Runs multi-stage verification on code changes: build, type checks (tsc/pyright), lint (eslint/ruff), tests with coverage, security scans (secrets/console.log), git diff review. Use before PRs, after refactors.
How this skill is triggered — by the user, by Claude, or both
Slash command
/everything-claude-code:verification-loopThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Claude Code 会话的全方位验证系统。
Claude Code 会话的全方位验证系统。
在以下场景调用此技能(Skill):
# 检查项目是否构建成功
npm run build 2>&1 | tail -20
# 或者
pnpm build 2>&1 | tail -20
如果构建失败,请停止并修复后方可继续。
# TypeScript 项目
npx tsc --noEmit 2>&1 | head -30
# Python 项目
pyright . 2>&1 | head -30
报告所有类型错误。在继续之前修复关键错误。
# JavaScript/TypeScript
npm run lint 2>&1 | head -30
# Python
ruff check . 2>&1 | head -30
# 运行带覆盖率的测试
npm run test -- --coverage 2>&1 | tail -50
# 检查覆盖率阈值
# 目标:最低 80%
报告:
# 检查密钥/机密
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
# 检查 console.log
grep -rn "console.log" --include="*.ts" --include="*.tsx" src/ 2>/dev/null | head -10
# 显示变更内容
git diff --stat
git diff HEAD~1 --name-only
审查每个变更的文件:
运行所有阶段后,生成验证报告:
验证报告(VERIFICATION REPORT)
==================
构建 (Build): [通过/失败]
类型 (Types): [通过/失败] (X 个错误)
Lint: [通过/失败] (X 个警告)
测试 (Tests): [通过/失败] (X/Y 通过, Z% 覆盖率)
安全 (Security): [通过/失败] (X 个问题)
变更 (Diff): [X 个文件已变更]
总体评价: [已就绪/未就绪] 提交 PR
待修复问题:
1. ...
2. ...
对于较长的会话,每 15 分钟或在重大更改后运行验证:
设定心智检查点:
- 完成每个函数后
- 完成一个组件后
- 在进入下一个任务前
运行:/verify
此技能是 PostToolUse 钩子(Hooks)的补充,但提供更深入的验证。
钩子能立即捕捉问题;此技能则提供全方位的审查。
npx claudepluginhub xu-xiang/everything-claude-code-zhRuns multi-phase code verification: build, type checks (TypeScript/Python), linting, tests with 80% coverage goal, security scans for secrets/console.log, git diff review. Use after features, refactors, before PRs.
Runs a multi-phase verification pipeline (build, types, lint, tests, security, diff review) after code changes or before PRs.
Runs a multi-phase verification loop including build, type check, lint, tests, security scan, and diff review. Useful before creating a PR or after significant changes.