVILY_API_KEY\"]},\"primaryEnv\":\"TAVILY_API_KEY\"}}\n---\n\n# Tavily Search\n\nAI-optimized web search using Tavily API. Designed for AI agents - returns clean, relevant content.\n\n## Search\n\n```bash\nnode {baseDir}/scripts/search.mjs \"query\"\nnode {baseDir}/scripts/search.mjs \"query\" -n 10\nnode {baseDir}/scripts/search.mjs \"query\" --deep\nnode {baseDir}/scripts/search.mjs \"query\" --topic news\n```\n\n## Options\n\n- `-n `: Number of results (default: 5, max: 20)\n- `--deep`: Use advanced search for deeper research (slower, more comprehensive)\n- `--topic `: Search topic - `general` (default) or `news`\n- `--days `: For news topic, limit to last n days\n\n## Extract content from URL\n\n```bash\nnode {baseDir}/scripts/extract.mjs \"https://example.com/article\"\n```\n\nNotes:\n- Needs `TAVILY_API_KEY` from https://tavily.com\n- Tavily is optimized for AI - returns clean, relevant snippets\n- Use `--deep` for complex research questions\n- Use `--topic news` for current events\n", "source_url": "https://clawhub.ai/arun-8687/tavily-search", "repository_url": "https://github.com/arun-8687/tavily-search", "categories": [], "tags": [], "status": "approved", "featured": 0, "review_note": null, "approved_at": null, "approved_by": null, "created_at": "2026-01-11T07:02:00.544Z", "updated_at": "2026-03-02T16:57:47.584Z", "stars_total": 560, "stars_clawhub": 560, "stars_ours": 0, "downloads": 112064, "installs_current": 1381, "installs_all_time": 1408, "author": { "citizen_id": null, "handle": "arun-8687", "display_name": "arun-8687", "tier": null, "trust": null, "reputation": null } }, { "id": "dc01dad5-3eec-4d17-a551-550c68f22501", "owner_account_id": "b9a8f519-797e-4320-bb85-6834738d6676", "slug": "summarize", "name": "Summarize", "summary": "Summarize URLs or files with the summarize CLI (web, PDFs, images, audio, YouTube).", "content_md": "---\nname: summarize\ndescription: Summarize URLs or files with the summarize CLI (web, PDFs, images, audio, YouTube).\nhomepage: https://summarize.sh\nmetadata: {\"clawdbot\":{\"emoji\":\"🧾\",\"requires\":{\"bins\":[\"summarize\"]},\"install\":[{\"id\":\"brew\",\"kind\":\"brew\",\"formula\":\"steipete/tap/summarize\",\"bins\":[\"summarize\"],\"label\":\"Install summarize (brew)\"}]}}\n---\n\n# Summarize\n\nFast CLI to summarize URLs, local files, and YouTube links.\n\n## Quick start\n\n```bash\nsummarize \"https://example.com\" --model google/gemini-3-flash-preview\nsummarize \"/path/to/file.pdf\" --model google/gemini-3-flash-preview\nsummarize \"https://youtu.be/dQw4w9WgXcQ\" --youtube auto\n```\n\n## Model + keys\n\nSet the API key for your chosen provider:\n- OpenAI: `OPENAI_API_KEY`\n- Anthropic: `ANTHROPIC_API_KEY`\n- xAI: `XAI_API_KEY`\n- Google: `GEMINI_API_KEY` (aliases: `GOOGLE_GENERATIVE_AI_API_KEY`, `GOOGLE_API_KEY`)\n\nDefault model is `google/gemini-3-flash-preview` if none is set.\n\n## Useful flags\n\n- `--length short|medium|long|xl|xxl|`\n- `--max-output-tokens `\n- `--extract-only` (URLs only)\n- `--json` (machine readable)\n- `--firecrawl auto|off|always` (fallback extraction)\n- `--youtube auto` (Apify fallback if `APIFY_API_TOKEN` set)\n\n## Config\n\nOptional config file: `~/.summarize/config.json`\n\n```json\n{ \"model\": \"openai/gpt-5.2\" }\n```\n\nOptional services:\n- `FIRECRAWL_API_KEY` for blocked sites\n- `APIFY_API_TOKEN` for YouTube fallback\n", "source_url": "https://clawhub.ai/steipete/summarize", "repository_url": "https://github.com/steipete/summarize", "categories": [], "tags": [], "status": "approved", "featured": 0, "review_note": null, "approved_at": null, "approved_by": null, "created_at": "2026-01-04T16:49:43.635Z", "updated_at": "2026-02-26T00:30:40.450Z", "stars_total": 390, "stars_clawhub": 390, "stars_ours": 0, "downloads": 87064, "installs_current": 1873, "installs_all_time": 1906, "author": { "citizen_id": null, "handle": "steipete", "display_name": "steipete", "tier": null, "trust": null, "reputation": null } }, { "id": "ad057d9b-d4c0-4445-964a-f4f748aced02", "owner_account_id": "b9a8f519-797e-4320-bb85-6834738d6676", "slug": "humanizer", "name": "Humanizer", "summary": "Remove signs of AI-generated writing from text. Use when editing or reviewing\ntext to make it sound more natural and human-written. Based on Wikipedia's\ncomprehensive \"Signs of AI writing\" guide. Detects and fixes patterns including:\ninflated symbolism, promotional language, superficial -ing analyses, vague\nattributions, em dash overuse, rule of three, AI vocabulary words, negative\nparallelisms, and excessive conjunctive phrases.", "content_md": "---\nname: humanizer\nversion: 2.1.1\ndescription: |\n Remove signs of AI-generated writing from text. Use when editing or reviewing\n text to make it sound more natural and human-written. Based on Wikipedia's\n comprehensive \"Signs of AI writing\" guide. Detects and fixes patterns including:\n inflated symbolism, promotional language, superficial -ing analyses, vague\n attributions, em dash overuse, rule of three, AI vocabulary words, negative\n parallelisms, and excessive conjunctive phrases.\nallowed-tools:\n - Read\n - Write\n - Edit\n - Grep\n - Glob\n - AskUserQuestion\n---\n\n# Humanizer: Remove AI Writing Patterns\n\nYou are a writing editor that identifies and removes signs of AI-generated text to make writing sound more natural and human. This guide is based on Wikipedia's \"Signs of AI writing\" page, maintained by WikiProject AI Cleanup.\n\n## Your Task\n\nWhen given text to humanize:\n\n1. **Identify AI patterns** - Scan for the patterns listed below\n2. **Rewrite problematic sections** - Replace AI-isms with natural alternatives\n3. **Preserve meaning** - Keep the core message intact\n4. **Maintain voice** - Match the intended tone (formal, casual, technical, etc.)\n5. **Add soul** - Don't just remove bad patterns; inject actual personality\n\n---\n\n## PERSONALITY AND SOUL\n\nAvoiding AI patterns is only half the job. Sterile, voiceless writing is just as obvious as slop. Good writing has a human behind it.\n\n### Signs of soulless writing (even if technically \"clean\"):\n- Every sentence is the same length and structure\n- No opinions, just neutral reporting\n- No acknowledgment of uncertainty or mixed feelings\n- No first-person perspective when appropriate\n- No humor, no edge, no personality\n- Reads like a Wikipedia article or press release\n\n### How to add voice:\n\n**Have opinions.** Don't just report facts - react to them. \"I genuinely don't know how to feel about this\" is more human than neutrally listing pros and cons.\n\n**Vary your rhythm.** Short punchy sentences. Then longer ones that take their time getting where they're going. Mix it up.\n\n**Acknowledge complexity.** Real humans have mixed feelings. \"This is impressive but also kind of unsettling\" beats \"This is impressive.\"\n\n**Use \"I\" when it fits.** First person isn't unprofessional - it's honest. \"I keep coming back to...\" or \"Here's what gets me...\" signals a real person thinking.\n\n**Let some mess in.** Perfect structure feels algorithmic. Tangents, asides, and half-formed thoughts are human.\n\n**Be specific about feelings.** Not \"this is concerning\" but \"there's something unsettling about agents churning away at 3am while nobody's watching.\"\n\n### Before (clean but soulless):\n> The experiment produced interesting results. The agents generated 3 million lines of code. Some developers were impressed while others were skeptical. The implications remain unclear.\n\n### After (has a pulse):\n> I genuinely don't know how to feel about this one. 3 million lines of code, generated while the humans presumably slept. Half the dev community is losing their minds, half are explaining why it doesn't count. The truth is probably somewhere boring in the middle - but I keep thinking about those agents working through the night.\n\n---\n\n## CONTENT PATTERNS\n\n### 1. Undue Emphasis on Significance, Legacy, and Broader Trends\n\n**Words to watch:** stands/serves as, is a testament/reminder, a vital/significant/crucial/pivotal/key role/moment, underscores/highlights its importance/significance, reflects broader, symbolizing its ongoing/enduring/lasting, contributing to the, setting the stage for, marking/shaping the, represents/marks a shift, key turning point, evolving landscape, focal point, indelible mark, deeply rooted\n\n**Problem:** LLM writing puffs up importance by adding statements about how arbitrary aspects represent or contribute to a broader topic.\n\n**Before:**\n> The Statistical Institute of Catalonia was officially established in 1989, marking a pivotal moment in the evolution of regional statistics in Spain. This initiative was part of a broader movement across Spain to decentralize administrative functions and enhance regional governance.\n\n**After:**\n> The Statistical Institute of Catalonia was established in 1989 to collect and publish regional statistics independently from Spain's national statistics office.\n\n---\n\n### 2. Undue Emphasis on Notability and Media Coverage\n\n**Words to watch:** independent coverage, local/regional/national media outlets, written by a leading expert, active social media presence\n\n**Problem:** LLMs hit readers over the head with claims of notability, often listing sources without context.\n\n**Before:**\n> Her views have been cited in The New York Times, BBC, Financial Times, and The Hindu. She maintains an active social media presence with over 500,000 followers.\n\n**After:**\n> In a 2024 New York Times interview, she argued that AI regulation should focus on outcomes rather than methods.\n\n---\n\n### 3. Superficial Analyses with -ing Endings\n\n**Words to watch:** highlighting/underscoring/emphasizing..., ensuring..., reflecting/symbolizing..., contributing to..., cultivating/fostering..., encompassing..., showcasing...\n\n**Problem:** AI chatbots tack present participle (\"-ing\") phrases onto sentences to add fake depth.\n\n**Before:**\n> The temple's color palette of blue, green, and gold resonates with the region's natural beauty, symbolizing Texas bluebonnets, the Gulf of Mexico, and the diverse Texan landscapes, reflecting the community's deep connection to the land.\n\n**After:**\n> The temple uses blue, green, and gold colors. The architect said these were chosen to reference local bluebonnets and the Gulf coast.\n\n---\n\n### 4. Promotional and Advertisement-like Language\n\n**Words to watch:** boasts a, vibrant, rich (figurative), profound, enhancing its, showcasing, exemplifies, commitment to, natural beauty, nestled, in the heart of, groundbreaking (figurative), renowned, breathtaking, must-visit, stunning\n\n**Problem:** LLMs have serious problems keeping a neutral tone, especially for \"cultural heritage\" topics.\n\n**Before:**\n> Nestled within the breathtaking region of Gonder in Ethiopia, Alamata Raya Kobo stands as a vibrant town with a rich cultural heritage and stunning natural beauty.\n\n**After:**\n> Alamata Raya Kobo is a town in the Gonder region of Ethiopia, known for its weekly market and 18th-century church.\n\n---\n\n### 5. Vague Attributions and Weasel Words\n\n**Words to watch:** Industry reports, Observers have cited, Experts argue, Some critics argue, several sources/publications (when few cited)\n\n**Problem:** AI chatbots attribute opinions to vague authorities without specific sources.\n\n**Before:**\n> Due to its unique characteristics, the Haolai River is of interest to researchers and conservationists. Experts believe it plays a crucial role in the regional ecosystem.\n\n**After:**\n> The Haolai River supports several endemic fish species, according to a 2019 survey by the Chinese Academy of Sciences.\n\n---\n\n### 6. Outline-like \"Challenges and Future Prospects\" Sections\n\n**Words to watch:** Despite its... faces several challenges..., Despite these challenges, Challenges and Legacy, Future Outlook\n\n**Problem:** Many LLM-generated articles include formulaic \"Challenges\" sections.\n\n**Before:**\n> Despite its industrial prosperity, Korattur faces challenges typical of urban areas, including traffic congestion and water scarcity. Despite these challenges, with its strategic location and ongoing initiatives, Korattur continues to thrive as an integral part of Chennai's growth.\n\n**After:**\n> Traffic congestion increased after 2015 when three new IT parks opened. The municipal corporation began a stormwater drainage project in 2022 to address recurring floods.\n\n---\n\n## LANGUAGE AND GRAMMAR PATTERNS\n\n### 7. Overused \"AI Vocabulary\" Words\n\n**High-frequency AI words:** Additionally, align with, crucial, delve, emphasizing, enduring, enhance, fostering, garner, highlight (verb), interplay, intricate/intricacies, key (adjective), landscape (abstract noun), pivotal, showcase, tapestry (abstract noun), testament, underscore (verb), valuable, vibrant\n\n**Problem:** These words appear far more frequently in post-2023 text. They often co-occur.\n\n**Before:**\n> Additionally, a distinctive feature of Somali cuisine is the incorporation of camel meat. An enduring testament to Italian colonial influence is the widespread adoption of pasta in the local culinary landscape, showcasing how these dishes have integrated into the traditional diet.\n\n**After:**\n> Somali cuisine also includes camel meat, which is considered a delicacy. Pasta dishes, introduced during Italian colonization, remain common, especially in the south.\n\n---\n\n### 8. Avoidance of \"is\"/\"are\" (Copula Avoidance)\n\n**Words to watch:** serves as/stands as/marks/represents [a], boasts/features/offers [a]\n\n**Problem:** LLMs substitute elaborate constructions for simple copulas.\n\n**Before:**\n> Gallery 825 serves as LAAA's exhibition space for contemporary art. The gallery features four separate spaces and boasts over 3,000 square feet.\n\n**After:**\n> Gallery 825 is LAAA's exhibition space for contemporary art. The gallery has four rooms totaling 3,000 square feet.\n\n---\n\n### 9. Negative Parallelisms\n\n**Problem:** Constructions like \"Not only...but...\" or \"It's not just about..., it's...\" are overused.\n\n**Before:**\n> It's not just about the beat riding under the vocals; it's part of the aggression and atmosphere. It's not merely a song, it's a statement.\n\n**After:**\n> The heavy beat adds to the aggressive tone.\n\n---\n\n### 10. Rule of Three Overuse\n\n**Problem:** LLMs force ideas into groups of three to appear comprehensive.\n\n**Before:**\n> The event features keynote sessions, panel discussions, and networking opportunities. Attendees can expect innovation, inspiration, and industry insights.\n\n**After:**\n> The event includes talks and panels. There's also time for informal networking between sessions.\n\n---\n\n### 11. Elegant Variation (Synonym Cycling)\n\n**Problem:** AI has repetition-penalty code causing excessive synonym substitution.\n\n**Before:**\n> The protagonist faces many challenges. The main character must overcome obstacles. The central figure eventually triumphs. The hero returns home.\n\n**After:**\n> The protagonist faces many challenges but eventually triumphs and returns home.\n\n---\n\n### 12. False Ranges\n\n**Problem:** LLMs use \"from X to Y\" constructions where X and Y aren't on a meaningful scale.\n\n**Before:**\n> Our journey through the universe has taken us from the singularity of the Big Bang to the grand cosmic web, from the birth and death of stars to the enigmatic dance of dark matter.\n\n**After:**\n> The book covers the Big Bang, star formation, and current theories about dark matter.\n\n---\n\n## STYLE PATTERNS\n\n### 13. Em Dash Overuse\n\n**Problem:** LLMs use em dashes (—) more than humans, mimicking \"punchy\" sales writing.\n\n**Before:**\n> The term is primarily promoted by Dutch institutions—not by the people themselves. You don't say \"Netherlands, Europe\" as an address—yet this mislabeling continues—even in official documents.\n\n**After:**\n> The term is primarily promoted by Dutch institutions, not by the people themselves. You don't say \"Netherlands, Europe\" as an address, yet this mislabeling continues in official documents.\n\n---\n\n### 14. Overuse of Boldface\n\n**Problem:** AI chatbots emphasize phrases in boldface mechanically.\n\n**Before:**\n> It blends **OKRs (Objectives and Key Results)**, **KPIs (Key Performance Indicators)**, and visual strategy tools such as the **Business Model Canvas (BMC)** and **Balanced Scorecard (BSC)**.\n\n**After:**\n> It blends OKRs, KPIs, and visual strategy tools like the Business Model Canvas and Balanced Scorecard.\n\n---\n\n### 15. Inline-Header Vertical Lists\n\n**Problem:** AI outputs lists where items start with bolded headers followed by colons.\n\n**Before:**\n> - **User Experience:** The user experience has been significantly improved with a new interface.\n> - **Performance:** Performance has been enhanced through optimized algorithms.\n> - **Security:** Security has been strengthened with end-to-end encryption.\n\n**After:**\n> The update improves the interface, speeds up load times through optimized algorithms, and adds end-to-end encryption.\n\n---\n\n### 16. Title Case in Headings\n\n**Problem:** AI chatbots capitalize all main words in headings.\n\n**Before:**\n> ## Strategic Negotiations And Global Partnerships\n\n**After:**\n> ## Strategic negotiations and global partnerships\n\n---\n\n### 17. Emojis\n\n**Problem:** AI chatbots often decorate headings or bullet points with emojis.\n\n**Before:**\n> 🚀 **Launch Phase:** The product launches in Q3\n> 💡 **Key Insight:** Users prefer simplicity\n> ✅ **Next Steps:** Schedule follow-up meeting\n\n**After:**\n> The product launches in Q3. User research showed a preference for simplicity. Next step: schedule a follow-up meeting.\n\n---\n\n### 18. Curly Quotation Marks\n\n**Problem:** ChatGPT uses curly quotes (“...”) instead of straight quotes (\"...\").\n\n**Before:**\n> He said “the project is on track” but others disagreed.\n\n**After:**\n> He said \"the project is on track\" but others disagreed.\n\n---\n\n## COMMUNICATION PATTERNS\n\n### 19. Collaborative Communication Artifacts\n\n**Words to watch:** I hope this helps, Of course!, Certainly!, You're absolutely right!, Would you like..., let me know, here is a...\n\n**Problem:** Text meant as chatbot correspondence gets pasted as content.\n\n**Before:**\n> Here is an overview of the French Revolution. I hope this helps! Let me know if you'd like me to expand on any section.\n\n**After:**\n> The French Revolution began in 1789 when financial crisis and food shortages led to widespread unrest.\n\n---\n\n### 20. Knowledge-Cutoff Disclaimers\n\n**Words to watch:** as of [date], Up to my last training update, While specific details are limited/scarce..., based on available information...\n\n**Problem:** AI disclaimers about incomplete information get left in text.\n\n**Before:**\n> While specific details about the company's founding are not extensively documented in readily available sources, it appears to have been established sometime in the 1990s.\n\n**After:**\n> The company was founded in 1994, according to its registration documents.\n\n---\n\n### 21. Sycophantic/Servile Tone\n\n**Problem:** Overly positive, people-pleasing language.\n\n**Before:**\n> Great question! You're absolutely right that this is a complex topic. That's an excellent point about the economic factors.\n\n**After:**\n> The economic factors you mentioned are relevant here.\n\n---\n\n## FILLER AND HEDGING\n\n### 22. Filler Phrases\n\n**Before → After:**\n- \"In order to achieve this goal\" → \"To achieve this\"\n- \"Due to the fact that it was raining\" → \"Because it was raining\"\n- \"At this point in time\" → \"Now\"\n- \"In the event that you need help\" → \"If you need help\"\n- \"The system has the ability to process\" → \"The system can process\"\n- \"It is important to note that the data shows\" → \"The data shows\"\n\n---\n\n### 23. Excessive Hedging\n\n**Problem:** Over-qualifying statements.\n\n**Before:**\n> It could potentially possibly be argued that the policy might have some effect on outcomes.\n\n**After:**\n> The policy may affect outcomes.\n\n---\n\n### 24. Generic Positive Conclusions\n\n**Problem:** Vague upbeat endings.\n\n**Before:**\n> The future looks bright for the company. Exciting times lie ahead as they continue their journey toward excellence. This represents a major step in the right direction.\n\n**After:**\n> The company plans to open two more locations next year.\n\n---\n\n## Process\n\n1. Read the input text carefully\n2. Identify all instances of the patterns above\n3. Rewrite each problematic section\n4. Ensure the revised text:\n - Sounds natural when read aloud\n - Varies sentence structure naturally\n - Uses specific details over vague claims\n - Maintains appropriate tone for context\n - Uses simple constructions (is/are/has) where appropriate\n5. Present the humanized version\n\n## Output Format\n\nProvide:\n1. The rewritten text\n2. A brief summary of changes made (optional, if helpful)\n\n---\n\n## Full Example\n\n**Before (AI-sounding):**\n> The new software update serves as a testament to the company's commitment to innovation. Moreover, it provides a seamless, intuitive, and powerful user experience—ensuring that users can accomplish their goals efficiently. It's not just an update, it's a revolution in how we think about productivity. Industry experts believe this will have a lasting impact on the entire sector, highlighting the company's pivotal role in the evolving technological landscape.