Communitygithub.com

verification-loop

Claude Code 세션을 위한 포괄적인 검증 시스템입니다. Claude Code 세션 검증 시 사용합니다.

verification-loop란 무엇인가요?

이 스킬은 Claude Code 세션을 위한 종합 검증 시스템(Verification Loop Skill)입니다. 기능 완료, PR 생성 전, 또는 리팩토링 후에 품질 게이트를 통과했는지 확인하고자 할 때 사용됩니다. 빌드 검증, 타입 검사, 린트 검사, 테스트 스위트 실행, 보안 스캔, Diff 리뷰의 6단계 검증을 순차적으로 수행합니다. 각 단계는 CLI 명령어를 통해 실행되며, 최종적으로 검증 보고서를 생성하여 PR 준비 상태를 평가합니다. 또한 장기 세션에서 15분마다 또는 주요 변경 후 자동 검증을 설정할 수 있는 연속 모드 기능과 PostToolUse 훅을 보완하는 심층 검토를 제공합니다.

지원 대상✓Claude Code~Codex CLI~Cursor
npx skills add https://github.com/affaan-m/everything-claude-code/tree/main/skills/verification-loop

즐겨 사용하는 AI에게 물어보기

이 에이전트 스킬이 미리 로드된 새 채팅을 엽니다.

문서

검증 루프 스킬

Claude Code 세션을 위한 포괄적인 검증 시스템입니다.

사용 시기

다음과 같은 경우 이 스킬을 호출하세요:

  • 기능 또는 중요한 코드 변경 완료 후
  • PR 생성 전
  • 품질 게이트 통과를 확인하려는 경우
  • 리팩토링 후

검증 단계

1단계: 빌드 검증

# 프로젝트 빌드 확인
npm run build 2>&1 | tail -20
# 또는
pnpm build 2>&1 | tail -20

빌드가 실패하면 중단하고 계속하기 전에 수정하세요.

2단계: 타입 검사

set -o pipefail
# TypeScript 프로젝트
npx --no-install tsc --noEmit 2>&1 | head -30

# Python 프로젝트
pyright . 2>&1 | head -30

모든 타입 오류를 보고하세요. 중요한 오류는 계속하기 전에 수정하세요.

3단계: 린트 검사

# JavaScript/TypeScript
npm run lint 2>&1 | head -30

# Python
ruff check . 2>&1 | head -30

4단계: 테스트 스위트

# 커버리지와 함께 테스트 실행
npm run test -- --coverage 2>&1 | tail -50

# 커버리지 임계값 확인
# 목표: 최소 80%

보고:

  • 총 테스트: X
  • 통과: X
  • 실패: X
  • 커버리지: X%

5단계: 보안 스캔

# 시크릿 확인
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

# console.log 확인
grep -rn "console.log" --include="*.ts" --include="*.tsx" src/ 2>/dev/null | head -10

6단계: Diff 검토

# 변경된 내용 보기
git diff --stat
git diff HEAD~1 --name-only

각 변경된 파일을 검토하세요:

  • 의도하지 않은 변경
  • 누락된 오류 처리
  • 잠재적인 엣지 케이스

출력 형식

모든 단계를 실행한 후 검증 보고서를 생성하세요:

검증 보고서
==================

빌드:     [PASS/FAIL]
타입:     [PASS/FAIL] (X 오류)
린트:     [PASS/FAIL] (X 경고)
테스트:   [PASS/FAIL] (X/Y 통과, Z% 커버리지)
보안:     [PASS/FAIL] (X 이슈)
Diff:     [X 파일 변경]

전체:     [READY/NOT READY] PR 가능

수정해야 할 이슈:
1. ...
2. ...

연속 모드

장기 세션의 경우 15분마다 또는 주요 변경 후 검증을 실행하세요:

정신적 체크포인트 설정:
- 각 함수 완료 후
- 컴포넌트 완료 후
- 다음 작업으로 이동하기 전

실행: /verify

훅과의 통합

이 스킬은 PostToolUse 훅을 보완하지만 더 깊은 검증을 제공합니다. 훅은 즉시 문제를 잡아내고, 이 스킬은 포괄적인 검토를 제공합니다.

