Loading...
Loading...
Found 9,121 Skills
Optimize command outputs with RTK (Rust Token Killer) for 70% token reduction
This skill should be used when the user asks to "ask questions interactively", "use the question tool", "present choices to the user", "avoid yes/no prompts", "use interactive confirmations", or needs guidance on asking structured questions with selectable options instead of free-text prompts.
Fundamental Perforce operations including sync, edit, add, delete, submit, revert, and file state management.
Use when the user wants to create AI music videos (MV)—including generating music from text prompts or using custom lyrics. Triggers: generate MV, music video, make video for this song, lyrics video, create MV, AI music video, music+video, generate video from lyrics.
Conversational briefing on your recent reading — what you finished, what you highlighted, and what you had to say about it
Generate pixel art SVG illustrations for READMEs, docs, or slides. Use when user says "画像素图", "pixel art", "make an SVG illustration", "README hero image", or wants a cute visual.
Apply Sherlock Holmes' deductive method to debug code, diagnose system issues, and solve technical puzzles using systematic elimination and logical reasoning
Turn a PRD into a traceable Memory Bank with product, requirements, epics, and features.
Create a high-quality pull request: branch, focused changes, lint/build, conventional commit, and a clear PR description with validation steps. Use when the user asks to open or prepare a PR.
Frontend-Only UI Proto 프로젝트에 피치 하네스 시스템을 설정합니다. CLAUDE.md를 최소 진입점으로 정리하고, AGENTS.md를 70~90줄 규모로 생성/업데이트합니다. Use when: "ui proto 하네스 설정", "ui proto AGENTS 정리", "Frontend-Only 하네스 설정", "프로토타입 프로젝트 초기 설정" 키워드.
Use when changing CFO Stack ledger conventions, process docs, Beancount metadata rules, or canonical ledger/file layout guidance that should stay out of AGENTS.md.
Turn repeatable outputs of a one-person company into compounding assets. Use when Codex needs to explain asset-compounding concepts when needed, verify prerequisite outputs, ask one question at a time, present multiple assetization priorities, and write user-confirmed outputs into `opc-doc/`.