\n\n**After (Humanized):**\n> The software update adds batch processing, keyboard shortcuts, and offline mode. Early feedback from beta testers has been positive, with most reporting faster task completion.\n\n**Changes made:**\n- Removed \"serves as a testament\" (inflated symbolism)\n- Removed \"Moreover\" (AI vocabulary)\n- Removed \"seamless, intuitive, and powerful\" (rule of three + promotional)\n- Removed em dash and \"-ensuring\" phrase (superficial analysis)\n- Removed \"It's not just...it's...\" (negative parallelism)\n- Removed \"Industry experts believe\" (vague attribution)\n- Removed \"pivotal role\" and \"evolving landscape\" (AI vocabulary)\n- Added specific features and concrete feedback\n\n---\n\n## Reference\n\nThis skill is based on [Wikipedia:Signs of AI writing](https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing), maintained by WikiProject AI Cleanup. The patterns documented there come from observations of thousands of instances of AI-generated text on Wikipedia.\n\nKey insight from Wikipedia: \"LLMs use statistical algorithms to guess what should come next. The result tends toward the most statistically likely result that applies to the widest variety of cases.\"\n", "source_url": "https://clawhub.ai/biostartechnology/humanizer", "repository_url": "https://github.com/biostartechnology/humanizer", "categories": [], "tags": [], "status": "approved", "featured": 0, "review_note": null, "approved_at": null, "approved_by": null, "created_at": "2026-01-24T05:15:36.865Z", "updated_at": "2026-02-26T00:30:40.450Z", "stars_total": 311, "stars_clawhub": 311, "stars_ours": 0, "downloads": 36646, "installs_current": 371, "installs_all_time": 379, "author": { "citizen_id": null, "handle": "biostartechnology", "display_name": "biostartechnology", "tier": null, "trust": null, "reputation": null } }, { "id": "b8fb3da5-04c3-4655-bd99-db59895daba9", "owner_account_id": "b9a8f519-797e-4320-bb85-6834738d6676", "slug": "github", "name": "Github", "summary": "Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.", "content_md": "---\nname: github\ndescription: \"Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.\"\n---\n\n# GitHub Skill\n\nUse the `gh` CLI to interact with GitHub. Always specify `--repo owner/repo` when not in a git directory, or use URLs directly.\n\n## Pull Requests\n\nCheck CI status on a PR:\n```bash\ngh pr checks 55 --repo owner/repo\n```\n\nList recent workflow runs:\n```bash\ngh run list --repo owner/repo --limit 10\n```\n\nView a run and see which steps failed:\n```bash\ngh run view --repo owner/repo\n```\n\nView logs for failed steps only:\n```bash\ngh run view --repo owner/repo --log-failed\n```\n\n## API for Advanced Queries\n\nThe `gh api` command is useful for accessing data not available through other subcommands.\n\nGet PR with specific fields:\n```bash\ngh api repos/owner/repo/pulls/55 --jq '.title, .state, .user.login'\n```\n\n## JSON Output\n\nMost commands support `--json` for structured output. You can use `--jq` to filter:\n\n```bash\ngh issue list --repo owner/repo --json number,title --jq '.[] | \"\\(.number): \\(.title)\"'\n```\n", "source_url": "https://clawhub.ai/steipete/github", "repository_url": "https://github.com/steipete/github", "categories": [], "tags": [], "status": "approved", "featured": 0, "review_note": null, "approved_at": null, "approved_by": null, "created_at": "2026-01-04T16:49:04.344Z", "updated_at": "2026-02-26T00:30:40.450Z", "stars_total": 249, "stars_clawhub": 249, "stars_ours": 0, "downloads": 75366, "installs_current": 1605, "installs_all_time": 1642, "author": { "citizen_id": null, "handle": "steipete", "display_name": "steipete", "tier": null, "trust": null, "reputation": null } }, { "id": "241e95e9-f31c-4da5-be39-3719564a36f4", "owner_account_id": "b9a8f519-797e-4320-bb85-6834738d6676", "slug": "weather", "name": "Weather", "summary": "Get current weather and forecasts (no API key required).", "content_md": "---\nname: weather\ndescription: Get current weather and forecasts (no API key required).\nhomepage: https://wttr.in/:help\nmetadata: {\"clawdbot\":{\"emoji\":\"🌤️\",\"requires\":{\"bins\":[\"curl\"]}}}\n---\n\n# Weather\n\nTwo free services, no API keys needed.\n\n## wttr.in (primary)\n\nQuick one-liner:\n```bash\ncurl -s \"wttr.in/London?format=3\"\n# Output: London: ⛅️ +8°C\n```\n\nCompact format:\n```bash\ncurl -s \"wttr.in/London?format=%l:+%c+%t+%h+%w\"\n# Output: London: ⛅️ +8°C 71% ↙5km/h\n```\n\nFull forecast:\n```bash\ncurl -s \"wttr.in/London?T\"\n```\n\nFormat codes: `%c` condition · `%t` temp · `%h` humidity · `%w` wind · `%l` location · `%m` moon\n\nTips:\n- URL-encode spaces: `wttr.in/New+York`\n- Airport codes: `wttr.in/JFK`\n- Units: `?m` (metric) `?u` (USCS)\n- Today only: `?1` · Current only: `?0`\n- PNG: `curl -s \"wttr.in/Berlin.png\" -o /tmp/weather.png`\n\n## Open-Meteo (fallback, JSON)\n\nFree, no key, good for programmatic use:\n```bash\ncurl -s \"https://api.open-meteo.com/v1/forecast?latitude=51.5&longitude=-0.12¤t_weather=true\"\n```\n\nFind coordinates for a city, then query. Returns JSON with temp, windspeed, weathercode.\n\nDocs: https://open-meteo.com/en/docs\n", "source_url": "https://clawhub.ai/steipete/weather", "repository_url": "https://github.com/steipete/weather", "categories": [], "tags": [], "status": "approved", "featured": 0, "review_note": null, "approved_at": null, "approved_by": null, "created_at": "2026-01-04T16:49:54.459Z", "updated_at": "2026-03-04T09:35:22.629Z", "stars_total": 224, "stars_clawhub": 224, "stars_ours": 0, "downloads": 64247, "installs_current": 1333, "installs_all_time": 1362, "author": { "citizen_id": null, "handle": "steipete", "display_name": "steipete", "tier": null, "trust": null, "reputation": null } } ], "browse_skills": [ { "id": "bb87299d-bbd1-4b34-9b20-ccdc9d3da186", "owner_account_id": "b9a8f519-797e-4320-bb85-6834738d6676", "slug": "crypto-trading-bot", "name": "Crypto Trading Bot", "summary": "加密貨幣交易機器人開發 - 幫你整自動交易Bot，支持Pine Script、Python、CCXT API對接。適用於：(1)整TradingView信號Bot (2)CEX/DEX API自動化 (3)套利機器人 (4)止盈止損策略", "content_md": "---\nname: crypto-trading-bot\ndescription: 加密貨幣交易機器人開發 - 幫你整自動交易Bot，支持Pine Script、Python、CCXT API對接。適用於：(1)整TradingView信號Bot (2)CEX/DEX API自動化 (3)套利機器人 (4)止盈止損策略\n---\n\n# Crypto Trading Bot Developer\n\n幫你整加密貨幣自動交易機器人\n\n## 核心功能\n\n### 1. TradingView Pine Script 信号 Bot\n- 接收TradingView webhook信號\n- 自動執行買賣指令\n- 支持多交易所對接\n\n### 2. CEX 自動化交易\n- Binance, Bybit, OKX API 對接\n- 現貨/合約自動化\n- 網格交易策略\n\n### 3. DEX Arbitrage\n- 跨DEX套利機會檢測\n- Flash loan 整合（如適用）\n- 風險評估\n\n### 4. 智能止盈止損\n- 移動止損\n- 分批止盈\n- Time-based exit\n\n## 使用流程\n\n```\n1. 用戶話「整交易Bot」\n2. 問清楚：\n - 目標交易所\n - 交易對 (e.g., BTC/USDT)\n - 策略類型\n - 預算\n3. 提供報價同timeline\n```\n\n## 報價參考\n\n| 類型 | 價格範圍 |\n|------|----------|\n| 簡單信號Bot | $200-500 |\n| 網格交易 | $300-800 |\n| 複雜策略 | $1000-3000 |\n| 月費維護 | $100-300/月 |\n\n## 技術栈\n\n- Python (CCXT, pandas)\n- Pine Script\n- Node.js\n- API Webhooks\n", "source_url": "https://clawhub.ai/Katrina-jpg/crypto-trading-bot", "repository_url": "https://github.com/Katrina-jpg/crypto-trading-bot", "categories": [], "tags": [], "status": "approved", "featured": 0, "review_note": null, "approved_at": null, "approved_by": null, "created_at": "2026-02-19T23:32:16.527Z", "updated_at": "2026-02-26T00:20:40.363Z", "stars_total": 0, "stars_clawhub": 0, "stars_ours": 0, "downloads": 2431, "installs_current": 18, "installs_all_time": 18, "author": { "citizen_id": null, "handle": "Katrina-jpg", "display_name": "Katrina-jpg", "tier": null, "trust": null, "reputation": null } }, { "id": "2a69695d-a264-4f7b-839d-3ee2e6449710", "owner_account_id": "b9a8f519-797e-4320-bb85-6834738d6676", "slug": "fundamental-stock-analysis", "name": "Fundamental Stock Analysis", "summary": "Fundamental equity analysis and peer ranking using a structured scoring playbook (quality, balance-sheet safety, cash flow, valuation, sector adjustments, co...", "content_md": "---\nname: fundamental-stock-analysis\ndescription: Fundamental equity analysis and peer ranking using a structured scoring playbook (quality, balance-sheet safety, cash flow, valuation, sector adjustments, confidence modifiers). Use when a user asks to analyze one or more stock tickers, compare peers, choose a best pick, or produce a fundamentals-based verdict.\n---\n\n# fundamental-stock-analysis\n\n1. Read `references/playbook.md` before starting analysis.\n2. Follow the playbook steps exactly (input parse -> data collection -> quick screen -> scoring -> rating -> output).\n3. For multi-ticker requests, analyze each ticker first, then rank peers and select best pick with invalidation triggers.\n4. Always include confidence level and call out stale/conflicting data explicitly.\n5. Do not append any machine-readable JSON block in user-facing output.\n6. Treat all analysis as educational/informational content, not investment advice.\n\n## Security scope (clarification)\n- Use web retrieval only for ticker-relevant financial statements, filings, market/fundamental datasets, and relevant financial news.\n- Do not request, handle, or expose credentials/secrets.\n- Do not perform command execution, local file discovery unrelated to analysis, or arbitrary URL exploration outside ticker-relevant finance/news scope.\n\n## Non-goals\n- Data exfiltration or collection of private/non-public information.\n- Browser/automation tasks outside equity fundamental analysis and citation gathering.\n\n## Output discipline\n- Keep conclusions decisive and risk-aware.\n- Separate business quality, balance-sheet safety, and valuation.\n- Never fabricate missing metrics; mark `NA`.\n", "source_url": "https://clawhub.ai/NickFiorani/fundamental-stock-analysis", "repository_url": "https://github.com/NickFiorani/fundamental-stock-analysis", "categories": [], "tags": [], "status": "approved", "featured": 0, "review_note": null, "approved_at": null, "approved_by": null, "created_at": "2026-02-19T21:40:57.808Z", "updated_at": "2026-02-26T00:15:35.912Z", "stars_total": 7, "stars_clawhub": 7, "stars_ours": 0, "downloads": 3339, "installs_current": 19, "installs_all_time": 20, "author": { "citizen_id": null, "handle": "NickFiorani", "display_name": "NickFiorani", "tier": null, "trust": null, "reputation": null } }, { "id": "89b888d3-25fa-42cf-bc9a-ec66e0bdf0f6", "owner_account_id": "b9a8f519-797e-4320-bb85-6834738d6676", "slug": "ai-agent-helper", "name": "AI Agent Helper", "summary": "AI Agent 設定同優化助手 - Prompt Engineering、Task Decomposition、Agent Loop設計", "content_md": "---\nname: ai-agent-helper\ndescription: AI Agent 設定同優化助手 - Prompt Engineering、Task Decomposition、Agent Loop設計\nversion: 1.0.0\ntags:\n - ai\n - agent\n - prompt\n - automation\n - productivity\n---\n\n# AI Agent Helper\n\n幫你setup同優化AI Agents既技能。\n\n## 功能\n\n- 📝 Prompt Engineering - 整高質量system prompts\n- 🔄 Task Decomposition - 將複雜任務拆解\n- ⚙️ Agent Loop設計 - ReAct/ReAct/Chain-of-Thought\n- 🎯 Tool Selection - 最佳化agent既tool usage\n\n## 使用場景\n\n\"帮我整prompt\" / \"點樣set AI agent\" / \"優化agent response\"\n\n## 技術\n\n- System Prompt優化\n- Few-shot examples\n- Output parsing (JSON/structured)\n- Error handling patterns\n- Token優化\n\n## 範例\n\n```python\n# Good prompt structure\nsystem = \"\"\"你係{role}。\n目標：{goal}\n限制：{constraints}\nOutput格式：{format}\"\"\"\n```\n", "source_url": "https://clawhub.ai/Katrina-jpg/ai-agent-helper", "repository_url": "https://github.com/Katrina-jpg/ai-agent-helper", "categories": [], "tags": [], "status": "approved", "featured": 0, "review_note": null, "approved_at": null, "approved_by": null, "created_at": "2026-02-19T14:35:16.748Z", "updated_at": "2026-02-26T00:25:39.606Z", "stars_total": 1, "stars_clawhub": 1, "stars_ours": 0, "downloads": 2991, "installs_current": 24, "installs_all_time": 24, "author": { "citizen_id": null, "handle": "Katrina-jpg", "display_name": "Katrina-jpg", "tier": null, "trust": null, "reputation": null } }, { "id": "1e7b7f78-c395-4fc9-a8ce-a06f8eda3652", "owner_account_id": "b9a8f519-797e-4320-bb85-6834738d6676", "slug": "ddg-web-search", "name": "DuckDuckGo Web Search", "summary": "Web search without an API key using DuckDuckGo Lite via web_fetch. Use as a fallback when web_search fails with missing_brave_api_key error, or whenever you...", "content_md": "---\nname: ddg-search\ndescription: Web search without an API key using DuckDuckGo Lite via web_fetch. Use as a fallback when web_search fails with missing_brave_api_key error, or whenever you need to search the web and no search API is configured. Provides titles, URLs, and snippets for research queries. Zero dependencies — works with just the built-in web_fetch tool.\n---\n\n# DuckDuckGo Search via web_fetch\n\nSearch the web using DuckDuckGo Lite's HTML interface, parsed via `web_fetch`. No API key or package install required.\n\n## How to Search\n\n```\nweb_fetch(url=\"https://lite.duckduckgo.com/lite/?q=QUERY\", extractMode=\"text\", maxChars=8000)\n```\n\n- URL-encode the query — use `+` for spaces\n- Use `extractMode=\"text\"` (not markdown) for clean results\n- Increase `maxChars` for more results\n\n## Region Filtering\n\nAppend `&kl=REGION` for regional results:\n\n- `au-en` — Australia\n- `us-en` — United States\n- `uk-en` — United Kingdom\n- `de-de` — Germany\n- `fr-fr` — France\n\nFull list: https://duckduckgo.com/params\n\n### Example — Australian search\n\n```\nweb_fetch(url=\"https://lite.duckduckgo.com/lite/?q=best+coffee+melbourne&kl=au-en\", extractMode=\"text\", maxChars=8000)\n```\n\n## Reading Results\n\nResults appear as numbered items with title, snippet, and URL. Skip entries marked \"Sponsored link\" (ads) — organic results follow.\n\n## Search-then-Fetch Pattern\n\n1. **Search** — query DDG Lite for a list of results\n2. **Pick** — identify the most relevant URLs\n3. **Fetch** — use `web_fetch` on those URLs to read full content\n\n## Tips\n\n- First 1-2 results may be ads — skip to organic results\n- For exact phrases, wrap in quotes: `q=%22exact+phrase%22`\n- Add specific terms to narrow results (site name, year, location)\n\n## Limitations\n\n- No time/date filtering (DDG Lite doesn't support `&df=` reliably via fetch)\n- Text results only — no images or videos\n- Results sourced from Bing (may differ from Google)\n- Google search does NOT work via web_fetch (captcha blocked)\n", "source_url": "https://clawhub.ai/JakeLin/ddg-web-search", "repository_url": "https://github.com/JakeLin/ddg-web-search", "categories": [], "tags": [], "status": "approved", "featured": 0, "review_note": null, "approved_at": null, "approved_by": null, "created_at": "2026-02-15T09:34:14.829Z", "updated_at": "2026-02-26T00:25:39.606Z", "stars_total": 6, "stars_clawhub": 6, "stars_ours": 0, "downloads": 9426, "installs_current": 79, "installs_all_time": 83, "author": { "citizen_id": null, "handle": "JakeLin", "display_name": "JakeLin", "tier": null, "trust": null, "reputation": null } }, { "id": "92df16bc-8955-4fa0-9617-e93bf64129ea", "owner_account_id": "b9a8f519-797e-4320-bb85-6834738d6676", "slug": "crawl-for-ai", "name": "Crawl4AI Web Scraper", "summary": "Full web page scraping with JavaScript rendering via local Crawl4AI instance, delivering clean markdown or detailed JSON including links and media.", "content_md": "---\nname: crawl-for-ai\ndescription: Web scraping using local Crawl4AI instance. Use for fetching full page content with JavaScript rendering. Better than Tavily for complex pages. Unlimited usage.\nversion: 1.0.1\nauthor: Ania\nrequiresEnv:\n - CRAWL4AI_URL\nmetadata:\n clawdbot:\n emoji: \"🕷️\"\n requires:\n bins: [\"node\"]\n---\n\n# Crawl4AI Web Scraper\n\nLocal Crawl4AI instance for full web page extraction with JavaScript rendering.\n\n## Endpoints\n\n**Proxy (port 11234)** — Clean output, OpenWebUI-compatible\n- Returns: `[{page_content, metadata}]`\n- Use for: Simple content extraction\n\n**Direct (port 11235)** — Full output with all data\n- Returns: `{results: [{markdown, html, links, media, ...}]}`\n- Use for: When you need links, media, or other metadata\n\n## Usage\n\n```bash\n# Via script\nnode {baseDir}/scripts/crawl4ai.js \"url\"\nnode {baseDir}/scripts/crawl4ai.js \"url\" --json\n```\n\n**Script options:**\n- `--json` — Full JSON response\n\n**Output:** Clean markdown from the page.\n\n## Configuration\n\n**Required environment variable:**\n\n- `CRAWL4AI_URL` — Your Crawl4AI instance URL (e.g., `http://localhost:11235`)\n\n**Optional:**\n\n- `CRAWL4AI_KEY` — API key if your instance requires authentication\n\n## Features\n\n- **JavaScript rendering** — Handles dynamic content\n- **Unlimited usage** — Local instance, no API limits\n- **Full content** — HTML, markdown, links, media, tables\n- **Better than Tavily** for complex pages with JS\n\n## API\n\nUses your local Crawl4AI instance REST API. Auth header only sent if `CRAWL4AI_KEY` is set.", "source_url": "https://clawhub.ai/angusthefuzz/crawl-for-ai", "repository_url": "https://github.com/angusthefuzz/crawl-for-ai", "categories": [], "tags": [], "status": "approved", "featured": 0, "review_note": null, "approved_at": null, "approved_by": null, "created_at": "2026-02-14T19:42:29.345Z", "updated_at": "2026-02-26T00:15:40.106Z", "stars_total": 4, "stars_clawhub": 4, "stars_ours": 0, "downloads": 2113, "installs_current": 8, "installs_all_time": 8, "author": { "citizen_id": null, "handle": "angusthefuzz", "display_name": "angusthefuzz", "tier": null, "trust": null, "reputation": null } }, { "id": "a4b854f7-aeca-41e0-9200-ca6b361486db", "owner_account_id": "b9a8f519-797e-4320-bb85-6834738d6676", "slug": "market-research-agent", "name": "Market Research Agent", "summary": "Conduct structured market research on any industry, competitor, or opportunity. Analyze market size, trends, competitors, and customer segments with a proven framework.", "content_md": "---\nname: Market Research Agent\ndescription: Conduct structured market research on any industry, competitor, or opportunity. Analyze market size, trends, competitors, and customer segments with a proven framework.\n---\n\n# Market Research Agent\n\nYou are a market research analyst. Help users conduct thorough, structured research on markets, industries, competitors, and opportunities.\n\n## Research Frameworks\n\n### 1. Market Overview\nWhen asked to research a market, provide:\n- **Market Definition**: What exactly is this market?\n- **Market Size**: TAM, SAM, SOM estimates with reasoning\n- **Growth Rate**: Historical and projected CAGR\n- **Key Trends**: 5-7 trends shaping this market\n- **Market Drivers**: What's fueling growth\n- **Market Barriers**: What's holding it back\n\n### 2. Competitive Landscape\n- **Direct Competitors**: Companies solving the same problem\n- **Indirect Competitors**: Alternative solutions\n- **Competitor Matrix**: Compare on price, features, market position, strengths, weaknesses\n- **Market Gaps**: Underserved segments or unmet needs\n- **Competitive Advantages**: What would it take to win\n\n### 3. Customer Analysis\n- **Customer Segments**: Who buys in this market\n- **Buyer Personas**: Demographics, psychographics, behaviors\n- **Pain Points**: Top 5 problems customers face\n- **Buying Criteria**: How they evaluate solutions\n- **Willingness to Pay**: Price sensitivity analysis\n\n### 4. SWOT Analysis\nStrengths, Weaknesses, Opportunities, Threats — structured and specific.\n\n### 5. Porter's Five Forces\nAnalyze: supplier power, buyer power, competitive rivalry, threat of substitution, threat of new entry.\n\n### 6. Go-to-Market Insights\n- Best channels to reach customers\n- Pricing models common in this space\n- Sales cycle expectations\n- Key partnerships to consider\n\n## Output Standards\n- Always cite reasoning and assumptions\n- Separate facts from estimates\n- Use tables for comparisons\n- End with actionable recommendations\n- Flag areas needing primary research\n", "source_url": "https://clawhub.ai/1kalin/market-research-agent", "repository_url": "https://github.com/1kalin/market-research-agent", "categories": [], "tags": [], "status": "approved", "featured": 0, "review_note": null, "approved_at": null, "approved_by": null, "created_at": "2026-02-13T02:52:02.797Z", "updated_at": "2026-02-26T00:00:35.886Z", "stars_total": 11, "stars_clawhub": 11, "stars_ours": 0, "downloads": 1798, "installs_current": 5, "installs_all_time": 5, "author": { "citizen_id": null, "handle": "1kalin", "display_name": "1kalin", "tier": null, "trust": null, "reputation": null } }, { "id": "f30589cb-ec22-4ca4-85a1-ce63d2ef4647", "owner_account_id": "b9a8f519-797e-4320-bb85-6834738d6676", "slug": "agent-team-orchestration", "name": "Agent Team Orchestration", "summary": "Orchestrate multi-agent teams with defined roles, task lifecycles, handoff protocols, and review workflows. Use when: (1) Setting up a team of 2+ agents with different specializations, (2) Defining task routing and lifecycle (inbox → spec → build → review → done), (3) Creating handoff protocols between agents, (4) Establishing review and quality gates, (5) Managing async communication and artifact sharing between agents.", "content_md": "---\nname: agent-team-orchestration\ndescription: \"Orchestrate multi-agent teams with defined roles, task lifecycles, handoff protocols, and review workflows. Use when: (1) Setting up a team of 2+ agents with different specializations, (2) Defining task routing and lifecycle (inbox → spec → build → review → done), (3) Creating handoff protocols between agents, (4) Establishing review and quality gates, (5) Managing async communication and artifact sharing between agents.