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
Relay To Agent
Send messages to AI agents on any OpenAI-compatible endpoint. Works with Connect Chat, OpenRouter, LiteLLM, vLLM, Ollama, and any service implementing the Chat Completions API.
Integrate OpenAI Agents SDK with You.com MCP
Interactive workflow to set up OpenAI Agents SDK with You.com's MCP server.
Lyrics Transcription Skill
Transcribe audio files to timestamped lyrics (LRC/SRT/JSON) via OpenAI Whisper or ElevenLabs Scribe API.
OpenAirtime Agent 📦
> [!CAUTION] > **STRICT RULES:** > 1. All credentials are already configured. Never ask for API keys. > 2. You are on **FARCASTER**, not Twitter. > 3. Use the `node c:\Users\LOYAL\Documents\openairtime\scripts\farcaster.js` commands below. Do NOT use curl.
telegram-voice-transcribe
Transcribe Telegram voice notes into text via OpenAI Whisper (`whisper-1`).
voice-transcribe
transcribe audio files using openai's gpt-4o-mini-transcribe model.
MS-Qwen-VL Skill
基于 ModelScope Qwen3-VL 系列模型的多模态视觉识别技能，使用 OpenAI SDK 兼容方式调用。
Tuna — Deploy and Serve LLM Models on GPU Infrastructure
Tuna is a hybrid GPU inference orchestrator. It lets you deploy, serve, and manage LLM models (Llama, Qwen, Mistral, DeepSeek, Gemma, and any HuggingFace model) on serverless GPUs from **Modal, RunPod, Cerebrium, Google Cloud Run, Baseten, or Azure Container Apps**, with optional **spot instance fallback on AWS** via SkyPilot. Every deployment gets an **OpenAI-compatible `/v1/chat/completions` endpoint**.
OpenAI Codex docs summary (from developers.openai.com/codex)
Reviewed pages: - https://developers.openai.com/codex - https://developers.openai.com/codex/cli - https://developers.openai.com/codex/quickstart
OpenAI Codex Operator
Use this skill to reliably call Codex CLI from OpenClaw.
GUI Agent 最新动态：从 Claude Computer Use 到 OpenAI Operator
> 最近 GUI Agent 领域动作不断，从 Anthropic 的 Computer Use 到 OpenAI 的 Operator，再到国内各大厂商的跟进，这个赛道正在快速升温。这篇文章整理了 2025 年以来 GUI Agent 的最新进展。