Shared library of reusable Claude Code skills and agents.
Work in any project, no configuration needed.
| Skill | Description |
|---|---|
| babysit | Superseded by shepard. Watch a PR's CI, auto-fix failures, push until green |
| build-it | Implement the last grill-me alignment: cut a worktree, write plan docs if chosen, build, run gates, open the PR |
| catchup | Load branch context, show progress, sync with base branch |
| commit | Small, focused commits with conventional messages + push |
| fix-bug | End-to-end bug-fix workflow: reproduce, diagnose, fix, verify via bug-fix-verifier, with a visual-risk gate before /pr |
| grill-me | Interview the developer through AskUserQuestion before any code is written; ends with docs-or-not and build-or-stop |
| implement-plan | Execute a feature plan end-to-end without TASKS.md; gated by /review-branch (both reviewers ≥ 7) |
| memory-hygiene | Audit the project memory store for stale, codified, duplicate entries; dry-run proposal, then sync worktree memory stores |
| newbranch | Create a new branch from the default branch |
| next | Continue through TASKS.md — find next task, execute, mark done |
| plan-feature | Interrogate the developer, verify citations, gate the Security & Cost Surface, then produce PLAN.md + DECISIONS.md reviewed by plan-reviewer + surface-reviewer |
| pr | Create a pull request for the current branch; gates on REVIEW_CLAUDE.md for plan branches and on BUG.md's verdict for bug branches |
| research | Research a topic, produce a filed report, build cumulative knowledge |
| retro | Write retrospectives capturing what went wrong, why, and what changed |
| review-branch | Two-agent review of the branch vs base: runtime-integrity-reviewer + precedent-reviewer in parallel, synthesized into REVIEW_CLAUDE.md |
| review-mcp-descriptions | Improve MCP tool/resource descriptions for discoverability |
| shepard | Drive one PR to green and answered: fix red CI, dispose every review finding, push once per cycle, arm a live watch |
| sync-worktrees | Copy gitignored .env* files and refresh dependencies from the primary worktree into every secondary worktree; optional safe fast-forward |
| task-writer | Break down features into phased TASKS.md with verification and a self-administered coverage checklist |
| wireframe | Generate structured WIREFRAMES.md with ASCII layouts, design tokens, and interaction specs; self-gated by wireframe-reviewer |
| worktree | Cut a fresh git worktree: branch, deps, env files, per-repo house rules, then hand back the path |
Generic across any project on a given stack, but assume that stack is in use.
| Skill | Stack | Description |
|---|---|---|
| nightwatch-mcp | Nightwatch MCP | Error and performance monitoring, exception triage |
| release-cli | Go + GoReleaser | Tag and release a Go CLI via GoReleaser on tag push |
| startup | Laravel + Vue + MinIO | Full project setup: Docker services, .env files, then parallel backend/frontend/MCP setup, with worktree support |
For any project using Kendo for issue tracking. Requires the Kendo CLI or MCP server.
| Skill | Description |
|---|---|
| board-sync | Sync kendo board with GitHub branch/PR status |
| kendo-cli | Kendo CLI for issues, sprints, epics, time tracking |
| kendo-mcp | Kendo MCP server integration for issue management |
| lint-issues | Audit every To Do / In Progress issue against the issue-writing standard via parallel issue-linter agents; post a summary on an audit issue |
| prepare-issue | Prepare a kendo issue: assign, branch, link, move to In Progress |
| triage-reports | Walk pending Kendo reports one-by-one; promote, combine, park, or dismiss with a logged reason |
| Agent | Description |
|---|---|
| agent-auditor | Audit agent definitions for quality and consistency |
| bug-fix-verifier | Verify a bug fix actually resolves BUG.md's defect; gates /fix-bug before PR |
| docs-auditor | Audit CLAUDE.md and docs against codebase for drift |
| librarian | Scan other repos for shareable skills/agents, grade and recommend imports |
| precedent-reviewer | Review a branch against written standards, sibling implementations, and its own plan prose; PR-time pair with runtime-integrity-reviewer |
| qa | Diagnose CI failures or evaluate implementations against acceptance criteria |
| reviewer | Review PRs for code quality, architecture, and pattern consistency |
| runtime-integrity-reviewer | Review a branch for transaction, concurrency, lifecycle, scaling, and silent-failure defects; PR-time pair with precedent-reviewer |
| surface-reviewer | Audit a plan's Security & Cost Surface section against six question-shaped rows; plan-time, runs beside plan-reviewer |
| wireframe-reviewer | Verify WIREFRAMES.md completeness, token validity, and plan coverage |
| Agent | Stack | Description |
|---|---|---|
| issue-linter | Kendo MCP | Grade one issue against kendo-mcp's issue-templates.md; post suggested rewrites on the audit issue, never edit the target |
| plan-reviewer | Laravel + Vue | Review feature plans for codebase convention violations against arch tests and CLAUDE.md |
Maintenance happens from the private mission-control repo, which adds this repo and the consumer repos as submodules under repos/. From there, the librarian agent walks repos/*/ looking for new skills and agents worth promoting into this catalog:
> Check my repos for new skills
It grades each candidate on quality and genericness, and recommends what to import.
See docs/contributing.md for how to add new skills and agents.
Use the templates in templates/ as a starting point:
templates/skill-template/— skeleton for a new skilltemplates/agent-template.md— skeleton for a new agent