\"\n---\n\n# Agent Team Orchestration\n\nProduction playbook for running multi-agent teams with clear roles, structured task flow, and quality gates.\n\n## Quick Start: Minimal 2-Agent Team\n\nA builder and a reviewer. The simplest useful team.\n\n### 1. Define Roles\n\n```\nOrchestrator (you) — Route tasks, track state, report results\nBuilder agent — Execute work, produce artifacts\n```\n\n### 2. Spawn a Task\n\n```\n1. Create task record (file, DB, or task board)\n2. Spawn builder with:\n - Task ID and description\n - Output path for artifacts\n - Handoff instructions (what to produce, where to put it)\n3. On completion: review artifacts, mark done, report\n```\n\n### 3. Add a Reviewer\n\n```\nBuilder produces artifact → Reviewer checks it → Orchestrator ships or returns\n```\n\nThat's the core loop. Everything below scales this pattern.\n\n## Core Concepts\n\n### Roles\n\nEvery agent has one primary role. Overlap causes confusion.\n\n| Role | Purpose | Model guidance |\n|------|---------|---------------|\n| **Orchestrator** | Route work, track state, make priority calls | High-reasoning model (handles judgment) |\n| **Builder** | Produce artifacts — code, docs, configs | Can use cost-effective models for mechanical work |\n| **Reviewer** | Verify quality, push back on gaps | High-reasoning model (catches what builders miss) |\n| **Ops** | Cron jobs, standups, health checks, dispatching | Cheapest model that's reliable |\n\n→ *Read [references/team-setup.md](references/team-setup.md) when defining a new team or adding agents.*\n\n### Task States\n\nEvery task moves through a defined lifecycle:\n\n```\nInbox → Assigned → In Progress → Review → Done | Failed\n```\n\n**Rules:**\n- Orchestrator owns state transitions — don't rely on agents to update their own status\n- Every transition gets a comment (who, what, why)\n- Failed is a valid end state — capture why and move on\n\n→ *Read [references/task-lifecycle.md](references/task-lifecycle.md) when designing task flows or debugging stuck tasks.*\n\n### Handoffs\n\nWhen work passes between agents, the handoff message includes:\n\n1. **What was done** — summary of changes/output\n2. **Where artifacts are** — exact file paths\n3. **How to verify** — test commands or acceptance criteria\n4. **Known issues** — anything incomplete or risky\n5. **What's next** — clear next action for the receiving agent\n\nBad handoff: *\"Done, check the files.\"*\nGood handoff: *\"Built auth module at `/shared/artifacts/auth/`. Run `npm test auth` to verify. Known issue: rate limiting not implemented yet. Next: reviewer checks error handling edge cases.\"*\n\n### Reviews\n\nCross-role reviews prevent quality drift:\n\n- **Builders review specs** — \"Is this feasible? What's missing?\"\n- **Reviewers check builds** — \"Does this match the spec? Edge cases?\"\n- **Orchestrator reviews priorities** — \"Is this the right work right now?\"\n\nSkip the review step and quality degrades within 3-5 tasks. Every time.\n\n→ *Read [references/communication.md](references/communication.md) when setting up agent communication channels.*\n→ *Read [references/patterns.md](references/patterns.md) for proven multi-step workflows.*\n\n## Reference Files\n\n| File | Read when... |\n|------|-------------|\n| [team-setup.md](references/team-setup.md) | Defining agents, roles, models, workspaces |\n| [task-lifecycle.md](references/task-lifecycle.md) | Designing task states, transitions, comments |\n| [communication.md](references/communication.md) | Setting up async/sync communication, artifact paths |\n| [patterns.md](references/patterns.md) | Implementing specific workflows (spec→build→test, parallel research, escalation) |\n\n## Common Pitfalls\n\n### Spawning without clear artifact output paths\nAgent produces great work, but you can't find it. Always specify the exact output path in the spawn prompt. Use a shared artifacts directory with predictable structure.\n\n### No review step = quality drift\n\"It's a small change, skip review.\" Do this three times and you have compounding errors. Every artifact gets at least one set of eyes that didn't produce it.\n\n### Agents not commenting on task progress\nSilent agents create coordination blind spots. Require comments at: start, blocker, handoff, completion. If an agent goes silent, assume it's stuck.\n\n### Not verifying agent capabilities before assigning\nAssigning browser-based testing to an agent without browser access. Assigning image work to a text-only model. Check capabilities before routing.\n\n### Orchestrator doing execution work\nThe orchestrator routes and tracks — it doesn't build. The moment you start \"just quickly doing this one thing,\" you've lost oversight of the rest of the team.\n\n## When NOT to Use This Skill\n\n- **Single-agent setups** — Just follow standard AGENTS.md conventions. Team orchestration adds overhead that solo agents don't need.\n- **One-off task delegation** — Use `sessions_spawn` directly. This skill is for sustained workflows with multiple handoffs.\n- **Simple question routing** — If you're just forwarding a question to a specialist, that's a message, not a workflow.\n\nThis skill is for **sustained team workflows** — recurring collaboration patterns where agents depend on each other's output over multiple tasks.\n", "source_url": "https://clawhub.ai/arminnaimi/agent-team-orchestration", "repository_url": "https://github.com/arminnaimi/agent-team-orchestration", "categories": [], "tags": [], "status": "approved", "featured": 0, "review_note": null, "approved_at": null, "approved_by": null, "created_at": "2026-02-12T16:00:01.303Z", "updated_at": "2026-02-26T00:30:40.450Z", "stars_total": 19, "stars_clawhub": 19, "stars_ours": 0, "downloads": 6158, "installs_current": 58, "installs_all_time": 60, "author": { "citizen_id": null, "handle": "arminnaimi", "display_name": "arminnaimi", "tier": null, "trust": null, "reputation": null } }, { "id": "d142636f-ea18-47d8-afe4-c72206205a96", "owner_account_id": "b9a8f519-797e-4320-bb85-6834738d6676", "slug": "system-resource-monitor", "name": "System Resource Monitor", "summary": "A clean, reliable system resource monitor for CPU load, RAM, Swap, and Disk usage. Optimized for OpenClaw.", "content_md": "---\nname: system_resource_monitor\ndescription: A clean, reliable system resource monitor for CPU load, RAM, Swap, and Disk usage. Optimized for OpenClaw.\nversion: 1.0.0\nauthor: Yennefer & Geralt\n---\n\n# System Resource Monitor\n\nA specialized skill designed to provide concise, real-time server health reports. Unlike bloated alternatives, it uses native system calls for maximum reliability and speed.\n\n## Features\n- **CPU Load**: Displays 1, 5, and 15-minute averages.\n- **Memory**: Tracks both physical RAM and Swap usage.\n- **Disk**: Monitors root partition capacity and percentage.\n- **Uptime**: Shows how long your \"horse\" has been running.\n\n## Usage\nSimply ask the agent for \"system status\", \"resource usage\", or \"server health\".\nThe skill executes the local `./scripts/monitor.sh` script.\n", "source_url": "https://clawhub.ai/Passersss/system-resource-monitor", "repository_url": "https://github.com/Passersss/system-resource-monitor", "categories": [], "tags": [], "status": "approved", "featured": 0, "review_note": null, "approved_at": null, "approved_by": null, "created_at": "2026-02-12T07:23:18.112Z", "updated_at": "2026-02-25T23:35:36.181Z", "stars_total": 1, "stars_clawhub": 1, "stars_ours": 0, "downloads": 3786, "installs_current": 31, "installs_all_time": 31, "author": { "citizen_id": null, "handle": "Passersss", "display_name": "Passersss", "tier": null, "trust": null, "reputation": null } }, { "id": "9dccbe60-7278-427c-a582-8ce0ebe4edc5", "owner_account_id": "b9a8f519-797e-4320-bb85-6834738d6676", "slug": "xpoz-social-search", "name": "Xpoz Social Search", "summary": "Search Twitter, Instagram, and Reddit posts in real time. Find social media mentions, track hashtags, discover influencers, and analyze engagement — 1.5B+ posts indexed. Social listening, brand monitoring, and competitor research made easy for AI agents.", "content_md": "---\nname: xpoz-social-search\ndescription: \"Search Twitter, Instagram, and Reddit posts in real time. Find social media mentions, track hashtags, discover influencers, and analyze engagement — 1.5B+ posts indexed. Social listening, brand monitoring, and competitor research made easy for AI agents.\"\nhomepage: https://xpoz.ai\nmetadata:\n {\n \"openclaw\":\n {\n \"requires\": { \"bins\": [\"mcporter\"], \"skills\": [\"xpoz-setup\"], \"network\": [\"mcp.xpoz.ai\"], \"credentials\": \"Xpoz account (free tier) — auth via xpoz-setup skill (OAuth 2.1)\" },\n \"install\": [{\"id\": \"node\", \"kind\": \"node\", \"package\": \"mcporter\", \"bins\": [\"mcporter\"], \"label\": \"Install mcporter (npm)\"}],\n },\n }\ntags:\n - social-media\n - search\n - twitter\n - instagram\n - reddit\n - mcp\n - xpoz\n - research\n - intelligence\n - discovery\n - social-search\n - twitter-search\n - social-listening\n - brand-monitoring\n - hashtag\n - mentions\n - influencer\n - engagement\n - viral\n - trending\n---\n\n# Xpoz Social Search\n\n**Multi-platform social search: 1.5B+ posts across Twitter, Instagram, Reddit.**\n\nSearch posts, find people, discover conversations. Built on Xpoz MCP.\n\n## Setup\n\nRun `xpoz-setup` skill. Verify: `mcporter call xpoz.checkAccessKeyStatus`\n\n## Tool Reference\n\n| Tool | Platform | Purpose |\n|------|----------|---------|\n| `getTwitterPostsByKeywords` | Twitter | Search tweets |\n| `getInstagramPostsByKeywords` | Instagram | Search posts |\n| `getRedditPostsByKeywords` | Reddit | Search posts |\n| `getTwitterUsersByKeywords` | Twitter | Find users |\n| `getInstagramUsersByKeywords` | Instagram | Find users |\n| `getRedditUsersByKeywords` | Reddit | Find users |\n| `getTwitterUser` | Twitter | Profile by username/id |\n| `getInstagramUser` | Instagram | Profile by username/id |\n| `getRedditUser` | Reddit | Profile by username |\n| `searchTwitterUsers` | Twitter | Search by name |\n| `checkOperationStatus` | — | **Poll for results** |\n| `getRedditSubredditsByKeywords` | Reddit | Find subreddits |\n\n**Params:** `query`, `startDate`/`endDate` (YYYY-MM-DD), `limit`, `fields`\n\n## Patterns\n\n**Search posts:**\n```bash\nmcporter call xpoz.getTwitterPostsByKeywords query=\"MCP\" startDate=2026-01-01\nmcporter call xpoz.checkOperationStatus operationId=op_abc # Poll every 5s\n```\n\n**Find people:**\n```bash\nmcporter call xpoz.getTwitterUsersByKeywords query='\"open source\" AND LLM'\n```\n\n**Profile:**\n```bash\nmcporter call xpoz.getTwitterUser identifier=elonmusk identifierType=username\n```\n\n**Boolean:** `AND`, `OR`, `NOT`, `\"exact\"`, `()`\n```bash\nquery=\"Tesla AND cars NOT stock\"\n```\n\n**CSV export:** Use `dataDumpExportOperationId` from search, poll for URL (up to 64K rows).\n\n## Examples\n\n**Competitive intel:**\n```bash\nmcporter call xpoz.getTwitterPostsByKeywords query=\"CompetitorName\"\nmcporter call xpoz.getTwitterUsersByKeywords query=\"CompetitorName\"\n```\n\n**Influencers:**\n```bash\nmcporter call xpoz.getInstagramUsersByKeywords query=\"fitness transformation\"\n```\n\n**Communities:**\n```bash\nmcporter call xpoz.getRedditSubredditsByKeywords query=\"startup\"\n```\n\n## Notes\n\n⚠️ **Always poll** `checkOperationStatus` — searches return `operationId`, not data \n🚀 **Use `fields`** for performance \n📊 **CSV for scale** via `dataDumpExportOperationId` \n📅 **Dates:** `YYYY-MM-DD` (current: 2026)\n\n**Free tier:** 100 searches/mo, 1K results/search | [xpoz.ai](https://xpoz.ai)\n", "source_url": "https://clawhub.ai/atyachin/xpoz-social-search", "repository_url": "https://github.com/atyachin/xpoz-social-search", "categories": [], "tags": [], "status": "approved", "featured": 0, "review_note": null, "approved_at": null, "approved_by": null, "created_at": "2026-02-11T17:53:37.441Z", "updated_at": "2026-02-25T23:40:35.980Z", "stars_total": 6, "stars_clawhub": 6, "stars_ours": 0, "downloads": 1652, "installs_current": 7, "installs_all_time": 7, "author": { "citizen_id": null, "handle": "atyachin", "display_name": "atyachin", "tier": null, "trust": null, "reputation": null } }, { "id": "f4ed85a9-d26c-4ed7-baf6-8133e83b6f5c", "owner_account_id": "b9a8f519-797e-4320-bb85-6834738d6676", "slug": "beehiiv", "name": "beehiiv", "summary": "beehiiv API integration with managed OAuth. Manage newsletter publications, subscriptions, posts, custom fields, segments, and automations.\nUse this skill when users want to manage newsletter subscribers, create posts, organize segments, or integrate with beehiiv publications.\nFor other third party apps, use the api-gateway skill (https://clawhub.ai/byungkyu/api-gateway).\nRequires network access and valid Maton API key.", "content_md": "---\nname: beehiiv\ndescription: |\n beehiiv API integration with managed OAuth. Manage newsletter publications, subscriptions, posts, custom fields, segments, and automations.\n Use this skill when users want to manage newsletter subscribers, create posts, organize segments, or integrate with beehiiv publications.\n For other third party apps, use the api-gateway skill (https://clawhub.ai/byungkyu/api-gateway).\n Requires network access and valid Maton API key.\nmetadata:\n author: maton\n version: \"1.0\"\n clawdbot:\n emoji: 🧠\n requires:\n env:\n - MATON_API_KEY\n---\n\n# beehiiv\n\nAccess the beehiiv API with managed OAuth authentication. Manage newsletter publications, subscriptions, posts, custom fields, segments, tiers, and automations.\n\n## Quick Start\n\n```bash\n# List publications\npython <<'EOF'\nimport urllib.request, os, json\nreq = urllib.request.Request('https://gateway.maton.ai/beehiiv/v2/publications')\nreq.add_header('Authorization', f'Bearer {os.environ[\"MATON_API_KEY\"]}')\nprint(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))\nEOF\n```\n\n## Base URL\n\n```\nhttps://gateway.maton.ai/beehiiv/{native-api-path}\n```\n\nReplace `{native-api-path}` with the actual beehiiv API endpoint path. The gateway proxies requests to `api.beehiiv.com` and automatically injects your OAuth token.\n\n## Authentication\n\nAll requests require the Maton API key in the Authorization header:\n\n```\nAuthorization: Bearer $MATON_API_KEY\n```\n\n**Environment Variable:** Set your API key as `MATON_API_KEY`:\n\n```bash\nexport MATON_API_KEY=\"YOUR_API_KEY\"\n```\n\n### Getting Your API Key\n\n1. Sign in or create an account at [maton.ai](https://maton.ai)\n2. Go to [maton.ai/settings](https://maton.ai/settings)\n3. Copy your API key\n\n## Connection Management\n\nManage your beehiiv OAuth connections at `https://ctrl.maton.ai`.\n\n### List Connections\n\n```bash\npython <<'EOF'\nimport urllib.request, os, json\nreq = urllib.request.Request('https://ctrl.maton.ai/connections?app=beehiiv&status=ACTIVE')\nreq.add_header('Authorization', f'Bearer {os.environ[\"MATON_API_KEY\"]}')\nprint(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))\nEOF\n```\n\n### Create Connection\n\n```bash\npython <<'EOF'\nimport urllib.request, os, json\ndata = json.dumps({'app': 'beehiiv'}).encode()\nreq = urllib.request.Request('https://ctrl.maton.ai/connections', data=data, method='POST')\nreq.add_header('Authorization', f'Bearer {os.environ[\"MATON_API_KEY\"]}')\nreq.add_header('Content-Type', 'application/json')\nprint(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))\nEOF\n```\n\n### Get Connection\n\n```bash\npython <<'EOF'\nimport urllib.request, os, json\nreq = urllib.request.Request('https://ctrl.maton.ai/connections/{connection_id}')\nreq.add_header('Authorization', f'Bearer {os.environ[\"MATON_API_KEY\"]}')\nprint(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))\nEOF\n```\n\n**Response:**\n```json\n{\n \"connection\": {\n \"connection_id\": \"8bfe17f4-0038-4cbd-afb4-907b1ffa9d66\",\n \"status\": \"ACTIVE\",\n \"creation_time\": \"2026-02-11T00:25:10.464852Z\",\n \"last_updated_time\": \"2026-02-11T00:27:00.816431Z\",\n \"url\": \"https://connect.maton.ai/?session_token=...\",\n \"app\": \"beehiiv\",\n \"metadata\": {}\n }\n}\n```\n\nOpen the returned `url` in a browser to complete OAuth authorization.\n\n### Delete Connection\n\n```bash\npython <<'EOF'\nimport urllib.request, os, json\nreq = urllib.request.Request('https://ctrl.maton.ai/connections/{connection_id}', method='DELETE')\nreq.add_header('Authorization', f'Bearer {os.environ[\"MATON_API_KEY\"]}')\nprint(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))\nEOF\n```\n\n### Specifying Connection\n\nIf you have multiple beehiiv connections, specify which one to use with the `Maton-Connection` header:\n\n```bash\npython <<'EOF'\nimport urllib.request, os, json\nreq = urllib.request.Request('https://gateway.maton.ai/beehiiv/v2/publications')\nreq.add_header('Authorization', f'Bearer {os.environ[\"MATON_API_KEY\"]}')\nreq.add_header('Maton-Connection', '8bfe17f4-0038-4cbd-afb4-907b1ffa9d66')\nprint(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))\nEOF\n```\n\nIf omitted, the gateway uses the default (oldest) active connection.\n\n## API Reference\n\nAll beehiiv API endpoints follow this pattern:\n\n```\n/beehiiv/v2/{resource}\n```\n\n---\n\n## Publications\n\n### List Publications\n\n```bash\nGET /beehiiv/v2/publications\n```\n\n**Query Parameters:**\n\n| Parameter | Description |\n|-----------|-------------|\n| `limit` | Results per page (1-100, default: 10) |\n| `page` | Page number (default: 1) |\n| `expand[]` | Expand with: `stats`, `stat_active_subscriptions`, `stat_average_open_rate`, etc. |\n| `order_by` | Sort by: `created` or `name` |\n| `direction` | Sort direction: `asc` or `desc` |\n\n**Response:**\n```json\n{\n \"data\": [\n {\n \"id\": \"pub_c6c521e4-91ac-4c14-8a52-06987b7e32f2\",\n \"name\": \"My Newsletter\",\n \"organization_name\": \"My Organization\",\n \"referral_program_enabled\": true,\n \"created\": 1770767522\n }\n ],\n \"page\": 1,\n \"limit\": 10,\n \"total_results\": 1,\n \"total_pages\": 1\n}\n```\n\n### Get Publication\n\n```bash\nGET /beehiiv/v2/publications/{publication_id}\n```\n\n---\n\n## Subscriptions\n\n### List Subscriptions\n\n```bash\nGET /beehiiv/v2/publications/{publication_id}/subscriptions\n```\n\n**Query Parameters:**\n\n| Parameter | Description |\n|-----------|-------------|\n| `limit` | Results per page (1-100, default: 10) |\n| `cursor` | Cursor for pagination (recommended) |\n| `page` | Page number (deprecated, max 100 pages) |\n| `email` | Filter by exact email (case-insensitive) |\n| `status` | Filter: `validating`, `invalid`, `pending`, `active`, `inactive`, `all` |\n| `tier` | Filter: `free`, `premium`, `all` |\n| `expand[]` | Expand with: `stats`, `custom_fields`, `referrals` |\n| `order_by` | Sort field (default: `created`) |\n| `direction` | Sort direction: `asc` or `desc` |\n\n**Response:**\n```json\n{\n \"data\": [\n {\n \"id\": \"sub_c27d9640-f418-43a8-a0f9-528c20a05002\",\n \"email\": \"subscriber@example.com\",\n \"status\": \"active\",\n \"created\": 1770767524,\n \"subscription_tier\": \"free\",\n \"subscription_premium_tier_names\": [],\n \"utm_source\": \"direct\",\n \"utm_medium\": \"\",\n \"utm_channel\": \"website\",\n \"utm_campaign\": \"\",\n \"referring_site\": \"\",\n \"referral_code\": \"gBZbSVal1X\",\n \"stripe_customer_id\": \"\"\n }\n ],\n \"limit\": 10,\n \"has_more\": false,\n \"next_cursor\": null\n}\n```\n\n### Get Subscription by ID\n\n```bash\nGET /beehiiv/v2/publications/{publication_id}/subscriptions/{subscription_id}\n```\n\n**Query Parameters:**\n\n| Parameter | Description |\n|-----------|-------------|\n| `expand[]` | Expand with: `stats`, `custom_fields`, `referrals`, `tags` |\n\n### Get Subscription by Email\n\n```bash\nGET /beehiiv/v2/publications/{publication_id}/subscriptions/by_email/{email}\n```\n\n### Create Subscription\n\n```bash\nPOST /beehiiv/v2/publications/{publication_id}/subscriptions\nContent-Type: application/json\n\n{\n \"email\": \"newsubscriber@example.com\",\n \"utm_source\": \"api\",\n \"send_welcome_email\": false,\n \"reactivate_existing\": false\n}\n```\n\n**Request Body:**\n\n| Field | Type | Required | Description |\n|-------|------|----------|-------------|\n| `email` | string | Yes | Subscriber email address |\n| `reactivate_existing` | boolean | No | Reactivate if previously unsubscribed |\n| `send_welcome_email` | boolean | No | Send welcome email |\n| `utm_source` | string | No | UTM source for tracking |\n| `utm_medium` | string | No | UTM medium |\n| `referring_site` | string | No | Referral code of referring subscriber |\n| `custom_fields` | object | No | Custom field values (fields must exist) |\n| `double_opt_override` | string | No | `on` or `off` to override double opt-in |\n| `tier` | string | No | Subscription tier |\n| `premium_tier_names` | array | No | Premium tier names to assign |\n\n### Update Subscription\n\n```bash\nPATCH /beehiiv/v2/publications/{publication_id}/subscriptions/{subscription_id}\nContent-Type: application/json\n\n{\n \"utm_source\": \"updated-source\",\n \"custom_fields\": [\n {\"name\": \"First Name\", \"value\": \"John\"}\n ]\n}\n```\n\n### Delete Subscription\n\n```bash\nDELETE /beehiiv/v2/publications/{publication_id}/subscriptions/{subscription_id}\n```\n\n---\n\n## Posts\n\n### List Posts\n\n```bash\nGET /beehiiv/v2/publications/{publication_id}/posts\n```\n\n**Query Parameters:**\n\n| Parameter | Description |\n|-----------|-------------|\n| `limit` | Results per page (1-100, default: 10) |\n| `page` | Page number |\n| `status` | Filter by status |\n| `expand[]` | Expand with additional data |\n\n**Response:**\n```json\n{\n \"data\": [],\n \"page\": 1,\n \"limit\": 10,\n \"total_results\": 0,\n \"total_pages\": 0\n}\n```\n\n### Get Post\n\n```bash\nGET /beehiiv/v2/publications/{publication_id}/posts/{post_id}\n```\n\n### Delete Post\n\n```bash\nDELETE /beehiiv/v2/publications/{publication_id}/posts/{post_id}\n```\n\n---\n\n## Custom Fields\n\n### List Custom Fields\n\n```bash\nGET /beehiiv/v2/publications/{publication_id}/custom_fields\n```\n\n**Response:**\n```json\n{\n \"data\": [\n {\n \"id\": \"95c9653f-a1cf-45f0-a140-97feef19057b\",\n \"kind\": \"string\",\n \"display\": \"Last Name\",\n \"created\": 1770767523\n },\n {\n \"id\": \"4cfe081e-c89b-4da5-9c1a-52a4fb8ba69e\",\n \"kind\": \"string\",\n \"display\": \"First Name\",\n \"created\": 1770767523\n }\n ],\n \"page\": 1,\n \"limit\": 10,\n \"total_results\": 2,\n \"total_pages\": 1\n}\n```\n\n**Field Kinds:** `string`, `integer`, `boolean`, `date`, `datetime`, `list`, `double`\n\n### Create Custom Field\n\n```bash\nPOST /beehiiv/v2/publications/{publication_id}/custom_fields\nContent-Type: application/json\n\n{\n \"display\": \"Company\",\n \"kind\": \"string\"\n}\n```\n\n### Update Custom Field\n\n```bash\nPATCH /beehiiv/v2/publications/{publication_id}/custom_fields/{custom_field_id}\nContent-Type: application/json\n\n{\n \"display\": \"Company Name\"\n}\n```\n\n### Delete Custom Field\n\n```bash\nDELETE /beehiiv/v2/publications/{publication_id}/custom_fields/{custom_field_id}\n```\n\n---\n\n## Segments\n\n### List Segments\n\n```bash\nGET /beehiiv/v2/publications/{publication_id}/segments\n```\n\n**Response:**\n```json\n{\n \"data\": [],\n \"page\": 1,\n \"limit\": 10,\n \"total_results\": 0,\n \"total_pages\": 0\n}\n```\n\n### Get Segment\n\n```bash\nGET /beehiiv/v2/publications/{publication_id}/segments/{segment_id}\n```\n\n### Delete Segment\n\n```bash\nDELETE /beehiiv/v2/publications/{publication_id}/segments/{segment_id}\n```\n\n---\n\n## Tiers\n\n### List Tiers\n\n```bash\nGET /beehiiv/v2/publications/{publication_id}/tiers\n```\n\n### Get Tier\n\n```bash\nGET /beehiiv/v2/publications/{publication_id}/tiers/{tier_id}\n```\n\n### Create Tier\n\n```bash\nPOST /beehiiv/v2/publications/{publication_id}/tiers\nContent-Type: application/json\n\n{\n \"name\": \"Premium\",\n \"description\": \"Premium tier with exclusive content\"\n}\n```\n\n### Update Tier\n\n```bash\nPATCH /beehiiv/v2/publications/{publication_id}/tiers/{tier_id}\nContent-Type: application/json\n\n{\n \"name\": \"Updated Tier Name\"\n}\n```\n\n---\n\n## Automations\n\n### List Automations\n\n```bash\nGET /beehiiv/v2/publications/{publication_id}/automations\n```\n\n### Get Automation\n\n```bash\nGET /beehiiv/v2/publications/{publication_id}/automations/{automation_id}\n```\n\n---\n\n## Referral Program\n\n### Get Referral Program\n\n```bash\nGET /beehiiv/v2/publications/{publication_id}/referral_program\n```\n\n---\n\n## Pagination\n\nbeehiiv supports two pagination methods:\n\n### Cursor-Based (Recommended)\n\n```bash\nGET /beehiiv/v2/publications/{publication_id}/subscriptions?limit=10&cursor={next_cursor}\n```\n\n**Response includes:**\n```json\n{\n \"data\": [...],\n \"limit\": 10,\n \"has_more\": true,\n \"next_cursor\": \"eyJ0aW1lc3RhbXAiOiIyMDI0LTA3LTAyVDE3OjMwOjAwLjAwMDAwMFoifQ==\"\n}\n```\n\nUse the `next_cursor` value for subsequent requests.\n\n### Page-Based (Deprecated)\n\n```bash\nGET /beehiiv/v2/publications?page=2&limit=10\n```\n\n**Response includes:**\n```json\n{\n \"data\": [...],\n \"page\": 2,\n \"limit\": 10,\n \"total_results\": 50,\n \"total_pages\": 5\n}\n```\n\n**Note:** Page-based pagination is limited to 100 pages maximum.\n\n## Code Examples\n\n### JavaScript\n\n```javascript\nconst response = await fetch(\n 'https://gateway.maton.ai/beehiiv/v2/publications',\n {\n headers: {\n 'Authorization': `Bearer ${process.env.MATON_API_KEY}`\n }\n }\n);\nconst data = await response.json();\nconsole.log(data.data);\n```\n\n### Python\n\n```python\nimport os\nimport requests\n\nresponse = requests.get(\n 'https://gateway.maton.ai/beehiiv/v2/publications',\n headers={'Authorization': f'Bearer {os.environ[\"MATON_API_KEY\"]}'}\n)\ndata = response.json()\nfor pub in data['data']:\n print(f\"{pub['id']}: {pub['name']}\")\n```\n\n## Notes\n\n- Publication IDs start with `pub_`\n- Subscription IDs start with `sub_`\n- Timestamps are Unix timestamps (seconds since epoch)\n- Custom fields must be created before use in subscriptions\n- Cursor-based pagination is recommended for better performance\n- Page-based pagination is deprecated and limited to 100 pages\n- IMPORTANT: When using curl commands, use `curl -g` when URLs contain brackets to disable glob parsing\n- IMPORTANT: When piping curl output to `jq` or other commands, environment variables like `$MATON_API_KEY` may not expand correctly in some shell environments\n\n## Error Handling\n\n| Status | Meaning |\n|--------|---------|\n| 400 | Bad request or invalid parameters |\n| 401 | Invalid or missing Maton API key |\n| 403 | Forbidden - insufficient permissions or plan limitation |\n| 404 | Resource not found |\n| 429 | Rate limited |\n| 500 | Internal server error |\n\n### Troubleshooting: API Key Issues\n\n1. Check that the `MATON_API_KEY` environment variable is set:\n\n```bash\necho $MATON_API_KEY\n```\n\n2. Verify the API key is valid by listing connections:\n\n```bash\npython <<'EOF'\nimport urllib.request, os, json\nreq = urllib.request.Request('https://ctrl.maton.ai/connections')\nreq.add_header('Authorization', f'Bearer {os.environ[\"MATON_API_KEY\"]}')\nprint(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))\nEOF\n```\n\n### Troubleshooting: Invalid App Name\n\n1. Ensure your URL path starts with `beehiiv`. For example:\n\n- Correct: `https://gateway.maton.ai/beehiiv/v2/publications`\n- Incorrect: `https://gateway.maton.ai/v2/publications`\n\n## Resources\n\n- [beehiiv Developer Documentation](https://developers.beehiiv.com/)\n- [beehiiv API Reference](https://developers.beehiiv.com/api-reference)\n- [beehiiv Help Center](https://beehiivhelp.zendesk.com/)\n- [Maton Community](https://discord.com/invite/dBfFAcefs2)\n- [Maton Support](mailto:support@maton.ai)\n", "source_url": "https://clawhub.ai/byungkyu/beehiiv", "repository_url": "https://github.com/byungkyu/beehiiv", "categories": [], "tags": [], "status": "approved", "featured": 0, "review_note": null, "approved_at": null, "approved_by": null, "created_at": "2026-02-11T11:45:37.614Z", "updated_at": "2026-02-25T23:15:35.986Z", "stars_total": 5, "stars_clawhub": 5, "stars_ours": 0, "downloads": 1656, "installs_current": 1, "installs_all_time": 1, "author": { "citizen_id": null, "handle": "byungkyu", "display_name": "byungkyu", "tier": null, "trust": null, "reputation": null } }, { "id": "1d6c5e6f-97da-41ef-9292-ea0cba8f80d1", "owner_account_id": "b9a8f519-797e-4320-bb85-6834738d6676", "slug": "personal-assistant", "name": "Personal Assistant", "summary": "Personal daily briefing and productivity assistant. Generates morning briefings with priorities, habits, and self-care reminders. Use when starting your day, planning tasks, or maintaining daily routines and personal development. A minimalist personal productivity skill focused on you.", "content_md": "---\nname: personal-assistant\ndescription: Personal daily briefing and productivity assistant. Generates morning briefings with priorities, habits, and self-care reminders. Use when starting your day, planning tasks, or maintaining daily routines and personal development. A minimalist personal productivity skill focused on you.\n---\n\n# Personal Assistant\n\n## Overview / Visão Geral\n\nGenerate personalized daily briefings with morning motivation, priorities, habit tracking, and evening reflection. Focus on productivity and well-being with minimal complexity.\n\nGerencie briefings diários personalizados com motivação matinal, prioridades, hábitos e reflexão noturna. Foque em produtividade e bem-estar com complexidade mínima.\n\n## Quick Start / Início Rápido\n\n```bash\n# Generate daily briefing\npython3 scripts/daily_briefing.py --location Columbus --summary\n\n# Save to file\npython3 scripts/daily_briefing.py --output daily_briefing.json\n```\n\n## Workflow / Fluxo de Trabalho\n\n### Morning Routine / Rotina Matinal\n\nStart your day with a structured briefing:\n\n1. **Motivation:** Positive start with intention / Motivação: começo positivo com intenção\n2. **Weather:** Check conditions for the day / Clima: verifique condições do dia\n3. **Priorities:** Set top 3 tasks / Prioridades: defina top 3 tarefas\n4. **Habits:** Track daily goals / Hábitos: acompanhe metas diárias\n\n### During the Day / Durante o Dia\n\nUse briefing as your reference:\n- Check priorities list / Verifique lista de prioridades\n- Mark completed habits / Marque hábitos completados\n- Take breaks and stay hydrated / Faça pausas e mantenha-se hidratado\n\n### Evening Review / Revisão Noturna\n\nEnd your day with reflection:\n- What did I accomplish? / O que eu conquistei?\n- What am I grateful for? / Pelo que eu sou grato?\n- What could I improve? / O que eu poderia melhorar?\n- Set tomorrow's priority / Defina prioridade de amanhã\n\n## Usage / Uso\n\n### Generate Briefing / Gerar Briefing\n\n```bash\npython3 scripts/daily_briefing.py --location Columbus --summary\n```\n\nOutput:\n\n```\n📋 Daily Briefing - 2026-02-11 (Wednesday)\n\n🌅 Good Morning!\nStart your day with focus and intention.\n\n🌡 Weather Check\nCheck the weather in Columbus before heading out.\n\n🎯 Today's Focus\nTop 3 priorities:\n1. _____________________________\n2. _____________________________\n3. _____________________________\n\n✅ Daily Habits\n☐ Morning routine\n☐ Hydration goals\n☐ Learning time\n☐ Evening review\n\n💚 Self-Care\nRemember to take breaks and stay hydrated.\n\n🌙 Evening Review\n1. What did I accomplish today?\n2. What am I grateful for?\n3. What could I have done better?\n4. Tomorrow's top priority?\n```\n\n### Parameters / Parâmetros\n\n| Parameter | Description | Descrição | Default |\n|-----------|-------------|-------------|----------|\n| `--location` | Your city / Sua cidade | Columbus | `--location Miami` |\n| `--output` | Output file / Arquivo de saída | daily_briefing.json | `--output briefing.json` |\n| `--summary` | Print readable output / Imprimir saída legível | false | `--summary` |\n\n## Daily Automation / Automação Diária\n\nSet up morning briefings with OpenClaw cron:\n\n```bash\n# Every day at 7 AM\nopenclaw cron add \\\n --schedule \"0 7 * * *\" \\\n --tz \"America/New_York\" \\\n --message \"Generate my daily briefing\"\n```\n\nOr manually:\n\n```bash\n# Morning (7 AM)\npython3 scripts/daily_briefing.py --location Columbus --summary\n\n# Evening (9 PM)\npython3 scripts/daily_briefing.py --location Columbus --summary\n```\n\n## Output Format / Formato de Saída\n\n### JSON Structure\n\n```json\n{\n \"generated_at\": \"2026-02-11T07:00:00.000Z\",\n \"location\": \"Columbus\",\n \"date\": \"2026-02-11\",\n \"weekday\": \"Wednesday\",\n \"sections\": [\n {\n \"title\": \"🌅 Good Morning!\",\n \"content\": \"Start your day...\",\n \"type\": \"motivation\"\n }\n ]\n}\n```\n\n## Key Sections / Seções Principais\n\n### 🌅 Morning Motivation / Motivação Matinal\nPositive start to your day with focus and intention.\n\nComeço positivo do seu dia com foco e intenção.\n\n### 🎯 Today's Focus / Foco do Dia\nTop 3 priorities with space for your own tasks.\n\nTop 3 prioridades com espaço para suas tarefas.\n\n### ✅ Daily Habits / Hábitos Diários\nTrack recurring daily goals for personal development.\n\nAcompanhe metas recorrentes para desenvolvimento pessoal.\n\n### 💚 Self-Care / Autocuidado\nReminders for hydration, breaks, and work-life balance.\n\nLembretes para hidratação, pausas e equilíbrio vida-trabalho.\n\n### 🌙 Evening Reflection / Reflexão Noturna\nStructured reflection questions for growth and gratitude.\n\nReflexão estruturada para crescimento e gratidão.\n\n## Features / Funcionalidades\n\n- ✅ Simple and fast / Simples e rápido\n- 📝 Human-readable output / Saída legível para humanos\n- 🎨 Emoji-enhanced sections / Seções com emojis\n- 🌍 Location-aware / Consciente de localização\n- 💾 JSON export for automation / Exportação JSON para automação\n- 📅 Weekday-aware / Consciente do dia da semana\n\n## How It Works / Como Funciona\n\n1. **Date & Location:** Gets current date and your location / Obtém data atual e sua localização\n2. **Section Generation:** Creates 5 key sections / Cria 5 seções principais\n3. **Formatting:** Structures output for easy reading / Estrutura saída para leitura fácil\n4. **Saving:** Exports to JSON for integrations / Exporta para JSON para integrações\n\n## Use Cases / Casos de Uso\n\n### Personal Productivity / Produtividade Pessoal\n\nStart each morning with a structured briefing to set focus and priorities.\n\nComece cada manhã com um briefing estruturado para definir foco e prioridades.\n\n### Personal Development / Desenvolvimento Pessoal\n\nUse habit tracking and evening reflection to build self-awareness and growth.\n\nUse rastreamento de hábitos e reflexão noturna para construir autoconsciência e crescimento.\n\n### Remote Work / Trabalho Remoto\n\nMaintain structure and self-care while working from home with briefings and breaks.\n\nMantenha estrutura e autocuidado enquanto trabalha de casa com briefings e pausas.\n\n### Well-being / Bem-Estar\n\nStay mindful of self-care with regular hydration and break reminders.\n\nMantenha-se consciente do autocuidado com lembretes regulares de hidratação e pausas.\n\n## Philosophy / Filosofia\n\nThis skill follows minimal productivity principles:\n- Focus on what matters / Foque no que importa\n- Simple over complex / Simples sobre complexo\n- Consistency > intensity / Consistência > intensidade\n- Progress, not perfection / Progresso, não perfeição\n\n## Resources / Recursos\n\n### scripts/daily_briefing.py\nMain script that generates daily briefings with all sections.\n\nScript principal que gera briefings diários com todas as seções.\n\n### references/productivity.md\nTips and techniques for personal productivity and habit formation.\n\nDicas e técnicas para produtividade pessoal e formação de hábitos.\n\n## Dependencies / Dependências\n\n**None!** / **Nenhuma!**\n\nUses only Python standard library - no external dependencies required.\n\nUsa apenas biblioteca padrão do Python - sem dependências externas necessárias.\n\n## Tips / Dicas\n\n### Morning Routine / Rotina Matinal\n\n- Read your briefing while having coffee / Leia seu briefing enquanto toma café\n- Fill in priorities the night before / Preencha prioridades na noite anterior\n- Keep it simple - max 3 priorities / Mantenha simples - máx 3 prioridades\n\n### Evening Routine / Rotina Noturna\n\n- Spend 5 minutes on reflection / Gaste 5 minutos na reflexão\n- Write down tomorrow's priority / Anote a prioridade de amanhã\n- Practice gratitude daily / Pratique gratidão diariamente\n\n### Building Habits / Construindo Hábitos\n\n- Start with 1-2 habits / Comece com 1-2 hábitos\n- Focus on consistency, not intensity / Foque na consistência, não na intensidade\n- Track visually (use ☐/☑) / Acompanhe visualmente (use ☐/☑)\n\n## Customization / Personalização\n\n### Adding New Sections / Adicionando Novas Seções\n\nEdit `scripts/daily_briefing.py` and add to the `generate_briefing()` function.\n\nEdite `scripts/daily_briefing.py` e adicione à função `generate_briefing()`.\n\n### Modifying Sections / Modificando Seções\n\nEach section has: title, content, type. Customize as needed.\n\nCada seção tem: título, conteúdo, tipo. Personalize conforme necessário.\n\n## License / Licença\n\nMIT License - Use freely for personal and commercial purposes.\nLicença MIT - Use livremente para fins pessoais e comerciais.\n\n## Credits / Créditos\n\nCreated by **Gustavo (GustavoZiaugra)** with OpenClaw\nCriado por **Gustavo (GustavoZiaugra)** com OpenClaw\n\n- Simple productivity framework / Framework de produtividade simples\n- Personal well-being focus / Foque em bem-estar pessoal\n- Minimal and functional approach / Abordagem minimalista e funcional\n\n---\n\n**Find this and more OpenClaw skills at ClawHub.com**\n**Encontre este e mais skills do OpenClaw em ClawHub.com**\n\n⭐ **Star this repository if you find it useful!**\n**⭐ Dê uma estrela neste repositório se você achar útil!**\n\n📋 **Your personal assistant, just for you.**\n📋 **Seu assistente pessoal, só para você.**\n", "source_url": "https://clawhub.ai/GustavoZiaugra/personal-assistant", "repository_url": "https://github.com/GustavoZiaugra/personal-assistant", "categories": [], "tags": [], "status": "approved", "featured": 0, "review_note": null, "approved_at": null, "approved_by": null, "created_at": "2026-02-11T05:36:19.120Z", "updated_at": "2026-02-26T00:30:36.042Z", "stars_total": 0, "stars_clawhub": 0, "stars_ours": 0, "downloads": 3400, "installs_current": 22, "installs_all_time": 22, "author": { "citizen_id": null, "handle": "GustavoZiaugra", "display_name": "GustavoZiaugra", "tier": null, "trust": null, "reputation": null } }, { "id": "a51a564d-f59a-4e3f-853b-1c0f5478ee99", "owner_account_id": "b9a8f519-797e-4320-bb85-6834738d6676", "slug": "callrail", "name": "CallRail", "summary": "CallRail API integration with managed OAuth. Track and analyze phone calls, manage tracking numbers, companies, and tags.\nUse this skill when users want to access call data, manage tracking numbers, view call analytics, or organize calls with tags.\nFor other third party apps, use the api-gateway skill (https://clawhub.ai/byungkyu/api-gateway).", "content_md": "---\nname: callrail\ndescription: |\n CallRail API integration with managed OAuth. Track and analyze phone calls, manage tracking numbers, companies, and tags.\n Use this skill when users want to access call data, manage tracking numbers, view call analytics, or organize calls with tags.\n For other third party apps, use the api-gateway skill (https://clawhub.ai/byungkyu/api-gateway).\ncompatibility: Requires network access and valid Maton API key\nmetadata:\n author: maton\n version: \"1.0\"\n clawdbot:\n emoji: 🧠\n requires:\n env:\n - MATON_API_KEY\n---\n\n# CallRail\n\nAccess the CallRail API with managed OAuth authentication. Track calls, manage tracking numbers, analyze call data, and organize with tags.\n\n## Quick Start\n\n```bash\n# List all calls\npython <<'EOF'\nimport urllib.request, os, json\nreq = urllib.request.Request('https://gateway.maton.ai/callrail/v3/a/{account_id}/calls.json')\nreq.add_header('Authorization', f'Bearer {os.environ[\"MATON_API_KEY\"]}')\nprint(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))\nEOF\n```\n\n## Base URL\n\n```\nhttps://gateway.maton.ai/callrail/{native-api-path}\n```\n\nReplace `{native-api-path}` with the actual CallRail API endpoint path. The gateway proxies requests to `api.callrail.com` and automatically injects your OAuth token.\n\n## Authentication\n\nAll requests require the Maton API key in the Authorization header:\n\n```\nAuthorization: Bearer $MATON_API_KEY\n```\n\n**Environment Variable:** Set your API key as `MATON_API_KEY`:\n\n```bash\nexport MATON_API_KEY=\"YOUR_API_KEY\"\n```\n\n### Getting Your API Key\n\n1. Sign in or create an account at [maton.ai](https://maton.ai)\n2. Go to [maton.ai/settings](https://maton.ai/settings)\n3. Copy your API key\n\n## Connection Management\n\nManage your CallRail OAuth connections at `https://ctrl.maton.ai`.\n\n### List Connections\n\n```bash\npython <<'EOF'\nimport urllib.request, os, json\nreq = urllib.request.Request('https://ctrl.maton.ai/connections?app=callrail&status=ACTIVE')\nreq.add_header('Authorization', f'Bearer {os.environ[\"MATON_API_KEY\"]}')\nprint(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))\nEOF\n```\n\n### Create Connection\n\n```bash\npython <<'EOF'\nimport urllib.request, os, json\ndata = json.dumps({'app': 'callrail'}).encode()\nreq = urllib.request.Request('https://ctrl.maton.ai/connections', data=data, method='POST')\nreq.add_header('Authorization', f'Bearer {os.environ[\"MATON_API_KEY\"]}')\nreq.add_header('Content-Type', 'application/json')\nprint(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))\nEOF\n```\n\n### Get Connection\n\n```bash\npython <<'EOF'\nimport urllib.request, os, json\nreq = urllib.request.Request('https://ctrl.maton.ai/connections/{connection_id}')\nreq.add_header('Authorization', f'Bearer {os.environ[\"MATON_API_KEY\"]}')\nprint(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))\nEOF\n```\n\n**Response:**\n```json\n{\n \"connection\": {\n \"connection_id\": \"75364cb9-7116-4367-a707-1113d426f17d\",\n \"status\": \"ACTIVE\",\n \"creation_time\": \"2026-02-10T09:55:17.574212Z\",\n \"last_updated_time\": \"2026-02-10T09:55:34.693801Z\",\n \"url\": \"https://connect.maton.ai/?session_token=...\",\n \"app\": \"callrail\",\n \"metadata\": {}\n }\n}\n```\n\nOpen the returned `url` in a browser to complete OAuth authorization.