affaan-m/ECC/docs/ko-KR/skills/verification-loop/SKILL.md
verification-loop
Use it for engineering tasks; the detail page covers purpose, installation, and practical steps.
- Source repository stars
- 234,327
- Declared platforms
- 1
- Static risk flags
- 1
- Last source update
- 2026-07-27
- Source checked
- 2026-07-28
Decision brief
What it does—and where it fits
Claude Code 세션을 위한 포괄적인 검증 시스템.
Not for
- Tasks that require unconfirmed production actions or broad system permissions.
- Environments where the pinned source and install steps cannot be inspected.
Compatibility matrix
Platform support, with evidence labels
| Platform | Status | Evidence | What to check |
|---|---|---|---|
| Codex | Not declared | No explicit evidence | Portability before use |
| Claude Code | Declared | Source record | Install path and trigger |
| Cursor | Not declared | No explicit evidence | Portability before use |
| Gemini CLI | Not declared | No explicit evidence | Portability before use |
Installation
Inspect first. Install second.
The source command is displayed only when detected. A safe inspection prompt is always available so your agent can explain every action before execution.
npx skills add https://github.com/affaan-m/ECC --skill "docs/ko-KR/skills/verification-loop"Inspect the Agent Skill "verification-loop" from https://github.com/affaan-m/ECC/blob/4e973d3eaf92d97f8d2e2d8abb39d8bdc8711b38/docs/ko-KR/skills/verification-loop/SKILL.md at commit 4e973d3eaf92d97f8d2e2d8abb39d8bdc8711b38. List every install step, command, network request, credential, file read/write, external action, and rollback step. Explain whether it fits my task. Do not install or execute anything until I approve.
Workflow
What the source asks the agent to do
- 01
사용 시점
다음 상황에서 이 스킬을 호출하세요: - 기능 또는 주요 코드 변경을 완료한 후 - PR을 생성하기 전 - 품질 게이트가 통과하는지 확인하고 싶을 때 - 리팩터링 후
기능 또는 주요 코드 변경을 완료한 후PR을 생성하기 전품질 게이트가 통과하는지 확인하고 싶을 때 - 02
검증 단계
Review the “검증 단계” section in the pinned source before continuing.
Review and apply the “검증 단계” source section. - 03
단계 1: 빌드 검증
Review the “단계 1: 빌드 검증” section in the pinned source before continuing.
Review and apply the “단계 1: 빌드 검증” source section. - 04
Check if project builds
Review the “Check if project builds” section in the pinned source before continuing.
Review and apply the “Check if project builds” source section.
Permission review
Static risk signals and limitations
Runs scripts
The documentation asks the agent to run terminal commands or scripts.
npm run build 2>&1 | tail -20Runs scripts
The documentation asks the agent to run terminal commands or scripts.
pnpm build 2>&1 | tail -20Evidence record
Why each signal appears
| Signal | Value | Evidence type | Meaning |
|---|---|---|---|
| Quality score | 61/100 | Computed | Documentation, specificity, maintenance, and trust rules |
| Repository stars | 234,327 | Source | Repository attention, not individual Skill quality |
| Compatibility | 1 platforms | Source | Declared in the catalog source record |
| Usage guide | automated source guide | Editorial | Generated or reviewed according to the visible evidence level |
Pinned source
Provenance and original SKILL.md
- Repository
- affaan-m/ECC
- Skill path
- docs/ko-KR/skills/verification-loop/SKILL.md
- Commit
- 4e973d3eaf92d97f8d2e2d8abb39d8bdc8711b38
- License
- MIT
- Collected
- 2026-07-28
- Default branch
- main
View the original SKILL.md
검증 루프 스킬
Claude Code 세션을 위한 포괄적인 검증 시스템.
사용 시점
다음 상황에서 이 스킬을 호출하세요:
- 기능 또는 주요 코드 변경을 완료한 후
- PR을 생성하기 전
- 품질 게이트가 통과하는지 확인하고 싶을 때
- 리팩터링 후
검증 단계
단계 1: 빌드 검증
# Check if project builds
npm run build 2>&1 | tail -20
# OR
pnpm build 2>&1 | tail -20
빌드가 실패하면 계속하기 전에 중단하고 수정합니다.
단계 2: 타입 검사
# TypeScript projects
npx tsc --noEmit 2>&1 | head -30
# Python projects
pyright . 2>&1 | head -30
모든 타입 에러를 보고합니다. 중요한 것은 계속하기 전에 수정합니다.
단계 3: 린트 검사
# JavaScript/TypeScript
npm run lint 2>&1 | head -30
# Python
ruff check . 2>&1 | head -30
단계 4: 테스트 스위트
# Run tests with coverage
npm run test -- --coverage 2>&1 | tail -50
# Check coverage threshold
# Target: 80% minimum
보고 항목:
- 전체 테스트: X
- 통과: X
- 실패: X
- 커버리지: X%
단계 5: 보안 스캔
# Check for secrets
grep -rn "sk-" --include="*.ts" --include="*.js" . 2>/dev/null | head -10
grep -rn "api_key" --include="*.ts" --include="*.js" . 2>/dev/null | head -10
# Check for console.log
grep -rn "console.log" --include="*.ts" --include="*.tsx" src/ 2>/dev/null | head -10
단계 6: Diff 리뷰
# Show what changed
git diff --stat
git diff --name-only
git diff --cached --name-only
각 변경된 파일에서 다음을 검토합니다:
- 의도하지 않은 변경
- 누락된 에러 처리
- 잠재적 엣지 케이스
출력 형식
모든 단계를 실행한 후 검증 보고서를 생성합니다:
VERIFICATION REPORT
==================
Build: [PASS/FAIL]
Types: [PASS/FAIL] (X errors)
Lint: [PASS/FAIL] (X warnings)
Tests: [PASS/FAIL] (X/Y passed, Z% coverage)
Security: [PASS/FAIL] (X issues)
Diff: [X files changed]
Overall: [READY/NOT READY] for PR
Issues to Fix:
1. ...
2. ...
연속 모드
긴 세션에서는 15분마다 또는 주요 변경 후에 검증을 실행합니다:
Set a mental checkpoint:
- After completing each function
- After finishing a component
- Before moving to next task
Run: /verify
Hook과의 통합
이 스킬은 PostToolUse Hook을 보완하지만 더 깊은 검증을 제공합니다. Hook은 즉시 문제를 포착하고, 이 스킬은 포괄적인 검토를 제공합니다.
Alternatives
Compare before choosing
affaan-m/ECC
verification-loop
A comprehensive verification system for Claude Code sessions.
affaan-m/ECC
verification-loop
A comprehensive verification system for Claude Code sessions.
affaan-m/ECC
verification-loop
Sistema de verificación completo para sesiones de Claude Code.
affaan-m/ECC
verification-loop
A comprehensive verification system for Claude Code sessions.