发现优质的 AI Agent 技能
聚合 Claude Skills、LangChain、AutoGPT 等优质资源,助力开发者快速构建智能应用
HokiPoki Skill
Route tasks to different AI CLIs (Claude, Codex, Gemini) via the HokiPoki P2P network. API keys never leave the provider's machine; only encrypted requests and results are exchanged.
Startup Info — Portable Prompt
> Universal system prompt for any LLM with web search capability. > Works with: ChatGPT (Custom GPTs), Gemini, Claude, Cursor, Windsurf, LangChain agents, etc. > Requires: web search tool access (built-in browsing, Tavily, SerpAPI, or equivalent).
AI Discoverability Query Bank
Ready-to-use queries organised by category. Copy/paste into ChatGPT, Perplexity, Claude, and Gemini.
BKMRK — Bookmark Intelligence
You are connected to the user's BKMRK library. BKMRK analyzes bookmarks with Claude AI against the user's coding projects, scoring relevance and generating implementation suggestions.
Agent Usage Patterns
This document describes how AI coding agents (Claude Code, OpenCode, etc.) can execute PRDs autonomously. **This skill only edits PRDs — agents use this reference to execute them.**
Bridle Skill
Unified configuration manager for AI coding assistants. Manage profiles, install skills/agents/commands, and switch configurations across Claude Code, OpenCode, Goose, and Amp.
copilot-cli
Execute GitHub Copilot CLI via exec for code gen, file edits, shell tasks using advanced models (Claude/GPT-5). Use when needing Copilot-powered coding/automation.
Design Style: Humanist Literary (The "Claude" Aesthetic)
来自 openclaw/skills 技能
Boardroom model: OpenRouter + Claude Opus 4.6
The board of advisors (four personas) should run on a stronger model so their arguments and rebuttals are higher quality. Recommended: **Claude Opus 4.6 via OpenRouter**.
AEO (Answer Engine Optimization) System
> Get AI assistants — ChatGPT, Perplexity, Claude, Gemini — to recommend your brand when people ask purchase-intent questions.
使用特定后端
python .claude/skills/pdf-process/script/pdf_parser.py \ '{"name": "pdf_to_markdown", "arguments": {"file_path": "/path/to/document.pdf", "output_dir": "/path/to/output", "backend": "pipeline"}}' python .claude/skills/pdf-process/script/pdf_parser.py \ '{"name": "pdf_to_markdown", "arguments": {"file_path": "/path/to/document.pdf", "output_dir": "/path/to/output", "start_page": 0, "end_page": 5}}' ```