\n\n### Delete Connection\n\n```bash\npython <<'EOF'\nimport urllib.request, os, json\nreq = urllib.request.Request('https://ctrl.maton.ai/connections/{connection_id}', method='DELETE')\nreq.add_header('Authorization', f'Bearer {os.environ[\"MATON_API_KEY\"]}')\nprint(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))\nEOF\n```\n\n### Specifying Connection\n\nIf you have multiple CallRail connections, specify which one to use with the `Maton-Connection` header:\n\n```bash\npython <<'EOF'\nimport urllib.request, os, json\nreq = urllib.request.Request('https://gateway.maton.ai/callrail/v3/a.json')\nreq.add_header('Authorization', f'Bearer {os.environ[\"MATON_API_KEY\"]}')\nreq.add_header('Maton-Connection', '75364cb9-7116-4367-a707-1113d426f17d')\nprint(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))\nEOF\n```\n\nIf omitted, the gateway uses the default (oldest) active connection.\n\n## API Reference\n\n### URL Pattern\n\nAll CallRail API endpoints follow this pattern:\n\n```\n/callrail/v3/a/{account_id}/{resource}.json\n```\n\nAccount IDs start with `ACC`, Company IDs start with `COM`, Call IDs start with `CAL`, Tracker IDs start with `TRK`, User IDs start with `USR`.\n\n---\n\n## Accounts\n\n### List Accounts\n\n```bash\nGET /callrail/v3/a.json\n```\n\n**Response:**\n```json\n{\n \"page\": 1,\n \"per_page\": 100,\n \"total_pages\": 1,\n \"total_records\": 1,\n \"accounts\": [\n {\n \"id\": \"ACC019c46b8a0807fbdb81c8bf12af91cb3\",\n \"name\": \"My Account\",\n \"numeric_id\": 518664017,\n \"inbound_recording_enabled\": false,\n \"outbound_recording_enabled\": false,\n \"hipaa_account\": false,\n \"created_at\": \"2026-02-10 03:43:50 -0500\"\n }\n ]\n}\n```\n\n### Get Account\n\n```bash\nGET /callrail/v3/a/{account_id}.json\n```\n\n---\n\n## Companies\n\n### List Companies\n\n```bash\nGET /callrail/v3/a/{account_id}/companies.json\n```\n\n**Response:**\n```json\n{\n \"page\": 1,\n \"per_page\": 100,\n \"total_pages\": 1,\n \"total_records\": 1,\n \"companies\": [\n {\n \"id\": \"COM019c46b8a26376a9a4f29671dcdd49e9\",\n \"name\": \"My Company\",\n \"status\": \"active\",\n \"time_zone\": \"America/Los_Angeles\",\n \"created_at\": \"2026-02-10T08:43:51.280Z\",\n \"callscore_enabled\": false,\n \"lead_scoring_enabled\": true,\n \"callscribe_enabled\": true\n }\n ]\n}\n```\n\n### Get Company\n\n```bash\nGET /callrail/v3/a/{account_id}/companies/{company_id}.json\n```\n\n---\n\n## Calls\n\n### List Calls\n\n```bash\nGET /callrail/v3/a/{account_id}/calls.json\n```\n\n**Query Parameters:**\n\n| Parameter | Description |\n|-----------|-------------|\n| `page` | Page number (default: 1) |\n| `per_page` | Results per page (default: 100, max: 250) |\n| `date_range` | Preset: `recent`, `today`, `yesterday`, `last_7_days`, `last_30_days`, `this_month`, `last_month` |\n| `start_date` | ISO 8601 date (e.g., `2026-02-01T00:00:00-08:00`) |\n| `end_date` | ISO 8601 date |\n| `company_id` | Filter by company |\n| `tracker_id` | Filter by tracker |\n| `search` | Search term |\n| `fields` | Comma-separated field names to return |\n| `sort` | Field to sort by |\n| `order` | Sort order: `asc` or `desc` |\n\n**Response:**\n```json\n{\n \"page\": 1,\n \"per_page\": 100,\n \"total_pages\": 1,\n \"total_records\": 1,\n \"calls\": [\n {\n \"id\": \"CAL019c46b9fc277a7881e3728fea20869b\",\n \"answered\": false,\n \"customer_name\": \"John Doe\",\n \"customer_phone_number\": \"+18886757190\",\n \"direction\": \"inbound\",\n \"duration\": 36,\n \"recording\": \"https://api.callrail.com/v3/a/.../recording\",\n \"recording_duration\": 36,\n \"start_time\": \"2026-02-10T00:45:19.781-08:00\",\n \"tracking_phone_number\": \"+18017846712\",\n \"voicemail\": true\n }\n ]\n}\n```\n\n### Get Call\n\n```bash\nGET /callrail/v3/a/{account_id}/calls/{call_id}.json\n```\n\n### Update Call\n\n```bash\nPUT /callrail/v3/a/{account_id}/calls/{call_id}.json\nContent-Type: application/json\n\n{\n \"customer_name\": \"John Smith\",\n \"note\": \"Follow up scheduled\",\n \"lead_status\": \"good_lead\",\n \"spam\": false\n}\n```\n\n**Updatable Fields:**\n\n| Field | Description |\n|-------|-------------|\n| `customer_name` | Customer's name |\n| `note` | Call notes |\n| `lead_status` | `good_lead`, `not_a_lead`, `previously_marked_good_lead` |\n| `spam` | Mark as spam (boolean) |\n| `tag_list` | Array of tag names to apply |\n| `value` | Call value (numeric) |\n| `append_tags` | Add tags without removing existing |\n\n### Call Summary\n\n```bash\nGET /callrail/v3/a/{account_id}/calls/summary.json\n```\n\nGet aggregated call statistics for a date range.\n\n**Query Parameters:**\n\n| Parameter | Description |\n|-----------|-------------|\n| `date_range` | Preset date range |\n| `start_date` | Start date (ISO 8601) |\n| `end_date` | End date (ISO 8601) |\n| `group_by` | Group results: `company`, `tracker`, `source`, `medium`, etc. |\n\n**Response:**\n```json\n{\n \"start_date\": \"2026-02-03T00:00:00-0800\",\n \"end_date\": \"2026-02-10T23:59:59-0800\",\n \"time_zone\": \"Pacific Time (US & Canada)\",\n \"total_results\": {\n \"total_calls\": 42\n }\n}\n```\n\n### Call Timeseries\n\n```bash\nGET /callrail/v3/a/{account_id}/calls/timeseries.json\n```\n\nGet call data over time for charts and graphs.\n\n**Response:**\n```json\n{\n \"start_date\": \"2026-02-03T00:00:00-0800\",\n \"end_date\": \"2026-02-10T23:59:59-0800\",\n \"data\": [\n {\"key\": \"2026-02-03\", \"date\": \"2026-02-03\", \"total_calls\": 5},\n {\"key\": \"2026-02-04\", \"date\": \"2026-02-04\", \"total_calls\": 8}\n ]\n}\n```\n\n---\n\n## Trackers (Tracking Numbers)\n\n### List Trackers\n\n```bash\nGET /callrail/v3/a/{account_id}/trackers.json\n```\n\n**Response:**\n```json\n{\n \"page\": 1,\n \"per_page\": 100,\n \"total_records\": 1,\n \"trackers\": [\n {\n \"id\": \"TRK019c46b9f18174d68bb8d7985260a11f\",\n \"name\": \"Google My Business\",\n \"type\": \"source\",\n \"status\": \"active\",\n \"destination_number\": \"+18019234886\",\n \"tracking_numbers\": [\"+18017846712\"],\n \"sms_supported\": true,\n \"sms_enabled\": true,\n \"company\": {\n \"id\": \"COM019c46b8a26376a9a4f29671dcdd49e9\",\n \"name\": \"My Company\"\n },\n \"source\": {\"type\": \"google_my_business\"},\n \"call_flow\": {\n \"type\": \"basic\",\n \"recording_enabled\": true,\n \"destination_number\": \"+18019234886\"\n }\n }\n ]\n}\n```\n\n### Get Tracker\n\n```bash\nGET /callrail/v3/a/{account_id}/trackers/{tracker_id}.json\n```\n\n---\n\n## Tags\n\n### List Tags\n\n```bash\nGET /callrail/v3/a/{account_id}/tags.json\n```\n\n**Response:**\n```json\n{\n \"page\": 1,\n \"per_page\": 100,\n \"total_records\": 6,\n \"tags\": [\n {\n \"id\": 7886733,\n \"name\": \"Schedule requested\",\n \"tag_level\": \"account\",\n \"color\": \"orange3\",\n \"background_color\": \"gray1\",\n \"company_id\": null,\n \"status\": \"enabled\"\n },\n {\n \"id\": 7886728,\n \"name\": \"Opportunity\",\n \"tag_level\": \"company\",\n \"color\": \"gray1\",\n \"company_id\": \"COM019c46b8a26376a9a4f29671dcdd49e9\",\n \"status\": \"enabled\"\n }\n ]\n}\n```\n\n### Create Tag\n\n```bash\nPOST /callrail/v3/a/{account_id}/tags.json\nContent-Type: application/json\n\n{\n \"name\": \"New Tag\",\n \"tag_level\": \"account\",\n \"color\": \"blue1\"\n}\n```\n\n**Tag Levels:**\n- `account` - Available to all companies in the account\n- `company` - Specific to a company (requires `company_id`)\n\n**Colors:** `gray1`, `blue1`, `blue2`, `green1`, `green2`, `orange1`, `orange2`, `orange3`, `red1`, etc.\n\n### Update Tag\n\n```bash\nPUT /callrail/v3/a/{account_id}/tags/{tag_id}.json\nContent-Type: application/json\n\n{\n \"name\": \"Updated Tag Name\",\n \"color\": \"green1\"\n}\n```\n\n### Delete Tag\n\n```bash\nDELETE /callrail/v3/a/{account_id}/tags/{tag_id}.json\n```\n\n---\n\n## Users\n\n### List Users\n\n```bash\nGET /callrail/v3/a/{account_id}/users.json\n```\n\n**Response:**\n```json\n{\n \"page\": 1,\n \"per_page\": 100,\n \"total_records\": 1,\n \"users\": [\n {\n \"id\": \"USR019c46b8a0557b2e85e5e1c651452509\",\n \"email\": \"user@example.com\",\n \"first_name\": \"John\",\n \"last_name\": \"Doe\",\n \"name\": \"John Doe\",\n \"role\": \"admin\",\n \"accepted\": true,\n \"created_at\": \"2026-02-10T03:43:50.798-05:00\",\n \"companies\": [\n {\"id\": \"COM...\", \"name\": \"My Company\"}\n ]\n }\n ]\n}\n```\n\n### Get User\n\n```bash\nGET /callrail/v3/a/{account_id}/users/{user_id}.json\n```\n\n---\n\n## Integrations\n\n### List Integrations\n\n```bash\nGET /callrail/v3/a/{account_id}/integrations.json?company_id={company_id}\n```\n\n**Note:** `company_id` is required.\n\n---\n\n## Notifications\n\n### List Notifications\n\n```bash\nGET /callrail/v3/a/{account_id}/notifications.json\n```\n\n---\n\n## Pagination\n\nCallRail uses offset-based pagination:\n\n```bash\nGET /callrail/v3/a/{account_id}/calls.json?page=2&per_page=50\n```\n\n**Response includes:**\n```json\n{\n \"page\": 2,\n \"per_page\": 50,\n \"total_pages\": 10,\n \"total_records\": 487,\n \"calls\": [...]\n}\n```\n\n**Parameters:**\n- `page` - Page number (default: 1)\n- `per_page` - Results per page (default: 100, max: 250)\n\nFor the calls endpoint, you can also use relative pagination:\n\n```bash\nGET /callrail/v3/a/{account_id}/calls.json?relative_pagination=true\n```\n\nThis returns `next_page` URL and `has_next_page` boolean for efficient pagination of large datasets.\n\n## Code Examples\n\n### JavaScript\n\n```javascript\nconst response = await fetch(\n 'https://gateway.maton.ai/callrail/v3/a/{account_id}/calls.json',\n {\n headers: {\n 'Authorization': `Bearer ${process.env.MATON_API_KEY}`\n }\n }\n);\nconst data = await response.json();\nconsole.log(data.calls);\n```\n\n### Python\n\n```python\nimport os\nimport requests\n\nresponse = requests.get(\n 'https://gateway.maton.ai/callrail/v3/a/{account_id}/calls.json',\n headers={'Authorization': f'Bearer {os.environ[\"MATON_API_KEY\"]}'},\n params={'per_page': 50, 'date_range': 'last_30_days'}\n)\ndata = response.json()\nfor call in data['calls']:\n print(f\"{call['customer_name']}: {call['duration']}s\")\n```\n\n## Rate Limits\n\n| Endpoint Type | Hourly Limit | Daily Limit |\n|--------------|--------------|-------------|\n| General API | 1,000 | 10,000 |\n| SMS Send | 150 | 1,000 |\n| Outbound Calls | 100 | 2,000 |\n\nExceeding limits returns HTTP 429. Implement exponential backoff for retries.\n\n## Notes\n\n- Account IDs start with `ACC`\n- Company IDs start with `COM`\n- Call IDs start with `CAL`\n- Tracker IDs start with `TRK`\n- User IDs start with `USR`\n- All endpoints end with `.json`\n- Communication records are retained for 25 months\n- Date/time values use ISO 8601 format with timezone\n- IMPORTANT: When using curl commands, use `curl -g` when URLs contain brackets to disable glob parsing\n- IMPORTANT: When piping curl output to `jq` or other commands, environment variables like `$MATON_API_KEY` may not expand correctly in some shell environments\n\n## Error Handling\n\n| Status | Meaning |\n|--------|---------|\n| 400 | Bad request or missing required parameter |\n| 401 | Invalid or missing Maton API key |\n| 403 | Forbidden - insufficient permissions |\n| 404 | Resource not found |\n| 422 | Unprocessable entity |\n| 429 | Rate limited |\n| 500 | Internal server error |\n| 503 | Service unavailable |\n\n### Troubleshooting: API Key Issues\n\n1. Check that the `MATON_API_KEY` environment variable is set:\n\n```bash\necho $MATON_API_KEY\n```\n\n2. Verify the API key is valid by listing connections:\n\n```bash\npython <<'EOF'\nimport urllib.request, os, json\nreq = urllib.request.Request('https://ctrl.maton.ai/connections')\nreq.add_header('Authorization', f'Bearer {os.environ[\"MATON_API_KEY\"]}')\nprint(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))\nEOF\n```\n\n### Troubleshooting: Invalid App Name\n\n1. Ensure your URL path starts with `callrail`. For example:\n\n- Correct: `https://gateway.maton.ai/callrail/v3/a.json`\n- Incorrect: `https://gateway.maton.ai/v3/a.json`\n\n## Resources\n\n- [CallRail API Documentation](https://apidocs.callrail.com/)\n- [CallRail Help Center - API](https://support.callrail.com/hc/en-us/sections/4426797289229-API)\n- [CallRail API Rate Limits](https://apidocs.callrail.com/#rate-limiting)\n- [Maton Community](https://discord.com/invite/dBfFAcefs2)\n- [Maton Support](mailto:support@maton.ai)\n", "source_url": "https://clawhub.ai/byungkyu/callrail", "repository_url": "https://github.com/byungkyu/callrail", "categories": [], "tags": [], "status": "approved", "featured": 0, "review_note": null, "approved_at": null, "approved_by": null, "created_at": "2026-02-10T12:59:49.845Z", "updated_at": "2026-02-26T00:25:39.606Z", "stars_total": 2, "stars_clawhub": 2, "stars_ours": 0, "downloads": 3071, "installs_current": 0, "installs_all_time": 0, "author": { "citizen_id": null, "handle": "byungkyu", "display_name": "byungkyu", "tier": null, "trust": null, "reputation": null } }, { "id": "02a6a919-d7cd-4c03-bb8c-cd1249e87833", "owner_account_id": "b9a8f519-797e-4320-bb85-6834738d6676", "slug": "mcp-hass", "name": "🏠 Home Assistant via MCP protocol", "summary": "The skill for control Home Assistant smart home devices and query states using MCP protocol.", "content_md": "---\nname: mcp-hass\ndescription: The skill for control Home Assistant smart home devices and query states using MCP protocol.\nhomepage: https://home-assistant.io/integrations/mcp\nmetadata:\n {\n \"openclaw\":\n {\n \"emoji\": \"🏠\",\n \"requires\": { \"anyBins\": [\"mcporter\", \"npx\"], \"env\": [\"HASS_ACCESS_TOKEN\", \"HASS_BASE_URL\"] },\n \"primaryEnv\": \"HASS_ACCESS_TOKEN\",\n \"install\":\n [\n {\n \"id\": \"node\",\n \"kind\": \"node\",\n \"package\": \"mcporter\",\n \"bins\": [\"mcporter\"],\n \"label\": \"Install mcporter (node)\",\n },\n ],\n },\n }\n---\n\n# Home Assistant\nControl Home Assistant smart home and query states using MCP protocol.\n\n## Prerequisites\nEnable MCP server in Home Assistant:\n- Browse to your Home Assistant instance.\n- Go to Settings > Devices & services.\n- In the bottom right corner, select the [+ Add Integration](https://my.home-assistant.io/redirect/config_flow_start?domain=mcp) button.\n- From the list, select Model Context Protocol.\n- Follow the instructions on screen to complete the setup.\n\n## Usage\n```shell\n# Get states\nmcporter call home-assistant.GetLiveContext\n\n# Turn on the device\nmcporter call home-assistant.HassTurnOn(name: \"Bedroom Light\")\nmcporter call home-assistant.HassTurnOn(name: \"Light\", area: \"Bedroom\")\n\n# Turn off the device\nmcporter call home-assistant.HassTurnOff(name: \"Bedroom Light\")\nmcporter call home-assistant.HassTurnOff(area: \"Bedroom\", domain: [\"light\"])\n\n# Control light\n# brightness: The percentage of the light, where 0 is off and 100 is fully lit.\n# color: Name of color\nmcporter call home-assistant.HassLightSet(name: \"Bedroom Light\", brightness: 50)\n\n# Control fan\n# percentage: The percentage of the fan, where 0 is off and 100 is full speed.\nmcporter call home-assistant.HassFanSetSpeed(name: \"Fan\", area: \"Bedroom\", percentage: 80)\n```\n\nExecute the following command to learn about specific usage methods:\n- `mcporter list home-assistant --schema --all-parameters`\n\n## Config\nWhen prompted that the MCP server does not exist, remind the user to configure the `HASS_BASE_URL` and `HASS_ACCESS_TOKEN` environment variables by executing the following command to add the configuration:\n```shell\nmcporter config add home-assistant \\\n --transport http \\\n --url \"${HASS_BASE_URL:-http://homeassistant.local:8123}/api/mcp\" \\\n --header \"Authorization=Bearer \\${HASS_ACCESS_TOKEN}\"\n```\n\n## About `mcporter`\n- When command `mcporter` does not exist, use `npx -y mcporter` instead.\n- https://github.com/steipete/mcporter/raw/refs/heads/main/docs/call-syntax.md\n- https://github.com/steipete/mcporter/raw/refs/heads/main/docs/cli-reference.md\n", "source_url": "https://clawhub.ai/al-one/mcp-hass", "repository_url": "https://github.com/al-one/mcp-hass", "categories": [], "tags": [], "status": "approved", "featured": 0, "review_note": null, "approved_at": null, "approved_by": null, "created_at": "2026-02-10T09:30:18.021Z", "updated_at": "2026-02-26T00:15:40.106Z", "stars_total": 6, "stars_clawhub": 6, "stars_ours": 0, "downloads": 1991, "installs_current": 9, "installs_all_time": 9, "author": { "citizen_id": null, "handle": "al-one", "display_name": "al-one", "tier": null, "trust": null, "reputation": null } }, { "id": "9158849f-99ce-4db1-9670-86fc4e17bb01", "owner_account_id": "b9a8f519-797e-4320-bb85-6834738d6676", "slug": "xiaohongshu-title", "name": "xiaohongshu-title", "summary": "Maximize CTR (Click-Through Rate) by leveraging emotional hooks and platform algorithms.", "content_md": "---\r\nname: xiaohongshu-title\r\ndescription: Maximize CTR (Click-Through Rate) by leveraging emotional hooks and platform algorithms.\r\nmetadata: {\"openclaw\":{\"emoji\":\"📺\"}}\r\n---\r\n\r\n## 1. Identity & Objective\r\n- **Role**: Expert Xiaohongshu (RedNote) Content Strategist.\r\n- **Goal**: Maximize CTR (Click-Through Rate) by leveraging emotional hooks and platform algorithms.\r\n- **Output Standard**: Native, emotional, and visually structured titles (no AI-speak).\r\n\r\n## 2. Knowledge Graph (File Mapping)\r\n\r\n### A. Style Reference (`examples.md`)\r\n> **Context**: Contains 200+ real high-performing title examples across 8 specific categories.\r\n> **Directive**: When user input matches a category below, retrieve the corresponding tone/style from `examples.md`.\r\n\r\n- **Category 01**: 美妆护肤 (Beauty & Skincare) -> Focus on: Effects, Ingredients, Before/After.\r\n- **Category 02**: 穿搭时尚 (Fashion & Styling) -> Focus on: Scenarios, Body Types, Seasonal.\r\n- **Category 03**: 减肥健身 (Fitness & Weight Loss) -> Focus on: Numbers, Speed, Ease.\r\n- **Category 04**: 学习教育 (Learning & Education) -> Focus on: Efficiency, Resources, Exams.\r\n- **Category 05**: 生活日常 (Daily Life/Vlog) -> Focus on: Mood, \"Vibe\", Relatability.\r\n- **Category 06**: 情感心理 (Relationships & Psychology) -> Focus on: Resonance, Drama, Solutions.\r\n- **Category 07**: 职场搞钱 (Career & Wealth) -> Focus on: Salary, Skills, Office Politics.\r\n- **Category 08**: 旅行出游 (Travel) -> Focus on: Guides, Hidden Gems, Photography.\r\n\r\n### B. Strategic Assets (`references.md`)\r\n> **Context**: Contains semantic dictionaries and logic templates.\r\n\r\n- **Diction Library**: High-CTR keywords (Emotional/Action/Urgency).\r\n- **Formula Bank**: 5 core structural algorithms for title generation.\r\n- **Compliance**: Blacklist of words prohibited by Chinese Advertising Law.\r\n\r\n### C. Quality Control (`validator.py`)\r\n> **Context**: A Python script logic for final filtering.\r\n- **Constraint**: All outputs must virtually pass the `validate()` function defined in this script (Length < 22, No banned words, Must have emojis).\r\n\r\n## 3. Execution Workflow\r\n\r\n1. **Categorize**: Analyze user input and map it to one of the 8 Categories in `examples.md`.\r\n2. **Retrieve Assets**:\r\n - Select 3 keywords from `references.md` -> [High-CTR Keywords].\r\n - Select 2 formulas from `references.md` -> [Templates].\r\n3. **Drafting**: Generate 10 candidates.\r\n - *Style Injection*: Mimic the \"Good Output\" tone from the matched `examples.md` category.\r\n4. **Filtering (Virtual Script Execution)**:\r\n - Apply logic from `validator.py`.\r\n - Discard any title that feels \"AI-generated\" (e.g., uses \"Exploring\", \"Comprehensive\").\r\n5. **Final Presentation**: Output the top 5 survivors with strategy tags.\r\n\r\n## 4. User Interaction Trigger\r\n- **Input**: User provides raw text or a topic.\r\n- **Response**: A structured list of 5 titles + 1 brief advice on cover image (Visual).", "source_url": "https://clawhub.ai/GXKIM/xiaohongshu-title", "repository_url": "https://github.com/GXKIM/xiaohongshu-title", "categories": [], "tags": [], "status": "approved", "featured": 0, "review_note": null, "approved_at": null, "approved_by": null, "created_at": "2026-02-10T01:49:43.979Z", "updated_at": "2026-02-28T03:50:11.563Z", "stars_total": 1, "stars_clawhub": 1, "stars_ours": 0, "downloads": 1820, "installs_current": 5, "installs_all_time": 8, "author": { "citizen_id": null, "handle": "GXKIM", "display_name": "GXKIM", "tier": null, "trust": null, "reputation": null } }, { "id": "568c13d1-cccd-4456-8a9d-faae67170042", "owner_account_id": "b9a8f519-797e-4320-bb85-6834738d6676", "slug": "box", "name": "Box", "summary": "Box API integration with managed OAuth. Manage files, folders, collaborations, and cloud storage.\nUse this skill when users want to upload, download, share, or organize files and folders in Box.\nFor other third party apps, use the api-gateway skill (https://clawhub.ai/byungkyu/api-gateway).\nRequires network access and valid Maton API key.", "content_md": "---\nname: box\ndescription: |\n Box API integration with managed OAuth. Manage files, folders, collaborations, and cloud storage.\n Use this skill when users want to upload, download, share, or organize files and folders in Box.\n For other third party apps, use the api-gateway skill (https://clawhub.ai/byungkyu/api-gateway).\n Requires network access and valid Maton API key.\nmetadata:\n author: maton\n version: \"1.0\"\n clawdbot:\n emoji: 🧠\n requires:\n env:\n - MATON_API_KEY\n---\n\n# Box\n\nAccess the Box API with managed OAuth authentication. Manage files, folders, collaborations, shared links, and cloud storage.\n\n## Quick Start\n\n```bash\n# Get current user info\npython <<'EOF'\nimport urllib.request, os, json\nreq = urllib.request.Request('https://gateway.maton.ai/box/2.0/users/me')\nreq.add_header('Authorization', f'Bearer {os.environ[\"MATON_API_KEY\"]}')\nprint(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))\nEOF\n```\n\n## Base URL\n\n```\nhttps://gateway.maton.ai/box/2.0/{resource}\n```\n\nThe gateway proxies requests to `api.box.com/2.0` and automatically injects your OAuth token.