wiggum
Start an autonomous implementation loop from a spec or PRD. Enters plan mode for user approval, enforces command gates (test/lint/typecheck/build), validates dependencies, commits incrementally, and maintains documentation and changelog. Production-ready quality gates.
npx skills add majiayu000/claude-skill-registry --skill wiggum-zbruhnke-claude-code-starter-2 --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
The skill starts an autonomous implementation loop from a provided spec or PRD. It enters a planning phase for user approval, enforces command gates (test/lint/typecheck/build), validates dependencies, commits incrementally, and maintains documentation and a changelog. It requires production-ready quality gates.
How it works
- When invoked, it enters a multi-step cycle: PLAN, PARSE requirements, CHUNK implementation pieces, BUILD code, DECIDE on ADRs, TEST to ensure coverage, REVIEW for quality, SIMPLIFY code, DOCUMENT updates, and COMMIT after each chunk.
- It uses a sequence of tasks and specialized agents (e.g., EnterPlanMode, Task with adr-writer, test-writer, code-reviewer, code-simplifier, documentation-writer) to perform distinct activities.
- It enforces automatic validation via a mandatory script (wiggum-validate.sh) that checks commits, CHANGELOG entries, and gate outcomes (TEST, LINT, BUILD).
- It requires documentation updates and an atomic commit per completed chunk, with subsequent verification loops until all gates pass.
When to use it
- Use when you have a spec or PRD and want an automated, staged implementation loop with user approval before code is written.
- Use to ensure continuous documentation and changelog maintenance alongside code changes.
What it can touch
- Commands and checks are driven by CLAUDE.md-defined gates: TEST, LINT, TYPECHECK, BUILD, FORMAT. The plan and execution flow relies on tools (Read, Grep, Glob, Edit, Write, Bash, Task).
- It relies on git for commits and on a pre-commit hook to enforce the wiggum session rules.
Caveats
- Requires the user to provide a spec/PRD and success criteria to proceed.
- Validation is mandatory and must pass before declaring completion; otherwise, the loop continues or stops with a plan for fixes.
- All changes are committed incrementally; stubs or TODOs are disallowed by the process.
# Wiggum Loop - Autonomous Implementation You are initiating a **Wiggum Loop** - an autonomous implementation cycle (inspired by the Ralph Wiggum technique) that plans first, then iterates until the spec is fully complete with all quality gates passed. **Your motto**: "Iteration beats perfection. Keep going until it's truly done." ## Core Philosophy 1. **Plan before implementing**: Enter plan mode first, get user approval before writing code. 2. **Iterate until complete**: Each cycle builds on the previous. Read your own git commits, see what changed, fix what's broken. 3. **Quality over speed**: Better to take 10 iterations and ship solid code than 2 iterations of broken code. 4. **No stubs, ever**: If you write `// TODO` or stub out a function, you're not done. Implement it fully. 5. **Document as you go**: Documentation and changelog entries are part of the work, not afterthoughts. 6. **Commit incrementally**: Each completed chunk gets its own atomic commit with a meaningful message. 7. **Trace every path**: Follow every code path to ensure completeness. Don't assume - verify. ## Input Handling You MUST receive a clear specification. If not provided: 1. Ask: "What would you like
- Core Philosophy
- Input Handling
- Quick Start
- The Wiggum Loop Process
- Mandatory Validation (ENFORCED)
- Stop Conditions (Prevent Runaway)
- Phase 0: Plan First (Command Discovery)
- Command Discovery (Required)
- Phase 1: Parse the Spec
- Phase 2: Plan the Implementation
- Phase 3: Build (The Loop)
- Invoking Specialized Agents
- Incremental Git Commits
- Phase 4: Update Changelog
cp .claude/hooks/wiggum-precommit.sh .git/hooks/pre-commit && chmod +x .git/hooks/pre-commit git rev-parse HEAD Stage chunk files git add src/feature.ts src/feature.test.ts Commit with descriptive message git commit -m "feat(feature): add user authentication
What does the wiggum skill do?
Start an autonomous implementation loop from a spec or PRD. Enters plan mode for user approval, enforces command gates (test/lint/typecheck/build), validates dependencies, commits incrementally, and maintains documentation and changelog. Production-ready quality gates.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill wiggum-zbruhnke-claude-code-starter-2 --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.