plugins/pokayokay/skills/verification-before-completion/SKILL.md
Use before claiming work is done, fixed, passing, ready to commit, ready to PR, or ready to mark complete. Requires fresh verification evidence and explicit command output before success claims.
npx skillsauth add srstomp/pokayokay verification-before-completionInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Evidence comes before completion claims. Do not say work is done, fixed, passing, ready, or complete until a fresh verification command proves it.
Before any success claim:
| Claim | Evidence required | |-------|-------------------| | Tests pass | Fresh test command with exit 0 | | Build passes | Fresh build/type-check command with exit 0 | | Bug fixed | Reproduction/regression test now passes | | Requirements met | Checklist mapped to files, tests, or behavior | | Agent completed | VCS diff reviewed plus verification command | | Ready to commit/PR | Tests/build relevant to changed surface plus self-review |
For bug fixes, a regression test must prove the original symptom:
If the project cannot support an automated regression test, document the manual reproduction steps and why automation was not feasible.
## Verification
- Command: `npm test -- path/to/test`
- Result: PASS, 12/12 tests, exit 0
- Scope checked: regression test for duplicate email handling
Avoid words like "should", "probably", or "looks good" when reporting status. Use observed results.
development
Git worktree management for isolated task development
development
Use when starting AI development sessions, resuming interrupted work, managing multi-session projects, or orchestrating work with human checkpoint control (supervised, semi-auto, auto, or unattended modes).
development
Use when designing test architecture, building API test suites, validating API contracts, setting up component or E2E testing, managing test data, debugging flaky tests, reviewing coverage strategy, or organizing test files. Covers test pyramid, mocking (MSW), frontend (React Testing Library, Playwright), and CI integration.
development
Use when diagnosing bugs, failing tests, build failures, unexpected behavior, flaky tests, regressions, or production incidents. Requires reproduction, root cause evidence, one-hypothesis fixes, and regression verification before editing.