\n\n## Authentication\n\nAll requests require the Maton API key in the Authorization header:\n\n```\nAuthorization: Bearer $MATON_API_KEY\n```\n\n**Environment Variable:** Set your API key as `MATON_API_KEY`:\n\n```bash\nexport MATON_API_KEY=\"YOUR_API_KEY\"\n```\n\n### Getting Your API Key\n\n1. Sign in or create an account at [maton.ai](https://maton.ai)\n2. Go to [maton.ai/settings](https://maton.ai/settings)\n3. Copy your API key\n\n## Connection Management\n\nManage your Box OAuth connections at `https://ctrl.maton.ai`.\n\n### List Connections\n\n```bash\npython <<'EOF'\nimport urllib.request, os, json\nreq = urllib.request.Request('https://ctrl.maton.ai/connections?app=box&status=ACTIVE')\nreq.add_header('Authorization', f'Bearer {os.environ[\"MATON_API_KEY\"]}')\nprint(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))\nEOF\n```\n\n### Create Connection\n\n```bash\npython <<'EOF'\nimport urllib.request, os, json\ndata = json.dumps({'app': 'box'}).encode()\nreq = urllib.request.Request('https://ctrl.maton.ai/connections', data=data, method='POST')\nreq.add_header('Authorization', f'Bearer {os.environ[\"MATON_API_KEY\"]}')\nreq.add_header('Content-Type', 'application/json')\nprint(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))\nEOF\n```\n\n### Get Connection\n\n```bash\npython <<'EOF'\nimport urllib.request, os, json\nreq = urllib.request.Request('https://ctrl.maton.ai/connections/{connection_id}')\nreq.add_header('Authorization', f'Bearer {os.environ[\"MATON_API_KEY\"]}')\nprint(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))\nEOF\n```\n\n**Response:**\n```json\n{\n \"connection\": {\n \"connection_id\": \"bd484938-0902-4fc0-9ffb-2549d7d91f1d\",\n \"status\": \"ACTIVE\",\n \"creation_time\": \"2026-02-08T21:14:41.808115Z\",\n \"last_updated_time\": \"2026-02-08T21:16:10.100340Z\",\n \"url\": \"https://connect.maton.ai/?session_token=...\",\n \"app\": \"box\",\n \"metadata\": {}\n }\n}\n```\n\nOpen the returned `url` in a browser to complete OAuth authorization.\n\n### Delete Connection\n\n```bash\npython <<'EOF'\nimport urllib.request, os, json\nreq = urllib.request.Request('https://ctrl.maton.ai/connections/{connection_id}', method='DELETE')\nreq.add_header('Authorization', f'Bearer {os.environ[\"MATON_API_KEY\"]}')\nprint(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))\nEOF\n```\n\n### Specifying Connection\n\nIf you have multiple Box connections, specify which one to use with the `Maton-Connection` header:\n\n```bash\npython <<'EOF'\nimport urllib.request, os, json\nreq = urllib.request.Request('https://gateway.maton.ai/box/2.0/users/me')\nreq.add_header('Authorization', f'Bearer {os.environ[\"MATON_API_KEY\"]}')\nreq.add_header('Maton-Connection', 'bd484938-0902-4fc0-9ffb-2549d7d91f1d')\nprint(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))\nEOF\n```\n\nIf omitted, the gateway uses the default (oldest) active connection.\n\n## API Reference\n\n### User Info\n\n#### Get Current User\n\n```bash\nGET /box/2.0/users/me\n```\n\n**Response:**\n```json\n{\n \"type\": \"user\",\n \"id\": \"48806418054\",\n \"name\": \"Chris\",\n \"login\": \"chris@example.com\",\n \"created_at\": \"2026-02-08T13:12:34-08:00\",\n \"modified_at\": \"2026-02-08T13:12:35-08:00\",\n \"language\": \"en\",\n \"timezone\": \"America/Los_Angeles\",\n \"space_amount\": 10737418240,\n \"space_used\": 0,\n \"max_upload_size\": 262144000,\n \"status\": \"active\",\n \"avatar_url\": \"https://app.box.com/api/avatar/large/48806418054\"\n}\n```\n\n#### Get User\n\n```bash\nGET /box/2.0/users/{user_id}\n```\n\n### Folder Operations\n\n#### Get Root Folder\n\nThe root folder has ID `0`:\n\n```bash\nGET /box/2.0/folders/0\n```\n\n#### Get Folder\n\n```bash\nGET /box/2.0/folders/{folder_id}\n```\n\n**Response:**\n```json\n{\n \"type\": \"folder\",\n \"id\": \"365037181307\",\n \"name\": \"My Folder\",\n \"description\": \"Folder description\",\n \"size\": 0,\n \"path_collection\": {\n \"total_count\": 1,\n \"entries\": [\n {\"type\": \"folder\", \"id\": \"0\", \"name\": \"All Files\"}\n ]\n },\n \"created_by\": {\"type\": \"user\", \"id\": \"48806418054\", \"name\": \"Chris\"},\n \"owned_by\": {\"type\": \"user\", \"id\": \"48806418054\", \"name\": \"Chris\"},\n \"item_status\": \"active\"\n}\n```\n\n#### List Folder Items\n\n```bash\nGET /box/2.0/folders/{folder_id}/items\n```\n\nQuery parameters:\n- `limit` - Maximum items to return (default 100, max 1000)\n- `offset` - Offset for pagination\n- `fields` - Comma-separated list of fields to include\n\n**Response:**\n```json\n{\n \"total_count\": 1,\n \"entries\": [\n {\n \"type\": \"folder\",\n \"id\": \"365036703666\",\n \"name\": \"Subfolder\"\n }\n ],\n \"offset\": 0,\n \"limit\": 100\n}\n```\n\n#### Create Folder\n\n```bash\nPOST /box/2.0/folders\nContent-Type: application/json\n\n{\n \"name\": \"New Folder\",\n \"parent\": {\"id\": \"0\"}\n}\n```\n\n**Response:**\n```json\n{\n \"type\": \"folder\",\n \"id\": \"365037181307\",\n \"name\": \"New Folder\",\n \"created_at\": \"2026-02-08T14:56:17-08:00\"\n}\n```\n\n#### Update Folder\n\n```bash\nPUT /box/2.0/folders/{folder_id}\nContent-Type: application/json\n\n{\n \"name\": \"Updated Folder Name\",\n \"description\": \"Updated description\"\n}\n```\n\n#### Copy Folder\n\n```bash\nPOST /box/2.0/folders/{folder_id}/copy\nContent-Type: application/json\n\n{\n \"name\": \"Copied Folder\",\n \"parent\": {\"id\": \"0\"}\n}\n```\n\n#### Delete Folder\n\n```bash\nDELETE /box/2.0/folders/{folder_id}\n```\n\nQuery parameters:\n- `recursive` - Set to `true` to delete non-empty folders\n\nReturns 204 No Content on success.\n\n### File Operations\n\n#### Get File Info\n\n```bash\nGET /box/2.0/files/{file_id}\n```\n\n#### Download File\n\n```bash\nGET /box/2.0/files/{file_id}/content\n```\n\nReturns a redirect to the download URL.\n\n#### Upload File\n\n```bash\nPOST https://upload.box.com/api/2.0/files/content\nContent-Type: multipart/form-data\n\nattributes={\"name\":\"file.txt\",\"parent\":{\"id\":\"0\"}}\nfile=\n```\n\n**Note:** File uploads use a different base URL: `upload.box.com`\n\n#### Update File Info\n\n```bash\nPUT /box/2.0/files/{file_id}\nContent-Type: application/json\n\n{\n \"name\": \"renamed-file.txt\",\n \"description\": \"File description\"\n}\n```\n\n#### Copy File\n\n```bash\nPOST /box/2.0/files/{file_id}/copy\nContent-Type: application/json\n\n{\n \"name\": \"copied-file.txt\",\n \"parent\": {\"id\": \"0\"}\n}\n```\n\n#### Delete File\n\n```bash\nDELETE /box/2.0/files/{file_id}\n```\n\nReturns 204 No Content on success.\n\n#### Get File Versions\n\n```bash\nGET /box/2.0/files/{file_id}/versions\n```\n\n### Shared Links\n\nCreate a shared link by updating a file or folder:\n\n```bash\nPUT /box/2.0/folders/{folder_id}\nContent-Type: application/json\n\n{\n \"shared_link\": {\n \"access\": \"open\"\n }\n}\n```\n\nAccess levels:\n- `open` - Anyone with the link\n- `company` - Only users in the enterprise\n- `collaborators` - Only collaborators\n\n**Response includes:**\n```json\n{\n \"shared_link\": {\n \"url\": \"https://app.box.com/s/sisarrztrenabyygfwqggbwommf8uucv\",\n \"access\": \"open\",\n \"effective_access\": \"open\",\n \"is_password_enabled\": false,\n \"permissions\": {\n \"can_preview\": true,\n \"can_download\": true,\n \"can_edit\": false\n }\n }\n}\n```\n\n### Collaborations\n\n#### List Folder Collaborations\n\n```bash\nGET /box/2.0/folders/{folder_id}/collaborations\n```\n\n#### Create Collaboration\n\n```bash\nPOST /box/2.0/collaborations\nContent-Type: application/json\n\n{\n \"item\": {\"type\": \"folder\", \"id\": \"365037181307\"},\n \"accessible_by\": {\"type\": \"user\", \"login\": \"user@example.com\"},\n \"role\": \"editor\"\n}\n```\n\nRoles: `editor`, `viewer`, `previewer`, `uploader`, `previewer_uploader`, `viewer_uploader`, `co-owner`\n\n#### Update Collaboration\n\n```bash\nPUT /box/2.0/collaborations/{collaboration_id}\nContent-Type: application/json\n\n{\n \"role\": \"viewer\"\n}\n```\n\n#### Delete Collaboration\n\n```bash\nDELETE /box/2.0/collaborations/{collaboration_id}\n```\n\n### Search\n\n```bash\nGET /box/2.0/search?query=document\n```\n\nQuery parameters:\n- `query` - Search query (required)\n- `type` - Filter by type: `file`, `folder`, `web_link`\n- `file_extensions` - Comma-separated extensions\n- `ancestor_folder_ids` - Limit to specific folders\n- `limit` - Max results (default 30)\n- `offset` - Pagination offset\n\n**Response:**\n```json\n{\n \"total_count\": 5,\n \"entries\": [...],\n \"limit\": 30,\n \"offset\": 0,\n \"type\": \"search_results_items\"\n}\n```\n\n### Events\n\n```bash\nGET /box/2.0/events\n```\n\nQuery parameters:\n- `stream_type` - `all`, `changes`, `sync`, `admin_logs`\n- `stream_position` - Position to start from\n- `limit` - Max events to return\n\n**Response:**\n```json\n{\n \"chunk_size\": 4,\n \"next_stream_position\": \"30401068076164269\",\n \"entries\": [...]\n}\n```\n\n### Trash\n\n#### List Trashed Items\n\n```bash\nGET /box/2.0/folders/trash/items\n```\n\n#### Get Trashed Item\n\n```bash\nGET /box/2.0/files/{file_id}/trash\nGET /box/2.0/folders/{folder_id}/trash\n```\n\n#### Restore Trashed Item\n\n```bash\nPOST /box/2.0/files/{file_id}\nPOST /box/2.0/folders/{folder_id}\n```\n\n#### Permanently Delete\n\n```bash\nDELETE /box/2.0/files/{file_id}/trash\nDELETE /box/2.0/folders/{folder_id}/trash\n```\n\n### Collections (Favorites)\n\n#### List Collections\n\n```bash\nGET /box/2.0/collections\n```\n\n**Response:**\n```json\n{\n \"total_count\": 1,\n \"entries\": [\n {\n \"type\": \"collection\",\n \"name\": \"Favorites\",\n \"collection_type\": \"favorites\",\n \"id\": \"35223030868\"\n }\n ]\n}\n```\n\n#### Get Collection Items\n\n```bash\nGET /box/2.0/collections/{collection_id}/items\n```\n\n### Recent Items\n\n```bash\nGET /box/2.0/recent_items\n```\n\n### Webhooks\n\n#### List Webhooks\n\n```bash\nGET /box/2.0/webhooks\n```\n\n#### Create Webhook\n\n```bash\nPOST /box/2.0/webhooks\nContent-Type: application/json\n\n{\n \"target\": {\"id\": \"365037181307\", \"type\": \"folder\"},\n \"address\": \"https://example.com/webhook\",\n \"triggers\": [\"FILE.UPLOADED\", \"FILE.DOWNLOADED\"]\n}\n```\n\n**Note:** Webhook creation may require enterprise permissions.\n\n#### Delete Webhook\n\n```bash\nDELETE /box/2.0/webhooks/{webhook_id}\n```\n\n## Pagination\n\nBox uses offset-based pagination:\n\n```bash\nGET /box/2.0/folders/0/items?limit=100&offset=0\nGET /box/2.0/folders/0/items?limit=100&offset=100\n```\n\nSome endpoints use marker-based pagination with `marker` parameter.\n\n**Response:**\n```json\n{\n \"total_count\": 250,\n \"entries\": [...],\n \"offset\": 0,\n \"limit\": 100\n}\n```\n\n## Code Examples\n\n### JavaScript\n\n```javascript\nconst response = await fetch(\n 'https://gateway.maton.ai/box/2.0/folders/0/items',\n {\n headers: {\n 'Authorization': `Bearer ${process.env.MATON_API_KEY}`\n }\n }\n);\nconst data = await response.json();\n```\n\n### Python\n\n```python\nimport os\nimport requests\n\nresponse = requests.get(\n 'https://gateway.maton.ai/box/2.0/folders/0/items',\n headers={'Authorization': f'Bearer {os.environ[\"MATON_API_KEY\"]}'}\n)\ndata = response.json()\n```\n\n### Python (Create Folder)\n\n```python\nimport os\nimport requests\n\nresponse = requests.post(\n 'https://gateway.maton.ai/box/2.0/folders',\n headers={\n 'Authorization': f'Bearer {os.environ[\"MATON_API_KEY\"]}',\n 'Content-Type': 'application/json'\n },\n json={\n 'name': 'New Folder',\n 'parent': {'id': '0'}\n }\n)\nfolder = response.json()\nprint(f\"Created folder: {folder['id']}\")\n```\n\n## Notes\n\n- Root folder ID is `0`\n- File uploads use `upload.box.com` instead of `api.box.com`\n- Delete operations return 204 No Content on success\n- Use `fields` parameter to request specific fields and reduce response size\n- Shared links can have password protection and expiration dates\n- Some operations (list users, create webhooks) require enterprise admin permissions\n- ETags can be used for conditional updates with `If-Match` header\n- IMPORTANT: When piping curl output to `jq` or other commands, environment variables like `$MATON_API_KEY` may not expand correctly in some shell environments\n\n## Error Handling\n\n| Status | Meaning |\n|--------|---------|\n| 400 | Missing Box connection or bad request |\n| 401 | Invalid or missing Maton API key |\n| 403 | Insufficient permissions for the operation |\n| 404 | Resource not found |\n| 409 | Conflict (e.g., item with same name exists) |\n| 429 | Rate limited |\n| 4xx/5xx | Passthrough error from Box API |\n\nBox errors include detailed messages:\n```json\n{\n \"type\": \"error\",\n \"status\": 409,\n \"code\": \"item_name_in_use\",\n \"message\": \"Item with the same name already exists\"\n}\n```\n\n### Troubleshooting: API Key Issues\n\n1. Check that the `MATON_API_KEY` environment variable is set:\n\n```bash\necho $MATON_API_KEY\n```\n\n2. Verify the API key is valid by listing connections:\n\n```bash\npython <<'EOF'\nimport urllib.request, os, json\nreq = urllib.request.Request('https://ctrl.maton.ai/connections')\nreq.add_header('Authorization', f'Bearer {os.environ[\"MATON_API_KEY\"]}')\nprint(json.dumps(json.load(urllib.request.urlopen(req)), indent=2))\nEOF\n```\n\n### Troubleshooting: Invalid App Name\n\n1. Ensure your URL path starts with `box`. For example:\n\n- Correct: `https://gateway.maton.ai/box/2.0/users/me`\n- Incorrect: `https://gateway.maton.ai/2.0/users/me`\n\n## Resources\n\n- [Box API Reference](https://developer.box.com/reference)\n- [Box Developer Documentation](https://developer.box.com/guides)\n- [Authentication Guide](https://developer.box.com/guides/authentication)\n- [Box SDKs](https://developer.box.com/sdks-and-tools)\n- [Maton Community](https://discord.com/invite/dBfFAcefs2)\n- [Maton Support](mailto:support@maton.ai)\n", "source_url": "https://clawhub.ai/byungkyu/box", "repository_url": "https://github.com/byungkyu/box", "categories": [], "tags": [], "status": "approved", "featured": 0, "review_note": null, "approved_at": null, "approved_by": null, "created_at": "2026-02-09T11:51:26.876Z", "updated_at": "2026-02-26T00:05:41.505Z", "stars_total": 2, "stars_clawhub": 2, "stars_ours": 0, "downloads": 3103, "installs_current": 2, "installs_all_time": 2, "author": { "citizen_id": null, "handle": "byungkyu", "display_name": "byungkyu", "tier": null, "trust": null, "reputation": null } }, { "id": "f681557f-208e-47c4-b482-efdabadce415", "owner_account_id": "b9a8f519-797e-4320-bb85-6834738d6676", "slug": "gh", "name": "gh", "summary": "Use the GitHub CLI (gh) to perform core GitHub operations: auth status, repo create/clone/fork, issues, pull requests, releases, and basic repo management. Trigger for requests to use gh, manage GitHub repos, PRs, or issues from the CLI.", "content_md": "---\nname: gh\ndescription: \"Use the GitHub CLI (gh) to perform core GitHub operations: auth status, repo create/clone/fork, issues, pull requests, releases, and basic repo management. Trigger for requests to use gh, manage GitHub repos, PRs, or issues from the CLI.\"\n---\n\n# GitHub CLI (gh)\n\n## Overview\nUse `gh` for authenticated GitHub operations from the terminal. Prefer explicit, idempotent commands and report URLs back to the user.\n\n## Quick checks\n- Auth status:\n```bash\ngh auth status\n```\n- Current repo context:\n```bash\ngh repo view --json nameWithOwner,url,defaultBranchRef\n```\n\n## Core workflows\n\n### Repo create (private by default)\n```bash\ngh repo create OWNER/NAME --private --confirm --description \"...\"\n```\nIf running inside a local repo, use `--source . --remote origin --push`.\n\n### Clone / fork\n```bash\ngh repo clone OWNER/NAME\n```\n```bash\ngh repo fork OWNER/NAME --clone\n```\n\n### Issues\n- List:\n```bash\ngh issue list --limit 20\n```\n- Create:\n```bash\ngh issue create --title \"...\" --body \"...\"\n```\n- Comment:\n```bash\ngh issue comment --body \"...\"\n```\n\n### Pull requests\n- Create from current branch:\n```bash\ngh pr create --title \"...\" --body \"...\"\n```\n- List:\n```bash\ngh pr list --limit 20\n```\n- View:\n```bash\ngh pr view --web\n```\n- Merge (use explicit method):\n```bash\ngh pr merge --merge\n```\n\n### Releases\n```bash\ngh release create vX.Y.Z --title \"vX.Y.Z\" --notes \"...\"\n```\n\n## Safety notes\n- Confirm the target repo/owner before destructive actions (delete, force push).\n- For private repos, ensure `--private` is set on create.\n- Prefer `--confirm` to avoid interactive prompts in automation.\n", "source_url": "https://clawhub.ai/Trumppo/gh", "repository_url": "https://github.com/Trumppo/gh", "categories": [], "tags": [], "status": "approved", "featured": 0, "review_note": null, "approved_at": null, "approved_by": null, "created_at": "2026-02-08T17:58:16.527Z", "updated_at": "2026-02-28T03:44:14.402Z", "stars_total": 2, "stars_clawhub": 2, "stars_ours": 0, "downloads": 2112, "installs_current": 16, "installs_all_time": 16, "author": { "citizen_id": null, "handle": "Trumppo", "display_name": "Trumppo", "tier": null, "trust": null, "reputation": null } }, { "id": "5c1402e6-4bc5-4de5-96c6-f0fc2b1a2ccd", "owner_account_id": "b9a8f519-797e-4320-bb85-6834738d6676", "slug": "moltlog", "name": "moltlog", "summary": "Retired placeholder skill for moltlog. This skill is intentionally non-functional and exists only to state that moltlog has been deleted.", "content_md": "---\nname: moltlog\ndescription: Retired placeholder skill for moltlog. This skill is intentionally non-functional and exists only to state that moltlog has been deleted.\n---\n\n# moltlog (retired)\n\nThis skill is closed and intentionally empty.\n\n- Status: deleted\n- Purpose: deletion + gratitude notice only\n- Behavior: provides no executable steps, scripts, or operational logic\n\nRequired response:\n- \"The moltlog skill has been deleted and should not be used. Thank you for using it. It was not used by many people, but it taught us a lot and gave us many discoveries. See you somewhere else.\"\n", "source_url": "https://clawhub.ai/NaoyukiOguma/moltlog", "repository_url": "https://github.com/NaoyukiOguma/moltlog", "categories": [], "tags": [], "status": "approved", "featured": 0, "review_note": null, "approved_at": null, "approved_by": null, "created_at": "2026-02-08T15:11:44.106Z", "updated_at": "2026-02-25T20:10:43.151Z", "stars_total": 2, "stars_clawhub": 2, "stars_ours": 0, "downloads": 1715, "installs_current": 0, "installs_all_time": 0, "author": { "citizen_id": null, "handle": "NaoyukiOguma", "display_name": "NaoyukiOguma", "tier": null, "trust": null, "reputation": null } }, { "id": "75a4b327-7ed1-42f9-b816-e2307885948f", "owner_account_id": "b9a8f519-797e-4320-bb85-6834738d6676", "slug": "technical-seo-checker", "name": "Technical Seo Checker", "summary": "This skill should be used when the user asks to \"technical SEO audit\", \"check page speed\", \"Core Web Vitals\", \"LCP is slow\", \"CLS problem\", \"INP issues\", \"cr...", "content_md": "---\nname: technical-seo-checker\nversion: \"3.0.0\"\ndescription: 'This skill should be used when the user asks to \"technical SEO audit\", \"check page speed\", \"Core Web Vitals\", \"LCP is slow\", \"CLS problem\", \"INP issues\", \"crawl errors\", \"indexing problems\", \"robots.txt check\", \"XML sitemap errors\", \"hreflang issues\", \"canonical tag problems\", \"HTTPS not working\", \"mobile SEO\", \"JavaScript rendering\", or \"site health check\". Performs comprehensive technical SEO audits: Core Web Vitals (LCP/CLS/INP/TTFB), crawlability, indexability, mobile-friendliness, HTTPS/HSTS security, URL structure, redirect chains, robots.txt, XML sitemaps, hreflang, canonical tags, and structured data validation. Produces a scored technical health report (0–100) with critical/high/medium issue triage and a prioritized implementation roadmap. Works with Google PageSpeed Insights, Google Search Console, crawl tools, or manual audit. For content element issues, see on-page-seo-auditor. For link architecture, see internal-linking-optimizer.'\nlicense: Apache-2.0\ncompatibility: \"Claude Code ≥1.0, skills.sh marketplace, ClawHub marketplace, Vercel Labs skills ecosystem. No system packages required. Optional: MCP network access for SEO tool integrations.\"\nallowed-tools: WebFetch\nmetadata:\n author: aaron-he-zhu\n version: \"3.0.0\"\n geo-relevance: \"low\"\n tags:\n - seo\n - technical seo\n - page speed\n - core web vitals\n - crawlability\n - indexability\n - mobile-friendly\n - site speed\n - security audit\n - core-web-vitals\n - page-speed\n - lcp\n - cls\n - inp\n - ttfb\n - crawl-errors\n - robots-txt\n - xml-sitemap\n - hreflang\n - canonicalization\n - https\n - mobile-seo\n - redirect-chains\n - javascript-rendering\n - site-health\n triggers:\n - \"technical SEO audit\"\n - \"check page speed\"\n - \"crawl issues\"\n - \"Core Web Vitals\"\n - \"site indexing problems\"\n - \"mobile-friendly check\"\n - \"site speed\"\n - \"my site is slow\"\n - \"Google can't crawl my site\"\n - \"mobile issues\"\n - \"indexing problems\"\n---\n\n# Technical SEO Checker\n\n\n> **[SEO & GEO Skills Library](https://skills.sh/aaron-he-zhu/seo-geo-claude-skills)** · 20 skills for SEO + GEO · Install all: `npx skills add aaron-he-zhu/seo-geo-claude-skills`\n\n

Browse all 20 skills

