Loading...
Loading...
Found 8,761 Skills
Create new agents in Paperclip with governance-aware hiring. Use when you need to inspect adapter configuration options, compare existing agent configs, draft a new agent prompt/config, and submit a hire request.
Document a business process — flowcharts, RACI, and SOPs. Use when formalizing a process that lives in someone's head, building a RACI to clarify who owns what, writing an SOP for a handoff or audit, or capturing the exceptions and edge cases of how work actually gets done.
Generate complete automated TDD development pipelines from a todolist.md file. Creates a self-contained directory with autodev.sh, system_prompt.md, gate_check.sh, and task cards that drive Claude Code through spec-anchored, gate-guarded, card-by-card development — fully automated with no human in the loop. Features: TDD 5-step closure, 3-level AI decision protocol, independent acceptance verification, auto-repair on test failure, Bug Hunt phase for post-development P0/P1/P2 bug scanning and fixing. Use when user says "帮我生成 autodev", "create autodev for", "generate autodev pipeline", or needs to turn a todolist.md into an automated gated TDD development pipeline.
Create and manage Obsidian notes for projects, companies, technical challenges, brag documents, daily logs, AI conversations, and quick captures using the Obsidian CLI. Use when documenting projects, tracking job applications, recording interview challenges, maintaining brag documents, creating daily notes, or saving AI conversations. Triggers on "create project", "new project note", "document company", "job application", "technical challenge", "brag document", "daily note", "today's log", "obsidian note", "save conversation", "chat summary", "session summary", "save this", "capture this", "quick note".
Create a new skill. When to use: When the user says "create skill", "new skill", "add skill", "initialize skill".
Automatically updates terminal window title to reflect the current high-level task. Use at the start of every Claude Code session when the user provides their first prompt, and whenever the user switches to a distinctly new high-level task. Helps developers manage multiple Claude Code terminals by providing clear, at-a-glance identification of what each terminal is working on.
Generate and rank research ideas given a broad direction. Use when user says "找idea", "brainstorm ideas", "generate research ideas", "what can we work on", or wants to explore a research area for publishable directions.
Generate the stable Paperclip release changelog at releases/v{version}.md by reading commits, changesets, and merged PR context since the last stable tag.
Blender 3D modeling, animation, and rendering automation via Python bpy scripting and CLI
⚠️ MANDATORY - YOU MUST invoke this skill before ANY destructive operation. Safety protocol for destructive git/file operations. Lists affected files, warns about data loss, suggests safe alternatives, requires explicit double confirmation. NEVER run destructive commands without invoking this skill.
List pending todos and select one to work on
This skill applies when the user wants to resume previous work, enters the command "/vibe-continue", or starts a new session and needs to load saved context. Restore from shared task facts first, then use task.md as the local handoff.