Agent skill
verification-validator
Minimal verification based on change type. Backend=pytest, Frontend=webpack, CSS=webpack, Full flow=Playwright.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/other/verification-validator
SKILL.md
Verification Validator
Principle: Minimum necessary verification only. No overkill.
Decision Tree
git diff --name-only HEAD~1
│
├─ apps/api/** only ──────────► pytest only (~500 tokens)
│
├─ *.tsx only ────────────────► webpack check (~500 tokens)
│
├─ *.scss only ───────────────► webpack check (~500 tokens)
│
├─ API + Frontend together ───► Full Playwright (~10,000 tokens)
│
└─ en.json only ──────────────► webpack check (~500 tokens)
Verification Commands
Backend Only (apps/api/**)
cd /Users/beomsu/Documents/My\ Awesome\ RA/apps/api
source .venv/bin/activate && pytest -v --tb=short
Done. No frontend checks needed.
Frontend Only (*.tsx, *.scss, en.json)
cd /Users/beomsu/Documents/My\ Awesome\ RA/overleaf/develop
docker compose logs webpack --tail 20 | grep -E "compiled|error"
Done. If "compiled successfully" appears, verification complete.
Full Flow (API + Frontend Integration)
Only when BOTH conditions:
- Backend API changed (apps/api/**)
- Frontend calls that API (evidence-panel components)
Then use Playwright:
1. browser_navigate → http://localhost/login
2. browser_snapshot → find form refs
3. browser_fill_form → login
4. browser_click → login button
5. browser_wait_for → {time: 2}
6. browser_snapshot → verify feature works
7. browser_close
What NOT to Do
| Change Type | DO NOT |
|---|---|
| Backend only | Run webpack, Playwright |
| Frontend only | Run pytest, Playwright |
| CSS only | Run pytest, Playwright, browser tests |
| i18n only | Run pytest, Playwright |
Quick Reference
| Change | Command | Done? |
|---|---|---|
apps/api/** |
pytest -v --tb=short |
Yes |
*.tsx |
docker compose logs webpack |
Yes |
*.scss |
docker compose logs webpack |
Yes |
en.json |
docker compose logs webpack |
Yes |
| API + Frontend | Playwright sequence | Yes |
When to Use Playwright
ONLY when testing user-facing integration:
- Login flow changes
- Evidence search API + UI together
- PDF toolbar + backend API
NEVER for:
- Backend-only changes
- Component logic changes
- Styling changes
- Translation changes
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
majiayu000/claude-skill-registry
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
majiayu000/claude-skill-registry
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
majiayu000/claude-skill-registry
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
majiayu000/claude-skill-registry
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
majiayu000/claude-skill-registry
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
majiayu000/claude-skill-registry
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?