Loading...
Loading...
Found 3,253 Skills
Used when completing tasks, implementing important features, or before merging to verify whether the work results meet the requirements
Use this when you have specifications or requirements for multi-step tasks, before starting to write code
Refactor code with safety nets — tests green before and after, no behavior change
Initialize a full ML research project control root with independent paper, code, and optional slide repositories, shared project memory, root-level agent guidance, code-owned worktree policy, and component handoffs. Use when starting a new research project, setting up a project root for agents, connecting paper/code/slides repos, or replacing a simple paper+code workspace with a lifecycle-aware research project structure.
Use when the user asks to commit changes, organize commits, write commit messages, or split working-tree changes into Conventional Commits. Trigger on phrases like "commit my changes", "커밋해줘", "커밋 분리", "make commits", "/conventional-commit", or whenever the user wants to turn current changes into Conventional Commit-style commits. For commit + push use `conventional-commit-push`; for rewriting non-Conventional commit history use `conventional-commit-rewrite`.
Use when the user asks to review code, review changes, review a commit, review a PR, audit code quality, check for security issues, or generate a code review report. Trigger on phrases like "review my changes", "코드 리뷰", "check my code", "review the last commit", "what do you think of this diff", "compare branches", "code audit" — even if they don't say "code review" explicitly. For persistent file output use `code-review-md` (markdown) or `code-review-html` (markdown + HTML).
Generates a full comprehensive status update of the project. Use when the user asks for a status update, progress report, "STATUS UPDATE", "WHAT'S THE STATUS", or wants to know what's done, what's broken, and what's next. Writes to docs/status/.
Creates or updates TODO_LIST.md by reading all .md files in the project using sub-agents, then verifies which TODOs are already done by checking the actual code. Use when the user wants to build a comprehensive TODO list from existing documentation, verify TODO status against code, or says "build TODO list".
Check test coverage for unstaged changes. Use when user asks to "check coverage", "/coverage", or wants to see which unstaged changes lack test coverage.
Create safe Conventional Commit messages and commits from current working tree changes.
Use when ALL tasks in an epic or branch are closed and you are ready to integrate the entire body of work - never after individual task completions, never mid-epic
Reset the working directory for the next task by ensuring no uncommitted changes exist, then switching to the main branch and pulling latest.