Individual skills in this repo

This repo contains 20 individual skills — each has its own dedicated page.

accessibility

Design, implement, and audit inclusive digital products using WCAG 2.2 Level AA. Use when building or auditing UI that must meet WCAG 2.2 Level AA, or when reviewing a change for keyboard, contrast, or screen-reader support.

affaan-m/claude-api

Anthropic Claude API patterns for Python and TypeScript. Covers Messages API, streaming, tool use, vision, extended thinking, batches, prompt caching, and Claude Agent SDK. Use when building applications with the Claude API or Anthropic SDKs.

affaan-m/everything-claude-code

End-to-end marketing campaign planning and execution. Covers audience research, positioning, campaign angle definition, landing page copy, email sequences, social posts, ad copy, short-form video scripts, and content calendars. Use as the orchestration layer for multi-channel product launches. Use when planning or executing a multi-channel product launch, or producing landing page, email, social, or ad copy.

affaan-m/everything-claude-code

Development conventions and patterns for everything-claude-code. JavaScript project with conventional commits.

affaan-m/everything-claude-code-conventions

Development conventions and patterns for everything-claude-code. JavaScript project with conventional commits.

affaan-m/frontend-design

Create distinctive, production-grade frontend interfaces with high design quality. Use when the user asks to build web components, pages, or applications and the visual direction matters as much as the code quality.

affaan-m/gget

gget CLI and Python workflow for quick genomic database queries, sequence lookup, BLAST-style searches, enrichment checks, and reproducible bioinformatics evidence logs.

affaan-m/literature-review

Systematic literature-review workflow for academic, biomedical, technical, and scientific topics, including search planning, source screening, synthesis, citation checks, and evidence logging.

affaan-m/motion-ui

Production-ready UI motion system for React/Next.js. Use when implementing animations, transitions, or motion patterns.

affaan-m/project-guidelines-example

Example project-specific skill template based on a real production application.

affaan-m/pubmed-database

Direct PubMed and NCBI E-utilities search workflows for biomedical literature, MeSH queries, PMID lookup, citation retrieval, and API-backed literature monitoring.

affaan-m/scholar-evaluation

Structured scholarly-work evaluation for papers, proposals, literature reviews, methods sections, evidence quality, citation support, and research-writing feedback.

affaan-m/uspto-database

USPTO patent and trademark data workflow for official record lookup, PatentSearch queries, TSDR checks, assignment data, and reproducible IP research logs.

agent-architecture-audit

Full-stack diagnostic for agent and LLM applications. Audits the 12-layer agent stack for wrapper regression, memory pollution, tool discipline failures, hidden repair loops, and rendering corruption. Produces severity-ranked findings with code-first fixes. Essential for developers building agent applications, autonomous loops, or any LLM-powered feature. Use when an agent or LLM feature misbehaves and the failing layer is unknown, or before shipping an agent stack.

agent-eval

Head-to-head comparison of coding agents (Claude Code, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and consistency metrics. Use when choosing between coding agents, or when a change to an agent setup needs measured pass rate, cost, and time rather than an impression.

agent-harness-construction

Design and optimize AI agent action spaces, tool definitions, and observation formatting for higher completion rates. Use when defining or revising an agent

agentic-engineering

Operate as an agentic engineer using eval-first execution, decomposition, and cost-aware model routing. Use when planning or executing engineering work that agents will carry out end to end.

agentic-os

Build persistent multi-agent operating systems on Claude Code. Covers kernel architecture, specialist agents, slash commands, file-based memory, scheduled automation, and state management without external databases. Use when building a persistent multi-agent system on Claude Code with its own memory, commands, and scheduling.

agent-introspection-debugging

Structured self-debugging workflow for AI agent failures using capture, diagnosis, contained recovery, and introspection reports. Use when an agent run fails and you need a reproducible diagnosis instead of a retry.

agent-payment-x402

Add x402 payment execution to AI agents with per-task budgets, spending controls, and non-custodial wallets. Supports Base through agentwallet-sdk and X Layer through OKX Payments / OKX Agent Payments Protocol. Use when an agent must pay for something itself and needs per-task budgets, spending controls, and a non-custodial wallet.

관련 스킬