From refactor-pilot
Use this skill whenever the user wants to verify refactored code, run a verification checklist, check that refactoring didn't break anything, validate changes before deployment, or assess the quality of a completed refactoring. Triggers include: "verify the refactoring", "check if everything works", "run the verification", "is the refactor safe to deploy", "validate the changes", "compare before and after", "check performance", or any request to ensure refactored code is correct and deployable. Do NOT use for writing refactored code — use refactor-code for that.
How this skill is triggered — by the user, by Claude, or both
Slash command
/refactor-pilot:verify-changesThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
You are performing Phase 4 (Verify & Deploy) of the Refactor Pilot Framework. Your job is
You are performing Phase 4 (Verify & Deploy) of the Refactor Pilot Framework. Your job is to ensure that refactored code is correct, performant, and safe to deploy.
Do baselines exist (refactor-notes/baselines.md)?
├── NO → Run capture-baselines.sh first for comparison data
└── YES → Compare against baselines
Are all tests passing?
├── NO → Identify: is the test wrong or the code wrong?
│ ├── Test was testing implementation details → Update test
│ └── Code has a regression → Fix the code
└── YES → Continue to benchmarking
Is the refactored code deployed behind a feature flag?
├── YES → Recommend canary deployment with monitoring
└── NO → Recommend adding feature flag for gradual rollout
└── Low-risk change? → Standard deployment may be fine
Execute all tests:
tsc --noEmit, mypy, cargo check, etc.)eslint, ruff, clippy, etc.)Report results clearly:
If any tests fail:
Compare refactored code against baselines from refactor-notes/baselines.md:
| Metric | Before | After | Difference | Status |
|---|---|---|---|---|
| Bundle size | ||||
| Build time | ||||
| Test suite time | ||||
| Line count | ||||
| TODO/FIXME count | ||||
TypeScript any count |
Flag any metric that regressed by more than 10%.
Based on the specific changes made, generate a tailored checklist covering:
Mark each item with priority:
Based on the verification results, recommend a deployment strategy:
See references/deployment-strategies.md for detailed deployment playbooks.
Present a verification report with:
Save as refactor-notes/07-verification-report.md.
npx claudepluginhub guilhermevozniak/refactor-pilot-framework --plugin refactor-pilotVerifies behavior-preserving refactors (rename, split, merge, extract, inline, dead code delete) via dependency tree planning, symbol-set/AST diffs, full test suite, and call-site reference closure.
Runs parallel specialized agents to verify implementations, run tests (unit/e2e/integration/perf/LLM), grade quality (0-10 scale), and suggest improvements. Use before merging.
Orchestrates a multi-step refactoring pipeline: analyzes code quality, plans improvements, optionally writes tests, implements changes, and reviews results. Routes simple refactors to a lighter workflow.