원클릭으로
verify-changes
"Code that exists" ≠ "Code that works." This skill ensures changes are verified through execution.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
메뉴
"Code that exists" ≠ "Code that works." This skill ensures changes are verified through execution.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Analyzes user's requests, determines tech stack, plans structure, and coordinates agents.
Apply consistent changes across many files at once. One pattern, many targets.
**MANDATORY:** Use for complex/vague requests, new features, updates.
Reduce AI token usage by **6.8x average** (up to **49x** on monorepos) by giving the AI a structural map of your codebase instead of letting it read everything.
Keep sessions productive by compressing completed work while preserving key decisions.
Advanced multi-agent coordination with parallel dispatch and synthesis. Use for complex tasks requiring multiple specialist perspectives.
| name | verify-changes |
| description | "Code that exists" ≠ "Code that works." This skill ensures changes are verified through execution. |
"Code that exists" ≠ "Code that works." This skill ensures changes are verified through execution.
❌ Verification by inspection: "I can see the function exists, it should work"
❌ Verification by assumption: "The types check out, so it's correct"
✅ Verification by execution: "I ran it, here's the output, it works because [evidence]"
- Which files were modified?
- What behavior should be different now?
- What was the original bug/requirement?
| Change Type | Verification Method |
|---|---|
| Bug fix | Reproduce the original bug scenario → confirm it no longer occurs |
| New feature | Run the feature → confirm expected output |
| Refactor | Run existing tests → confirm nothing broke |
| API change | Call the endpoint → confirm response shape |
| UI change | Render the component → confirm visual output |
| Config change | Load the config → confirm values applied |
| Build/infra | Run build command → confirm success |
# For Node.js projects
npm run build # Does it compile?
npm run test # Do tests pass?
npm run dev # Does it start?
# For specific files
node -e "require('./path/to/module'); console.log('✅ Loads correctly')"
# For API endpoints
curl http://localhost:3000/api/endpoint
# For scripts
python script.py --test
## Verification Report
### What was changed
- [File list and summary]
### How it was verified
- [Exact commands run]
### Evidence
- Build: ✅ Compiled without errors
- Tests: ✅ 42/42 passing
- Runtime: ✅ Server starts, endpoint returns expected JSON
- Edge case: ✅ Empty input handled correctly
### Not yet verified
- [Anything that couldn't be tested automatically]
npm run build — compiles without errorsnpm run lint — no linting errorsnpm run test — all tests pass| Anti-Pattern | Why It's Bad | Fix |
|---|---|---|
| "It should work" | No evidence | Run it and show output |
| Only checking happy path | Bugs hide in edge cases | Test error paths too |
| Verifying only compilation | Compiles ≠ correct | Test runtime behavior |
| Skipping verification for "trivial" changes | Trivial changes cause real bugs | Verify everything |
| After Using | Verify With |
|---|---|
frontend-design → UI changes | Render in browser, check console |
backend-specialist → API changes | curl endpoints, check responses |
database-design → Schema changes | Run migrations, query data |
testing-patterns → New tests | Run test suite, check coverage |
Generated by Agent Bridge