Evidence-based fitness coaching from workout/health screenshots and user context. Use for training plans, nutrition guidance, sleep/recovery optimization, tr...
{ "image_analysis": { "meta": { "file_name": "image_ef3de2.jpg", "file_type": "uploaded file", "analyst_persona": "Technical Photo Analyst" }, "scene_environment": {
Play the LIE.WATCH AI social deduction game - survive through trust, deception, and strategic betrayal
Analyze music/audio files locally without external APIs. Extract tempo, pocket/groove feel, pulse stability, swing proxy, section/repetition structure, key c...
Plan place search, geocoding, routing, and map-link workflows across Google Maps, Apple Maps, OpenStreetMap, and other providers.
Text-to-speech conversion using `uvx edge-tts` for generating audio from text. Use when: (1) User requests audio/voice output with the "tts" trigger or keyword. (2) Content needs to be spoken rath
--- name: study-habits description: Build effective study habits with spaced repetition, active recall, and session tracking author: clawd-team version: 1.0.0 triggers: - "study session" - "study
Windows 桌面 RPA 自动化控制。使用场景： (1) 操作桌面应用程序（非 Web 应用） (2) 模拟鼠标键盘操作 (3) 截图和图像识别 (4) 窗口管理和应用启动 (5) 剪贴
--- name: nexus-a2a description: Connect to the Nexus A2A Relevance network to exchange knowledge with other AI agents version: 2.0.0 tools: - web-fetch - http-request --- # Nexus A2A — Agent K
太郎（kairyuu.net）とのエージェント間知識交換スキル。太郎の交換エンドポイントを通じて知識の提案・取引を行う。知識交換、エージェント間通信
Fetches English Wikipedia's "Did you know?" (DYK) facts, caches them locally, and serves them one at a time. No API key required. Does not edit Wikipedia.
Security audit framework for AI agent skills, MCP servers, and packages. Your LLM does the analysis — we provide structure, prompts, and a shared trust database.
Multi-model peer review layer using local LLMs via Ollama to catch errors in cloud model output. Fan-out critiques to 2-3 local models, aggregate flags, synthesize consensus. Use when: validating tra
Analyze ChatGPT conversation exports to discover cognitive archetypes and optimize AI-human communication patterns. Enables personalized agent interactions based on detected user profiles.
Help an OpenClaw agent understand the Legiit marketplace from a buyer perspective and guide people through buying services with practical, step-by-step actio...
Bulletproof AI code verification. The agent IS the engine — no external tools required. Spawns parallel verification workers that slop-scan, type-check, muta...
Complete AI talent discovery and outreach workflow using BrightData MCP or Python scraping. This skill should be used when users need to find PhD students, r...
Detect mispriced correlations between Polymarket prediction markets. Cross-market arbitrage finder for AI agents.
半自动回复微信联系人消息（置信度>85%自动发送，否则确认），或主动发送指定内容。使用方式：wechat-auto-reply "联系人名称" 或 wechat-auto-reply "联系人
Enrich leads by finding verified emails via contact pages, Instagram, Hunter.io, and patterns, then format data for Notion with deduplication and batching.
If you can imagine it, CellCog can film it. Grand widescreen cinematics with consistent characters — what previously required million-dollar production budgets, now generated from a single prompt. S
Structured decision-making patterns for common engineering choices — library selection, architecture, build vs buy, prioritization, reversibility analysis, and ADRs. Use when choosing between tools,
Constrained autonomous delegate for identity-proxied communication. Handles incoming messages (Email, Discord, Slack, WhatsApp) by analyzing intent and applying declarative authority policies before g
Manage, consult on, and optimize OKRs (Objectives and Key Results). Use when helping set, track, review, score, or improve OKRs. Covers OKR philosophy, commo...