Loading...
Loading...
Found 9,210 Skills
Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions
Create New Skill - scaffolds a skill definition following Claude Code conventions and this repository's patterns. Use when adding a new skill.
Spec Status - displays pipeline progress dashboard for a single specification showing document statuses, blockers, and next action.
Implement Tasks - executes tasks from the tasks document using subagents. Use when ready to start coding a feature.
Invoke the skill `git:message` to generate a commit message, then create the Git commit non-interactively. Use when you need to commit either the already-staged changes or the full current working tree relative to `HEAD`, while preserving a review-friendly message and footer handling. Trigger for requests such as the skill `git:commit` or the skill `git:commit` with `HEAD`, especially when the user wants safe staging behavior and a clean commit created from the drafted message.
Generate a git-log-review-friendly commit message from repository changes. Use when you need to inspect staged changes, the current working tree relative to `HEAD`, or a commit-to-working-tree range and draft only the commit message text in a conventional-commit-style format, without creating the commit. Trigger for requests such as the skill `git:message`, the skill `git:message` with `staged`, the skill `git:message` with `HEAD`, or the skill `git:message` with `<commit>`, especially when the user wants a squash-ready summary of the most important changes.
Generate or update project memory for AI agents — default to AGENTS.md, support agent-specific targets such as CLAUDE.md, and keep sibling memory files synchronized while capturing stable architecture, conventions, and operational knowledge
Guided codebase understanding — detect project type, map dependencies and external systems, extract core concepts, enumerate API surfaces, and deep-dive into request paths interactively
Survey a project read-only — git working tree, GitHub issues and their declared priority, open PRs, unfiled plans — into a one-screen dashboard that crowns one finish-first next move routed to the kit that does it, saved by default as a throwaway snapshot under docs/status/. Use when you sit down at a project and ask "what should I do next", "check project status", "what's next", "what's most important right now", "orient me", "write me a status file", or run "/statuskit" — add "just print it" or "no file" to skip the snapshot.
Read-only root-cause analysis for a tracker issue. Identifies the bug's location and the minimal change surface so the next agent can implement the fix without re-exploring the repo. Outputs a short summary, the files that need to change, and the proposed approach.
Reference implementation demonstrating the Command → Agent → Skill orchestration pattern in Claude MPM, showing both preloaded-skill and dynamic-skill-invocation styles
The primary driver for every coding, refactoring, debugging, or engineering task -- used for the whole task.