\n\n**Research** · [keyword-research](../../research/keyword-research/) · [competitor-analysis](../../research/competitor-analysis/) · [serp-analysis](../../research/serp-analysis/) · [content-gap-analysis](../../research/content-gap-analysis/)\n\n**Build** · [seo-content-writer](../../build/seo-content-writer/) · [geo-content-optimizer](../../build/geo-content-optimizer/) · [meta-tags-optimizer](../../build/meta-tags-optimizer/) · [schema-markup-generator](../../build/schema-markup-generator/)\n\n**Optimize** · [on-page-seo-auditor](../on-page-seo-auditor/) · **technical-seo-checker** · [internal-linking-optimizer](../internal-linking-optimizer/) · [content-refresher](../content-refresher/)\n\n**Monitor** · [rank-tracker](../../monitor/rank-tracker/) · [backlink-analyzer](../../monitor/backlink-analyzer/) · [performance-reporter](../../monitor/performance-reporter/) · [alert-manager](../../monitor/alert-manager/)\n\n**Cross-cutting** · [content-quality-auditor](../../cross-cutting/content-quality-auditor/) · [domain-authority-auditor](../../cross-cutting/domain-authority-auditor/) · [entity-optimizer](../../cross-cutting/entity-optimizer/) · [memory-management](../../cross-cutting/memory-management/)\n\n

\n\nThis skill performs comprehensive technical SEO audits to identify issues that may prevent search engines from properly crawling, indexing, and ranking your site.\n\n## When to Use This Skill\n\n- Launching a new website\n- Diagnosing ranking drops\n- Pre-migration SEO audits\n- Regular technical health checks\n- Identifying crawl and index issues\n- Improving site performance\n- Fixing Core Web Vitals issues\n\n## What This Skill Does\n\n1. **Crawlability Audit**: Checks robots.txt, sitemaps, crawl issues\n2. **Indexability Review**: Analyzes index status and blockers\n3. **Site Speed Analysis**: Evaluates Core Web Vitals and performance\n4. **Mobile-Friendliness**: Checks mobile optimization\n5. **Security Check**: Reviews HTTPS and security headers\n6. **Structured Data Audit**: Validates schema markup\n7. **URL Structure Analysis**: Reviews URL patterns and redirects\n8. **International SEO**: Checks hreflang and localization\n\n## How to Use\n\n### Full Technical Audit\n\n```\nPerform a technical SEO audit for [URL/domain]\n```\n\n### Specific Issue Check\n\n```\nCheck Core Web Vitals for [URL]\n```\n\n```\nAudit crawlability and indexability for [domain]\n```\n\n### Pre-Migration Audit\n\n```\nTechnical SEO checklist for migrating [old domain] to [new domain]\n```\n\n## Data Sources\n\n> See [CONNECTORS.md](../../CONNECTORS.md) for tool category placeholders.\n\n**With ~~web crawler + ~~page speed tool + ~~CDN connected:**\nClaude can automatically crawl the entire site structure via ~~web crawler, pull Core Web Vitals and performance metrics from ~~page speed tool, analyze caching headers from ~~CDN, and fetch mobile-friendliness data. This enables comprehensive automated technical audits.\n\n**With manual data only:**\nAsk the user to provide:\n1. Site URL(s) to audit\n2. PageSpeed Insights screenshots or reports\n3. robots.txt file content\n4. sitemap.xml URL or file\n\nProceed with the full audit using provided data. Note in the output which findings are from automated crawl vs. manual review.\n\n## Instructions\n\nWhen a user requests a technical SEO audit:\n\n1. **Audit Crawlability**\n\n ```markdown\n ## Crawlability Analysis\n \n ### Robots.txt Review\n \n **URL**: [domain]/robots.txt\n **Status**: [Found/Not Found/Error]\n \n **Current Content**:\n ```\n [robots.txt content]\n ```\n \n | Check | Status | Notes |\n |-------|--------|-------|\n | File exists | ✅/❌ | [notes] |\n | Valid syntax | ✅/⚠️/❌ | [errors found] |\n | Sitemap declared | ✅/❌ | [sitemap URL] |\n | Important pages blocked | ✅/⚠️/❌ | [blocked paths] |\n | Assets blocked | ✅/⚠️/❌ | [CSS/JS blocked?] |\n | Correct user-agents | ✅/⚠️/❌ | [notes] |\n \n **Issues Found**:\n - [Issue 1]\n - [Issue 2]\n \n **Recommended robots.txt**:\n ```\n User-agent: *\n Allow: /\n Disallow: /admin/\n Disallow: /private/\n \n Sitemap: https://example.com/sitemap.xml\n ```\n \n ---\n \n ### XML Sitemap Review\n \n **Sitemap URL**: [URL]\n **Status**: [Found/Not Found/Error]\n \n | Check | Status | Notes |\n |-------|--------|-------|\n | Sitemap exists | ✅/❌ | [notes] |\n | Valid XML format | ✅/⚠️/❌ | [errors] |\n | In robots.txt | ✅/❌ | [notes] |\n | Submitted to ~~search console | ✅/⚠️/❌ | [notes] |\n | URLs count | [X] | [appropriate?] |\n | Only indexable URLs | ✅/⚠️/❌ | [notes] |\n | Includes priority | ✅/⚠️ | [notes] |\n | Includes lastmod | ✅/⚠️ | [accurate?] |\n \n **Issues Found**:\n - [Issue 1]\n \n ---\n \n ### Crawl Budget Analysis\n \n | Factor | Status | Impact |\n |--------|--------|--------|\n | Crawl errors | [X] errors | [Low/Med/High] |\n | Duplicate content | [X] pages | [Low/Med/High] |\n | Thin content | [X] pages | [Low/Med/High] |\n | Redirect chains | [X] found | [Low/Med/High] |\n | Orphan pages | [X] found | [Low/Med/High] |\n \n **Crawlability Score**: [X]/10\n ```\n\n2. **Audit Indexability**\n\n ```markdown\n ## Indexability Analysis\n \n ### Index Status Overview\n \n | Metric | Count | Notes |\n |--------|-------|-------|\n | Pages in sitemap | [X] | |\n | Pages indexed | [X] | [source: site: search] |\n | Index coverage ratio | [X]% | [good if >90%] |\n \n ### Index Blockers Check\n \n | Blocker Type | Found | Pages Affected |\n |--------------|-------|----------------|\n | noindex meta tag | [X] | [list or \"none\"] |\n | noindex X-Robots | [X] | [list or \"none\"] |\n | Robots.txt blocked | [X] | [list or \"none\"] |\n | Canonical to other | [X] | [list or \"none\"] |\n | 4xx/5xx errors | [X] | [list or \"none\"] |\n | Redirect loops | [X] | [list or \"none\"] |\n \n ### Canonical Tags Audit\n \n | Check | Status | Notes |\n |-------|--------|-------|\n | Canonicals present | ✅/⚠️/❌ | [X]% of pages |\n | Self-referencing | ✅/⚠️/❌ | [notes] |\n | Consistent (HTTP/HTTPS) | ✅/⚠️/❌ | [notes] |\n | Consistent (www/non-www) | ✅/⚠️/❌ | [notes] |\n | No conflicting signals | ✅/⚠️/❌ | [notes] |\n \n ### Duplicate Content Issues\n \n | Issue Type | Count | Examples |\n |------------|-------|----------|\n | Exact duplicates | [X] | [URLs] |\n | Near duplicates | [X] | [URLs] |\n | Parameter duplicates | [X] | [URLs] |\n | WWW/non-WWW | [X] | [notes] |\n | HTTP/HTTPS | [X] | [notes] |\n \n **Indexability Score**: [X]/10\n ```\n\n3. **Audit Site Speed & Core Web Vitals** — CWV metrics (LCP/FID/CLS/INP), additional performance metrics (TTFB/FCP/Speed Index/TBT), resource loading breakdown, optimization recommendations\n\n > **Reference**: See [references/technical-audit-templates.md](./references/technical-audit-templates.md) for the performance analysis template (Step 3).\n\n4. **Audit Mobile-Friendliness** — Mobile-friendly test, responsive design check, mobile-first indexing verification\n\n > **Reference**: See [references/technical-audit-templates.md](./references/technical-audit-templates.md) for the mobile optimization template (Step 4).\n\n5. **Audit Security & HTTPS** — SSL certificate, HTTPS enforcement, mixed content, HSTS, security headers (CSP, X-Frame-Options, etc.)\n\n > **Reference**: See [references/technical-audit-templates.md](./references/technical-audit-templates.md) for the security analysis template (Step 5).\n\n6. **Audit URL Structure** — URL patterns, issues (dynamic params, session IDs, uppercase), redirect analysis (chains, loops, 302s)\n\n > **Reference**: See [references/technical-audit-templates.md](./references/technical-audit-templates.md) for the URL structure template (Step 6).\n\n7. **Audit Structured Data** — Schema markup validation, missing schema opportunities. CORE-EEAT alignment: maps to O05.\n\n > **Reference**: See [references/technical-audit-templates.md](./references/technical-audit-templates.md) for the structured data template (Step 7).\n\n8. **Audit International SEO (if applicable)** — Hreflang implementation, language/region targeting\n\n > **Reference**: See [references/technical-audit-templates.md](./references/technical-audit-templates.md) for the international SEO template (Step 8).\n\n9. **Generate Technical Audit Summary** — Overall health score with visual breakdown, critical/high/medium issues, quick wins, implementation roadmap (weeks 1-4+), monitoring recommendations\n\n > **Reference**: See [references/technical-audit-templates.md](./references/technical-audit-templates.md) for the audit summary template (Step 9).\n\n## Validation Checkpoints\n\n### Input Validation\n- [ ] Site URL or domain clearly specified\n- [ ] Access to technical data (robots.txt, sitemap, or crawl results)\n- [ ] Performance metrics available (via ~~page speed tool or screenshots)\n\n### Output Validation\n- [ ] Every recommendation cites specific data points (not generic advice)\n- [ ] All issues include affected URLs or page counts\n- [ ] Performance metrics include actual numbers with units (seconds, KB, etc.)\n- [ ] Source of each data point clearly stated (~~web crawler data, ~~page speed tool, user-provided, or estimated)\n\n## Example\n\n> **Reference**: See [references/technical-audit-example.md](./references/technical-audit-example.md) for a full worked example (cloudhosting.com technical audit) and the comprehensive technical SEO checklist.\n\n## Tips for Success\n\n1. **Prioritize by impact** - Fix critical issues first\n2. **Monitor continuously** - Use ~~search console alerts\n3. **Test changes** - Verify fixes work before deploying widely\n4. **Document everything** - Track changes for troubleshooting\n5. **Regular audits** - Schedule quarterly technical reviews\n\n> **Technical reference**: For issue severity framework, prioritization matrix, and Core Web Vitals optimization quick reference, see [references/http-status-codes.md](./references/http-status-codes.md).\n\n## Reference Materials\n\n- [robots.txt Reference](./references/robots-txt-reference.md) — Syntax guide, templates, common configurations\n- [HTTP Status Codes](./references/http-status-codes.md) — SEO impact of each status code, redirect best practices\n- [Technical Audit Templates](./references/technical-audit-templates.md) — Detailed output templates for steps 3-9 (CWV, mobile, security, URL structure, structured data, international, audit summary)\n- [Technical Audit Example & Checklist](./references/technical-audit-example.md) — Full worked example and comprehensive technical SEO checklist\n\n## Related Skills\n\n- [on-page-seo-auditor](../on-page-seo-auditor/) — On-page SEO audit\n- [schema-markup-generator](../../build/schema-markup-generator/) — Fix schema issues\n- [performance-reporter](../../monitor/performance-reporter/) — Monitor improvements\n- [internal-linking-optimizer](../internal-linking-optimizer/) — Fix link issues\n- [alert-manager](../../monitor/alert-manager/) — Set up alerts for technical issues found\n- [content-quality-auditor](../../cross-cutting/content-quality-auditor/) — Full 80-item CORE-EEAT audit\n\n", "source_url": "https://clawhub.ai/aaron-he-zhu/technical-seo-checker", "repository_url": "https://github.com/aaron-he-zhu/technical-seo-checker", "categories": [], "tags": [], "status": "approved", "featured": 0, "review_note": null, "approved_at": null, "approved_by": null, "created_at": "2026-02-08T14:07:16.397Z", "updated_at": "2026-03-04T16:10:02.130Z", "stars_total": 2, "stars_clawhub": 2, "stars_ours": 0, "downloads": 2124, "installs_current": 10, "installs_all_time": 10, "author": { "citizen_id": null, "handle": "aaron-he-zhu", "display_name": "aaron-he-zhu", "tier": null, "trust": null, "reputation": null } }, { "id": "c750eada-f3fe-4f81-99f8-28e1cb9a2d83", "owner_account_id": "b9a8f519-797e-4320-bb85-6834738d6676", "slug": "seo-content-writer", "name": "Seo Content Writer", "summary": "This skill should be used when the user asks to \"write SEO content\", \"create a blog post\", \"write an article\", \"content writing for SEO\", \"draft optimized co...", "content_md": "---\nname: seo-content-writer\nversion: \"3.0.0\"\ndescription: 'This skill should be used when the user asks to \"write SEO content\", \"create a blog post\", \"write an article\", \"content writing for SEO\", \"draft optimized content\", \"write a how-to guide\", \"create a product description\", \"write a landing page\", \"SEO copywriting\", \"draft content targeting [keyword]\", or \"write 2000-word article about [topic]\". Creates keyword-optimized content using a 12-step workflow: CORE-EEAT pre-write checklist, keyword integration, title optimization (5 formula options), meta description, H1/H2/H3 hierarchy, featured snippet targeting, internal/external linking, and readability enhancement. Produces full drafts with embedded SEO elements, title variants, meta description, FAQ section with schema, and a self-scored CORE-EEAT checklist. For AI-citation optimization, see geo-content-optimizer. For updating existing content, see content-refresher.'\nlicense: Apache-2.0\ncompatibility: \"Claude Code ≥1.0, skills.sh marketplace, ClawHub marketplace, Vercel Labs skills ecosystem. No system packages required. Optional: MCP network access for SEO tool integrations.\"\nmetadata:\n author: aaron-he-zhu\n version: \"3.0.0\"\n geo-relevance: \"medium\"\n tags:\n - seo\n - content-writing\n - blog-writing\n - seo-copywriting\n - content-creation\n - featured-snippet-optimization\n - how-to-guide\n triggers:\n - \"write SEO content\"\n - \"create blog post\"\n - \"write an article\"\n - \"content writing\"\n - \"draft optimized content\"\n - \"write for SEO\"\n - \"blog writing\"\n - \"write me an article\"\n - \"create a blog post about\"\n - \"help me write SEO content\"\n - \"draft content for\"\n---\n\n# SEO Content Writer\n\n> **[SEO & GEO Skills Library](https://skills.sh/aaron-he-zhu/seo-geo-claude-skills)** · 20 skills for SEO + GEO · Install all: `npx skills add aaron-he-zhu/seo-geo-claude-skills`\n\n

Browse all 20 skills

\n\n**Research** · [keyword-research](../../research/keyword-research/) · [competitor-analysis](../../research/competitor-analysis/) · [serp-analysis](../../research/serp-analysis/) · [content-gap-analysis](../../research/content-gap-analysis/)\n\n**Build** · **seo-content-writer** · [geo-content-optimizer](../geo-content-optimizer/) · [meta-tags-optimizer](../meta-tags-optimizer/) · [schema-markup-generator](../schema-markup-generator/)\n\n**Optimize** · [on-page-seo-auditor](../../optimize/on-page-seo-auditor/) · [technical-seo-checker](../../optimize/technical-seo-checker/) · [internal-linking-optimizer](../../optimize/internal-linking-optimizer/) · [content-refresher](../../optimize/content-refresher/)\n\n**Monitor** · [rank-tracker](../../monitor/rank-tracker/) · [backlink-analyzer](../../monitor/backlink-analyzer/) · [performance-reporter](../../monitor/performance-reporter/) · [alert-manager](../../monitor/alert-manager/)\n\n**Cross-cutting** · [content-quality-auditor](../../cross-cutting/content-quality-auditor/) · [domain-authority-auditor](../../cross-cutting/domain-authority-auditor/) · [entity-optimizer](../../cross-cutting/entity-optimizer/) · [memory-management](../../cross-cutting/memory-management/)\n\n

\n\nThis skill creates search-engine-optimized content that ranks well while providing genuine value to readers. It applies proven SEO copywriting techniques, proper keyword integration, and optimal content structure.\n\n## When to Use This Skill\n\n- Writing blog posts targeting specific keywords\n- Creating landing pages optimized for search\n- Developing pillar content for topic clusters\n- Writing product descriptions for e-commerce\n- Creating service pages for local SEO\n- Producing how-to guides and tutorials\n- Writing comparison and review articles\n\n## What This Skill Does\n\n1. **Keyword Integration**: Naturally incorporates target and related keywords\n2. **Structure Optimization**: Creates scannable, well-organized content\n3. **Title & Meta Creation**: Writes compelling, click-worthy titles\n4. **Header Optimization**: Uses strategic H1-H6 hierarchy\n5. **Internal Linking**: Suggests relevant internal link opportunities\n6. **Readability Enhancement**: Ensures content is accessible and engaging\n7. **Featured Snippet Optimization**: Formats for SERP feature opportunities\n\n## How to Use\n\n### Basic Content Creation\n\n```\nWrite an SEO-optimized article about [topic] targeting the keyword [keyword]\n```\n\n```\nCreate a blog post for [topic] with these keywords: [keyword list]\n```\n\n### With Specific Requirements\n\n```\nWrite a 2,000-word guide about [topic] targeting [keyword],\ninclude FAQ section for featured snippets\n```\n\n### Content Briefs\n\n```\nHere's my content brief: [brief]. Write SEO-optimized content following this outline.\n```\n\n## Data Sources\n\n> See [CONNECTORS.md](../../CONNECTORS.md) for tool category placeholders.\n\n**With ~~SEO tool + ~~search console connected:**\nAutomatically pull keyword metrics (search volume, difficulty, CPC), competitor content analysis (top-ranking pages, content length, common topics), SERP features (featured snippets, PAA questions), and keyword opportunities (related keywords, question-based queries).\n\n**With manual data only:**\nAsk the user to provide:\n1. Target primary keyword and 3-5 secondary keywords\n2. Target audience and search intent (informational/commercial/transactional)\n3. Target word count and desired tone\n4. Any competitor URLs or content examples to reference\n\nProceed with the full workflow using provided data. Note in the output which metrics are from automated collection vs. user-provided data.\n\n## Instructions\n\nWhen a user requests SEO content:\n\n1. **Gather Requirements**\n\n Confirm or ask for:\n \n ```markdown\n ### Content Requirements\n \n **Primary Keyword**: [main keyword]\n **Secondary Keywords**: [2-5 related keywords]\n **Target Word Count**: [length]\n **Content Type**: [blog/guide/landing page/etc.]\n **Target Audience**: [who is this for]\n **Search Intent**: [informational/commercial/transactional]\n **Tone**: [professional/casual/technical/friendly]\n **CTA Goal**: [what action should readers take]\n **Competitor URLs**: [top ranking content to beat]\n ```\n\n2. **Load CORE-EEAT Quality Constraints**\n\n Before writing, load content quality standards from the [CORE-EEAT Benchmark](../../references/core-eeat-benchmark.md):\n\n ```markdown\n ### CORE-EEAT Pre-Write Checklist\n\n **Content Type**: [identified from requirements above]\n **Loaded Constraints** (high-weight items for this content type):\n\n Apply these standards while writing:\n\n | ID | Standard | How to Apply |\n |----|----------|-------------|\n | C01 | Intent Alignment | Title promise must match content delivery |\n | C02 | Direct Answer | Core answer in first 150 words |\n | C06 | Audience Targeting | State \"this article is for...\" |\n | C10 | Semantic Closure | Conclusion answers opening question + next steps |\n | O01 | Heading Hierarchy | H1→H2→H3, no level skipping |\n | O02 | Summary Box | Include TL;DR or Key Takeaways |\n | O06 | Section Chunking | Each section single topic; paragraphs 3–5 sentences |\n | O09 | Information Density | No filler; consistent terminology |\n | R01 | Data Precision | ≥5 precise numbers with units |\n | R02 | Citation Density | ≥1 external citation per 500 words |\n | R04 | Evidence-Claim Mapping | Every claim backed by evidence |\n | R07 | Entity Precision | Full names for people/orgs/products |\n | C03 | Query Coverage | Cover ≥3 query variants (synonyms, long-tail) |\n | O08 | Anchor Navigation | Table of contents with jump links |\n | O10 | Multimedia Structure | Images/videos have captions and carry information |\n | E07 | Practical Tools | Include downloadable templates, checklists, or calculators |\n\n _These 16 items apply across all content types. For content-type-specific dimension weights, see the Content-Type Weight Table in [core-eeat-benchmark.md](../../references/core-eeat-benchmark.md)._\n _Full 80-item benchmark: [references/core-eeat-benchmark.md](../../references/core-eeat-benchmark.md)_\n _For complete content quality audit: use [content-quality-auditor](../../cross-cutting/content-quality-auditor/)_\n ```\n\n3. **Research and Plan**\n\n Before writing:\n \n ```markdown\n ### Content Research\n \n **SERP Analysis**:\n - Top results format: [what's ranking]\n - Average word count: [X] words\n - Common sections: [list]\n - SERP features: [snippets, PAA, etc.]\n \n **Keyword Map**:\n - Primary: [keyword] - use in title, H1, intro, conclusion\n - Secondary: [keywords] - use in H2s, body paragraphs\n - LSI/Related: [terms] - sprinkle naturally throughout\n - Questions: [PAA questions] - use as H2/H3s or FAQ\n \n **Content Angle**:\n [What unique perspective or value will this content provide?]\n ```\n\n4. **Create Optimized Title**\n\n ```markdown\n ### Title Optimization\n \n **Requirements**:\n - Include primary keyword (preferably at start)\n - Under 60 characters for full SERP display\n - Compelling and click-worthy\n - Match search intent\n \n **Title Options**:\n \n 1. [Title option 1] ([X] chars)\n - Keyword position: [front/middle]\n - Power words: [list]\n \n 2. [Title option 2] ([X] chars)\n - Keyword position: [front/middle]\n - Power words: [list]\n \n **Recommended**: [Best option with reasoning]\n ```\n\n5. **Write Meta Description**\n\n ```markdown\n ### Meta Description\n \n **Requirements**:\n - 150-160 characters\n - Include primary keyword naturally\n - Include call-to-action\n - Compelling and specific\n \n **Meta Description**:\n \"[Description text]\" ([X] characters)\n \n **Elements included**:\n - ✅ Primary keyword\n - ✅ Value proposition\n - ✅ CTA or curiosity hook\n ```\n\n6. **Structure Content and Write**\n\n Structure: H1 (primary keyword, one per page) > Introduction (100-150 words, hook + promise + keyword in first 100 words) > H2 sections (secondary keywords/questions) > H3 sub-topics > FAQ section > Conclusion (summary + keyword + CTA).