메뉴
Verify code changes work by running them. Proves through execution, not just inspection.
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 |
| description | Verify code changes work by running them. Proves through execution, not just inspection. |
$ARGUMENTS
.agent/skills/verify-changes/SKILL.md firstUse the verify-changes skill to prove code works:
CONTEXT:
- What to verify: $ARGUMENTS
- If empty: verify the most recent code changes in this session
WORKFLOW:
1. IDENTIFY what changed (files, functions, behavior)
2. DETERMINE verification method (build, test, run, curl)
3. EXECUTE verification commands
4. REPORT evidence of success or failure
5. FLAG anything that couldn't be verified automatically
RULES:
1. Follow verify-changes/SKILL.md protocol
2. "It should work" is NOT verification — run it
3. Test error paths, not just success paths
4. Report with actual command output as evidence
## Verification Report
### Changes Verified
- [file/change 1]: ✅ Pass
- [file/change 2]: ✅ Pass
### Evidence
- Build: ✅ Compiled without errors
- Tests: ✅ [N]/[N] passing
- Runtime: ✅ [specific verification result]
### Not Verified
- [anything that needs manual testing]
/verify
/verify the login endpoint handles expired tokens
/verify build passes after refactoring
/verify the new component renders correctly
Generated by Agent Bridge