verification-loop
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseVerification Loop Skill
验证循环Skill
A comprehensive verification system for Claude Code sessions.
面向Claude Code会话的全面验证系统。
When to Use
使用场景
Invoke this skill:
- After completing a feature or significant code change
- Before creating a PR
- When you want to ensure quality gates pass
- After refactoring
调用此Skill的场景:
- 完成某个功能或重大代码变更后
- 创建PR之前
- 希望确保质量门禁通过时
- 重构完成后
Verification Phases
验证阶段
Phase 1: Build Verification
阶段1:构建验证
bash
undefinedbash
undefinedCheck if project builds
Check if project builds
npm run build 2>&1 | tail -20
npm run build 2>&1 | tail -20
OR
OR
pnpm build 2>&1 | tail -20
If build fails, STOP and fix before continuing.pnpm build 2>&1 | tail -20
如果构建失败,请停止操作并修复后再继续。Phase 2: Type Check
阶段2:类型检查
bash
undefinedbash
undefinedTypeScript projects
TypeScript projects
npx tsc --noEmit 2>&1 | head -30
npx tsc --noEmit 2>&1 | head -30
Python projects
Python projects
pyright . 2>&1 | head -30
Report all type errors. Fix critical ones before continuing.pyright . 2>&1 | head -30
报告所有类型错误。修复严重错误后再继续。Phase 3: Lint Check
阶段3:代码规范检查
bash
undefinedbash
undefinedJavaScript/TypeScript
JavaScript/TypeScript
npm run lint 2>&1 | head -30
npm run lint 2>&1 | head -30
Python
Python
ruff check . 2>&1 | head -30
undefinedruff check . 2>&1 | head -30
undefinedPhase 4: Test Suite
阶段4:测试套件
bash
undefinedbash
undefinedRun tests with coverage
Run tests with coverage
npm run test -- --coverage 2>&1 | tail -50
npm run test -- --coverage 2>&1 | tail -50
Check coverage threshold
Check coverage threshold
Target: 80% minimum
Target: 80% minimum
Report:
- Total tests: X
- Passed: X
- Failed: X
- Coverage: X%
报告内容:
- 测试总数:X
- 通过数:X
- 失败数:X
- 覆盖率:X%Phase 5: Security Scan
阶段5:安全扫描
bash
undefinedbash
undefinedCheck for secrets
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
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
Check for console.log
grep -rn "console.log" --include=".ts" --include=".tsx" src/ 2>/dev/null | head -10
undefinedgrep -rn "console.log" --include=".ts" --include=".tsx" src/ 2>/dev/null | head -10
undefinedPhase 6: Diff Review
阶段6:差异审查
bash
undefinedbash
undefinedShow what changed
Show what changed
git diff --stat
git diff HEAD~1 --name-only
Review each changed file for:
- Unintended changes
- Missing error handling
- Potential edge casesgit diff --stat
git diff HEAD~1 --name-only
审查每个变更文件,检查以下内容:
- 非预期变更
- 缺失的错误处理
- 潜在的边缘情况Output Format
输出格式
After running all phases, produce a verification report:
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. ...完成所有阶段后,生成一份验证报告:
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. ...Continuous Mode
持续模式
For long sessions, run verification every 15 minutes or after major changes:
markdown
Set a mental checkpoint:
- After completing each function
- After finishing a component
- Before moving to next task
Run: /verify对于长时间会话,每15分钟或在重大变更后运行一次验证:
markdown
Set a mental checkpoint:
- After completing each function
- After finishing a component
- Before moving to next task
Run: /verifyIntegration with Hooks
与Hooks的集成
This skill complements PostToolUse hooks but provides deeper verification.
Hooks catch issues immediately; this skill provides comprehensive review.
此Skill是PostToolUse Hooks的补充,可提供更深入的验证。
Hooks可即时发现问题;而此Skill可提供全面审查。