Loading...
Loading...
Found 6,998 Skills
Create GitHub issues using data-driven templates. Supports any issue type via configurable template configs. Use when the user asks to create a GitHub ticket, issue, or support ticket, or when they want to add a new issue template.
Use when writing new functions, adding features, fixing bugs, or refactoring by applying TDD principles - write failing tests before implementation code, make them pass, then refactor.
Guide wanderers to the right animal for their journey. Perch, tilt your head, chatter about the forest, present the options, and warble the recommendation. Use when helping users choose which skill to use, discovering capabilities, or navigating the ecosystem.
Unified code review system — dispatches the right review agents for the situation. Use when reviewing code for quality, bugs, compliance, or before merging.
Run /check-bitcoin, then fix the highest priority Bitcoin issue. Creates one fix per invocation. Invoke again for next issue. Use /log-bitcoin-issues to create issues without fixing.
Use when a session produced reusable insights, when the user says "learn from this", "remember this", or "improve yourself", or after completing a complex task where patterns were discovered
Generate structured task lists from specs or requirements. IMPORTANT: After completing ANY spec via ExitSpecMode, ALWAYS ask the user: "Would you like me to generate a task list for this spec?" Use when user confirms or explicitly requests task generation from a plan/spec/PRD.
A general research briefing template for quickly organizing research questions, distilling facts and uncertainties, and providing suggestions for subsequent experiments/interviews/data extraction.
Refactor code after tests pass. The "Refactor" phase of Red-Green-Refactor.
Commit any uncommitted changes, run lint checks, fix any issues, and push the current branch. Delegates to a haiku sub-agent for speed.
Review the current session for errors, issues, snags, and hard-won knowledge, then update the rules/ files (or AGENTS.md if no suitable rule file exists) with actionable learnings.
Hypothesis-driven autonomous debugging with real command validation