CommunityArt & Designgithub.com

haystackeditor/risk-brief

A pre-submit Claude Code / Codex skill that turns your agent's design decisions into a PR description — and self-audits the diff for risks you missed.

Works withClaude CodeCodex CLI~Cursor
npx skills add haystackeditor/risk-brief

Ask in your favorite AI

Open a new chat with this agent skill pre-loaded.

Documentation

haystackeditor/risk-brief

A pre-submit Claude Code / Codex skill that turns your agent's design decisions into a PR description — and self-audits the diff for risks you missed.

Related Skills

bettyguo/diagram-skills

Generate validated diagrams across Mermaid, PlantUML, Graphviz, D2, and Excalidraw. MCP server, CLI, and Claude Code skills bundle.

community

cosci7/ava-diy-companion

DIY AI Companion inspired by Razer Project AVA. 3D hologram-style avatar, voice interaction, long-term memory, agentic tools, personality that evolves. Built with Python, LangGraph/LangChain, local or cloud LLMs (Ollama/Groq/xAI), Gradio UI, Whisper STT, ElevenLabs or local TTS. Includes DIY Pepper's Ghost hologram guide.

community

Caiyujie007/Codex_Skills

Codex_Skills developped when do ASIC design using vibe coding

community

zhitongblog/doaipm-skill

doaipm — DO AI PM. The method as a portable AI skill. Speak it, and AI builds it. doaipm.com

community

Veronica0206/vera-clinical-indication-researching

Open-source Claude Code skill for clinical indication research: MoA landscape, compound landscape, endpoint framework, study designs. Outputs structured Word/PDF dossiers.

community

doany-ai/ai-music

Generate AI music on RunComfy via the `runcomfy` CLI — a smart router across the music-model catalog. Routes to ElevenLabs AI Music Generation (premium 44.1 kHz stereo vocal tracks, 5 s–5 min, $0.0083/s) and ACE Step / ACE Step 1.5 (StepFun-AI open-weights, tag-driven composition, multilingual lyrics, $0.0002–0.0003/s, ~27× cheaper), plus ACE Step audio-inpaint (regenerate a time range inside an existing track) and ACE Step audio-outpaint (extend a track before or after). Picks the right model for the user's actual intent — premium vocal hook, cheap background music library, multilingual pop song, repair a bad chorus, lengthen a 30 s draft into a 2 min cut — and ships each model's documented prompting patterns plus the minimal `runcomfy run` invoke. Triggers on "generate music", "make a song", "AI music", "background music", "instrumental track", "soundtrack", "jingle", "theme music", "royalty-free music", "compose", "music with lyrics", "extend music", "fix this song", "inpaint music", or any explicit ask to

community