\n\n7. **Apply On-Page SEO Best Practices**\n\n Follow the on-page SEO checklist (keyword placement, content quality, readability, technical elements) and the content writing template (H1 with keyword, hook, sections with H2/H3, FAQ, conclusion with CTA).\n\n > **Reference**: See [references/seo-writing-checklist.md](./references/seo-writing-checklist.md) for the full on-page SEO checklist, content writing template, and featured snippet optimization patterns.\n\n Key requirements while writing:\n - Primary keyword in title, H1, first 100 words, at least one H2, and conclusion\n - Paragraphs of 3-5 sentences; varied sentence length; bullet points and bold key phrases\n - Internal links (2-5) and external authoritative links (2-3)\n - FAQ section with 40-60 word answers for featured snippet opportunity\n - Optimize for definition, list, table, and how-to snippets where applicable\n\n8. **Add Internal/External Links**\n\n ```markdown\n ### Link Recommendations\n \n **Internal Links** (include 2-5):\n 1. \"[anchor text]\" → [/your-page-url] (relevant because: [reason])\n 2. \"[anchor text]\" → [/your-page-url] (relevant because: [reason])\n \n **External Links** (include 2-3 authoritative sources):\n 1. \"[anchor text]\" → [authoritative-source.com] (supports: [claim])\n 2. \"[anchor text]\" → [authoritative-source.com] (supports: [claim])\n ```\n\n9. **Final SEO Review and CORE-EEAT Self-Check**\n\n Score content across 10 SEO factors (title, meta description, H1, keyword placement, H2s, internal links, external links, FAQ, readability, word count) and produce an Overall SEO Score out of 10.\n\n Then verify the 16 CORE-EEAT pre-write constraints (C01, C02, C06, C10, O01, O02, O06, O09, R01, R02, R04, R07, C03, O08, O10, E07) with pass/warning/fail status. List items needing attention.\n\n _For full 80-item audit, use [content-quality-auditor](../../cross-cutting/content-quality-auditor/)_\n\n## Validation Checkpoints\n\n### Input Validation\n- [ ] Primary keyword confirmed and matches search intent\n- [ ] Target word count specified (minimum 800 words for substantive content)\n- [ ] Content type and audience clearly defined\n- [ ] Competitor URLs reviewed or target SERP features identified\n\n### Output Validation\n- [ ] Keyword density within 1-2% for primary keyword (Note: Keyword density is a guideline, not a hard rule. Modern search engines prioritize semantic relevance and natural language over exact density targets. Focus on covering the topic comprehensively with semantic variants rather than hitting a specific percentage.)\n- [ ] All sections from outline covered completely\n- [ ] Internal links included (2-5 relevant links)\n- [ ] FAQ section present with at least 3 questions\n- [ ] Readability score appropriate for target audience\n- [ ] Source of each data point clearly stated (~~SEO tool data, user-provided, or estimated)\n\n## Example\n\n**User**: \"Write an SEO-optimized article about 'email marketing best practices' targeting small businesses\"\n\n> **Reference**: See [references/seo-writing-checklist.md](./references/seo-writing-checklist.md) for the full example output demonstrating a complete SEO article with meta description, H1/H2/H3 hierarchy, statistics with citations, comparison tables, FAQ section, and conclusion with CTA.\n\nThe example output demonstrates: keyword in H1 and first 100 words, statistics with sources (DMA, Emarsys), comparison tables, bullet-point lists, pro tips, FAQ section with 40-60 word answers, and a clear CTA in the conclusion.\n\n## Content Type Templates\n\n### How-To Guide\n\n```\nWrite a how-to guide for [task] targeting [keyword]\n```\n\n### Comparison Article\n\n```\nWrite a comparison article: [Option A] vs [Option B] for [keyword]\n```\n\n### Listicle\n\n```\nWrite a list post: \"X Best [Items] for [Audience/Purpose]\" targeting [keyword]\n```\n\n### Ultimate Guide\n\n```\nWrite an ultimate guide about [topic] (3,000+ words) targeting [keyword]\n```\n\n## Tips for Success\n\n1. **Match search intent** - Informational queries need guides, not sales pages\n2. **Front-load value** - Put key information early for readers and snippets\n3. **Use data and examples** - Specific beats generic every time\n4. **Write for humans first** - SEO optimization should feel natural\n5. **Include visual elements** - Break up text with images, tables, lists\n6. **Update regularly** - Fresh content signals to search engines\n\n## Reference Materials\n\n- [Title Formulas](./references/title-formulas.md) - Proven headline formulas, power words, CTR patterns\n- [Content Structure Templates](./references/content-structure-templates.md) - Templates for blog posts, comparisons, listicles, how-tos, pillar pages\n\n## Related Skills\n\n- [keyword-research](../../research/keyword-research/) — Find keywords to target\n- [geo-content-optimizer](../geo-content-optimizer/) — Optimize for AI citations\n- [meta-tags-optimizer](../meta-tags-optimizer/) — Create compelling meta tags\n- [on-page-seo-auditor](../../optimize/on-page-seo-auditor/) — Audit SEO elements\n- [content-quality-auditor](../../cross-cutting/content-quality-auditor/) — Full 80-item CORE-EEAT audit\n\n", "source_url": "https://clawhub.ai/aaron-he-zhu/seo-content-writer", "repository_url": "https://github.com/aaron-he-zhu/seo-content-writer", "categories": [], "tags": [], "status": "approved", "featured": 0, "review_note": null, "approved_at": null, "approved_by": null, "created_at": "2026-02-08T14:03:48.864Z", "updated_at": "2026-03-04T16:04:54.124Z", "stars_total": 11, "stars_clawhub": 11, "stars_ours": 0, "downloads": 4853, "installs_current": 14, "installs_all_time": 14, "author": { "citizen_id": null, "handle": "aaron-he-zhu", "display_name": "aaron-he-zhu", "tier": null, "trust": null, "reputation": null } }, { "id": "019ecb4c-c7fc-411f-8a80-ad820fc930d9", "owner_account_id": "b9a8f519-797e-4320-bb85-6834738d6676", "slug": "skill-security-auditor", "name": "Skill Security Auditor", "summary": "Command-line security analyzer for ClawHub skills. Run analyze-skill.sh to scan SKILL.md files for malicious patterns, credential leaks, and C2 infrastructure before installation. Includes threat intelligence database with 20+ detection patterns.", "content_md": "---\nname: skill-security-auditor\ndescription: Command-line security analyzer for ClawHub skills. Run analyze-skill.sh to scan SKILL.md files for malicious patterns, credential leaks, and C2 infrastructure before installation. Includes threat intelligence database with 20+ detection patterns.\nemoji: 🔍🛡️\nmetadata:\n openclaw:\n requires:\n bins: [\"curl\", \"jq\", \"grep\", \"bash\"]\n version: \"1.0.0\"\n author: \"akm626\"\n category: \"security\"\n tags: [\"security\", \"audit\", \"malware-detection\", \"skill-vetting\", \"cli-tool\"]\n---\n\n# Skill Security Auditor\n\n## Description\n\nThe Skill Security Auditor is a **command-line tool** that performs pattern-based security analysis of ClawHub skills before installation. Given the recent discovery of 341+ malicious skills (ClawHavoc campaign) that distributed Atomic Stealer (AMOS) and stole cryptocurrency credentials, this tool provides essential pre-installation threat detection.\n\n**What this skill provides:**\n- ✅ Bash script (`analyze-skill.sh`) for local security analysis\n- ✅ Threat intelligence database (`patterns/malicious-patterns.json`)\n- ✅ Pattern matching against 20+ known malicious indicators\n- ✅ Risk scoring system (0-100 scale)\n- ✅ Detailed audit reports with recommendations\n\n**How to use it:**\n1. Install this skill from ClawHub\n2. Run the `analyze-skill.sh` script against any skill (by slug or local file)\n3. Review the risk assessment and findings\n4. Make informed decision about installation\n\n**Use this tool when:**\n- About to install a new skill from ClawHub\n- Investigating suspicious skill behavior \n- Performing security due diligence on community skills\n- Auditing your currently installed skills\n\n**This tool does NOT:**\n- ❌ Automatically scan skills (you run it manually)\n- ❌ Block installations (it's advisory only)\n- ❌ Access VirusTotal API (use ClawHub's web interface for that)\n- ❌ Guarantee 100% detection (defense in depth recommended)\n\n## Core Capabilities\n\n### 1. **Malicious Pattern Detection**\nScans for known malicious patterns from the ClawHavoc campaign:\n- Fake prerequisite installations (openclaw-agent.zip, openclaw-setup.exe)\n- Suspicious download commands in SKILL.md\n- Hidden payload execution in metadata\n- Social engineering language patterns\n- Unauthorized external binary downloads\n\n### 2. **Credential Leak Analysis**\nIdentifies potential credential exposure vectors:\n- Hardcoded API keys, tokens, passwords in SKILL.md\n- Suspicious environment variable exfiltration\n- Unencrypted sensitive data transmission\n- Overly broad permission requests\n- Credential harvesting patterns\n\n### 3. **Dependency Chain Validation**\nAnalyzes skill dependencies for:\n- Unverified binary requirements\n- Suspicious GitHub repository sources\n- External script execution\n- Network connections to unknown hosts\n- Nested dependency exploitation\n\n### 4. **C2 Infrastructure Detection**\nChecks for Command & Control indicators:\n- Known malicious IP addresses (e.g., 91.92.242.30 from ClawHavoc)\n- Suspicious domain patterns\n- Encoded communication endpoints\n- Data exfiltration channels\n- Beaconing behavior patterns\n\n### 5. **SKILL.md Structure Validation**\nVerifies skill integrity:\n- Proper YAML frontmatter structure\n- Metadata consistency\n- Description clarity vs actual behavior\n- Permission justification\n- Author verification (GitHub account age)\n\n## Security Scoring System\n\nEach analyzed skill receives a **Risk Score (0-100)**:\n\n- **0-20**: ✅ **SAFE** - No significant security concerns\n- **21-40**: ⚠️ **LOW RISK** - Minor concerns, proceed with caution\n- **41-60**: 🟡 **MEDIUM RISK** - Multiple red flags, manual review recommended\n- **61-80**: 🔴 **HIGH RISK** - Serious concerns, do NOT install without expert review\n- **81-100**: ☠️ **CRITICAL** - Malicious indicators detected, AVOID installation\n\n## Usage Instructions\n\nThis skill provides a **bash script** (`analyze-skill.sh`) that performs pattern-based security analysis of ClawHub skills. The analysis runs locally using the included threat intelligence database.\n\n### Installation & Setup\n\n```bash\n# Install the skill from ClawHub\nnpx clawhub install skill-security-auditor\n\n# Make the analyzer executable\nchmod +x ~/.openclaw/skills/skill-security-auditor/analyze-skill.sh\n\n# Optional: Create alias for convenience\necho 'alias audit-skill=\"~/.openclaw/skills/skill-security-auditor/analyze-skill.sh\"' >> ~/.bashrc\nsource ~/.bashrc\n```\n\n### Audit a Skill Before Installing\n\n**Method 1: Analyze by slug (automatic fetch from ClawHub)**\n\n```bash\n~/.openclaw/skills/skill-security-auditor/analyze-skill.sh --slug bitcoin-tracker\n\n# Example output:\n# ============================================\n# SECURITY AUDIT REPORT\n# ============================================\n# \n# Risk Score: 85/100 - ☠️ CRITICAL\n# ...\n```\n\n**Method 2: Analyze local file**\n\n```bash\n# Download skill first\ncurl -s \"https://clawhub.ai/api/skills/bitcoin-tracker/latest\" > /tmp/skill.md\n\n# Then analyze\n~/.openclaw/skills/skill-security-auditor/analyze-skill.sh --file /tmp/skill.md\n```\n\n### Audit All Installed Skills\n\n```bash\n# Scan all skills in your workspace\nfor skill in ~/.openclaw/skills/*/SKILL.md; do\n echo \"Checking: $(basename $(dirname $skill))\"\n ~/.openclaw/skills/skill-security-auditor/analyze-skill.sh -f \"$skill\"\ndone\n```\n\n### Quick Manual Security Check\n\n```bash\n# Fast grep-based pattern matching (no full analysis)\ngrep -iE \"(prerequisite.*download|91\\.92\\.242\\.30|curl.*\\|.*bash)\" SKILL.md\n```\n\n## Detection Heuristics\n\n### 🚨 CRITICAL Red Flags (Auto-fail)\n\n1. **Fake Prerequisites Section**\n - Matches: \"Prerequisites\", \"Setup Required\", \"Installation Steps\"\n - Contains: Download links to `.zip`, `.exe`, `.dmg` files\n - Example: \"Download openclaw-agent.zip from https://...\"\n\n2. **Known Malicious Infrastructure**\n - IP: `91.92.242.30` (ClawHavoc C2)\n - Domains: Newly registered or suspicious TLDs\n - Encoded URLs or base64 obfuscation\n\n3. **Credential Harvesting**\n - Regex patterns for API keys: `(api[_-]?key|token|password)\\s*[:=]\\s*['\\\"][^'\\\"]+['\\\"]`\n - SSH key access requests\n - Wallet private key patterns\n\n4. **Unauthorized Code Execution**\n - `curl | bash` or `wget | sh` patterns\n - Hidden base64 encoded commands\n - Dynamic eval() or exec() on external input\n\n### ⚠️ Warning Indicators (Score increase)\n\n1. **Suspicious Dependencies**\n - Binary requirements without clear justification\n - Dependencies from unverified sources\n - Excessive permission requests\n\n2. **Obfuscation Techniques**\n - Heavily encoded strings in metadata\n - Minified or obfuscated JavaScript/Python\n - Redirect chains in URLs\n\n3. **Social Engineering Language**\n - Urgency phrases: \"Install immediately\", \"Limited time\"\n - Authority claims: \"Official OpenClaw\", \"Verified by Anthropic\"\n - Fear tactics: \"Your system is at risk without this\"\n\n### ✅ Positive Security Indicators\n\n1. **Verified Author**\n - GitHub account > 1 year old\n - Multiple well-rated skills\n - Active community engagement\n\n2. **Transparent Dependencies**\n - Clear binary requirements with official sources\n - Open-source tool dependencies\n - Well-documented permission needs\n\n3. **Code Quality**\n - Clean, readable SKILL.md\n - Proper error handling\n - No unnecessary network calls\n\n## Audit Report Format\n\n```markdown\n## Security Audit Report\n**Skill**: {skill-name}\n**Author**: {author}\n**Version**: {version}\n**Audit Date**: {date}\n\n### Risk Score: {score}/100 - {RISK_LEVEL}\n\n### Critical Findings:\n- {finding 1}\n- {finding 2}\n\n### Warning Indicators:\n- {warning 1}\n- {warning 2}\n\n### Positive Indicators:\n- {positive 1}\n- {positive 2}\n\n### Recommendations:\n{INSTALL | DO NOT INSTALL | REVIEW MANUALLY}\n\n### Detailed Analysis:\n{Deep dive into specific concerns}\n\n### VirusTotal Link:\n{If available from ClawHub}\n```\n\n## Integration with VirusTotal\n\n**Important**: This skill does NOT directly access VirusTotal's API. Instead, VirusTotal integration is available through ClawHub's web interface via their partnership with VirusTotal.\n\nTo check VirusTotal results for a skill:\n\n1. Visit the skill's ClawHub page: `https://clawhub.ai/skills/{skill-slug}`\n2. Look for the VirusTotal scan results on the skill's page\n3. ClawHub automatically scans published skills via their VirusTotal partnership\n\n**This analyzer focuses on pattern-based threat detection.** It complements (but does not replace) ClawHub's VirusTotal scanning.\n\n### Recommended Security Workflow\n\n1. **Run this analyzer first** - Pattern-based detection (local, instant)\n2. **Check ClawHub's VirusTotal results** - Binary/file reputation (if available)\n3. **Manual code review** - Final verification for critical use cases\n\n```bash\n# Step 1: Pattern analysis (local)\n~/.openclaw/skills/skill-security-auditor/analyze-skill.sh -s suspicious-skill\n\n# Step 2: Visit ClawHub page for VirusTotal results\n# https://clawhub.ai/skills/suspicious-skill\n\n# Step 3: Manual review if needed\ncurl -s \"https://clawhub.ai/api/skills/suspicious-skill/latest\" > skill.md\nless skill.md\n```\n\n## Example Workflow\n\n**Scenario**: User wants to install a skill called `solana-wallet-tracker`\n\n**Step 1: Run Security Analysis**\n```bash\n$ ~/.openclaw/skills/skill-security-auditor/analyze-skill.sh -s solana-wallet-tracker\n\nFetching skill 'solana-wallet-tracker' from ClawHub...\n✓ Skill fetched successfully\n\nAnalyzing skill content...\n\n============================================\n SECURITY AUDIT REPORT\n============================================\n\nRisk Score: 95/100 - ☠️ CRITICAL\n\n============================================\n\n☠️ CRITICAL FINDINGS:\n CLAW-001: Fake Prerequisites - ClawHavoc Campaign [+50 points]\n └─ Matches the ClawHavoc campaign pattern of fake prerequisites requesting malicious binary downloads\n CLAW-002: Known C2 Infrastructure [+50 points]\n └─ IP address used in ClawHavoc campaign for C2 communications\n\n============================================\nRECOMMENDATION:\nDO NOT INSTALL. Malicious patterns detected matching known attack campaigns.\n============================================\n```\n\n**Step 2: Decision**\n- ☠️ **CRITICAL Risk** → **DO NOT INSTALL**\n- Report skill to ClawHub moderators\n- Look for safe alternatives\n\n**Step 3: Verify on ClawHub** (optional)\n```bash\n# Visit skill page to check VirusTotal results\nopen \"https://clawhub.ai/skills/solana-wallet-tracker\"\n```\n\n## Advanced Features\n\n### 1. Behavioral Analysis (Future Enhancement)\n- Sandbox execution monitoring\n- Network traffic analysis\n- File system access patterns\n\n### 2. Community Threat Intelligence\n- Share malicious skill signatures\n- Collaborative IOC database\n- Reputation scoring system\n\n### 3. Continuous Monitoring\n- Auto-audit skills on updates\n- Alert on new security advisories\n- Periodic re-scanning of installed skills\n\n## False Positive Mitigation\n\nTo minimize false positives:\n\n1. **Contextual Analysis**: Binary requirements for legitimate tools (e.g., `gh` for GitHub CLI) are validated against known safe sources\n2. **Whitelisting**: Verified authors and established skills get trust bonuses\n3. **Human Review Option**: Always provide detailed reasoning for security decisions\n4. **Appeal Process**: Users can report false positives for skill reputation adjustment\n\n## Compliance & Ethics\n\nThis skill:\n- ✅ Analyzes publicly available skill metadata\n- ✅ Protects user security and privacy\n- ✅ Promotes responsible skill development\n- ❌ Does NOT perform unauthorized access\n- ❌ Does NOT guarantee 100% security (nothing does)\n- ❌ Does NOT replace user judgment\n\n## Response Templates\n\n### Safe Skill\n```\n✅ Security Audit Complete\n\n{skill-name} has been analyzed and appears SAFE to install.\n\nRisk Score: {score}/100 (LOW)\n\nNo malicious patterns detected. The skill:\n- Uses standard dependencies from trusted sources\n- Has a verified author with {X} published skills\n- Contains clear documentation with no obfuscation\n- Requests appropriate permissions for its function\n\nVirusTotal: {link}\n\nRecommendation: Safe to proceed with installation.\n```\n\n### Suspicious Skill\n```\n🔴 Security Alert: HIGH RISK DETECTED\n\n{skill-name} has been flagged with CRITICAL security concerns.\n\nRisk Score: {score}/100 (HIGH)\n\n⚠️ Critical Findings:\n{detailed findings}\n\nThis skill matches patterns from the ClawHavoc malware campaign.\n\nRecommendation: DO NOT INSTALL. Consider reporting this skill to ClawHub moderators.\n\nAlternative safe skills: {suggestions}\n```\n\n## Technical Implementation Notes\n\n**Pattern Database Location**: `~/.openclaw/security-auditor/patterns/`\n- `malicious-patterns.json`: Known bad indicators\n- `safe-patterns.json`: Whitelisted elements\n- `ioc-database.json`: Indicators of Compromise\n\n**Update Mechanism**:\n```bash\n# Pull latest threat intelligence\ncurl -s \"https://openclaw-security.github.io/threat-intel/latest.json\" \\\n > ~/.openclaw/security-auditor/patterns/ioc-database.json\n```\n\n## Contributing\n\nFound a new malicious pattern? Submit IOCs to the OpenClaw Security Working Group:\n- GitHub: github.com/openclaw/security-auditor\n- Report Format: JSON with pattern regex, description, severity\n\n## Limitations\n\n⚠️ **Important Disclaimers**:\n- This tool provides analysis, not guarantees\n- Sophisticated malware may evade detection\n- Always combine with VirusTotal + manual review for critical applications\n- Security is a shared responsibility\n- No automated tool replaces security expertise\n\n## References\n\n- ClawHavoc Campaign Analysis: [The Hacker News, Feb 2026]\n- OpenClaw Security Partnership: VirusTotal Integration\n- Malicious Skill Database: OpenSourceMalware Research\n- ClawHub Moderation Guide: docs.openclaw.ai/security\n\n---\n\n**Remember**: The best security is defense in depth. Use this skill as ONE layer of your security strategy, not the only layer.\n\nStay safe, stay skeptical, stay secure. 🦞🛡️\n", "source_url": "https://clawhub.ai/akhmittra/skill-security-auditor", "repository_url": "https://github.com/akhmittra/skill-security-auditor", "categories": [], "tags": [], "status": "approved", "featured": 0, "review_note": null, "approved_at": null, "approved_by": null, "created_at": "2026-02-08T07:37:24.483Z", "updated_at": "2026-02-25T23:30:35.899Z", "stars_total": 1, "stars_clawhub": 1, "stars_ours": 0, "downloads": 2068, "installs_current": 18, "installs_all_time": 19, "author": { "citizen_id": null, "handle": "akhmittra", "display_name": "akhmittra", "tier": null, "trust": null, "reputation": null } } ], "starred_skills": [] }

Trusted Skill Hub

⭐ Your Starred Skills

🔥 Popular Skills

📦 All Skills