Verification Loop

affaan-m/ECC/docs/zh-CN/skills/verification-loop

by affaan-mef648e01899ba3e8dc6371642deaaf64b4477775No license275K starsListed Oct 9, 2026Updated Oct 9, 2026Repository updated 4 days ago

Claude Code 会话的全面验证系统。

Instructions onlySoftware Development
AI-generated overview

Runs a six-phase verification pass over a codebase before committing or opening a pull request.

What it does
Guides an agent through a structured verification loop covering build, type checking, linting, test suites with coverage, secret and debug-statement scanning, and diff review. It specifies shell commands for each phase and a report template summarizing pass/fail status per phase. The output is a verification report ending in a ready or not-ready verdict for a pull request.
When to use it
Use after finishing a feature or significant code change, before creating a pull request, after refactoring, or whenever quality gates need to be confirmed. It is also suggested for long sessions as a periodic checkpoint.
Requirements
No bundled scripts; instructions only. The described commands assume a project with npm or pnpm, TypeScript or Python tooling (tsc, pyright, ruff), a test runner with coverage, and git.

验证循环技能

一个全面的 Claude Code 会话验证系统。

何时使用

在以下情况下调用此技能:

  • 完成功能或重大代码变更后
  • 创建 PR 之前
  • 当您希望确保质量门通过时
  • 重构之后

验证阶段

阶段 1:构建验证

bash
# Check if project buildsnpm run build 2>&1 | tail -20# ORpnpm build 2>&1 | tail -20

如果构建失败,请停止并在继续之前修复。

阶段 2:类型检查

bash
# TypeScript projectsnpx tsc --noEmit 2>&1 | head -30
# Python projectspyright . 2>&1 | head -30

报告所有类型错误。在继续之前修复关键错误。

阶段 3:代码规范检查

bash
# JavaScript/TypeScriptnpm run lint 2>&1 | head -30
# Pythonruff check . 2>&1 | head -30

阶段 4:测试套件

bash
# Run tests with coveragenpm run test -- --coverage 2>&1 | tail -50
# Check coverage threshold# Target: 80% minimum

报告:

  • 总测试数:X
  • 通过:X
  • 失败:X
  • 覆盖率:X%

阶段 5:安全扫描

bash
# Check for secretsgrep -rn "sk-" --include="*.ts" --include="*.js" . 2>/dev/null | head -10grep -rn "api_key" --include="*.ts" --include="*.js" . 2>/dev/null | head -10
# Check for console.loggrep -rn "console.log" --include="*.ts" --include="*.tsx" src/ 2>/dev/null | head -10

阶段 6:差异审查

bash
# Show what changedgit diff --statgit diff HEAD~1 --name-only

审查每个更改的文件,检查:

  • 意外更改
  • 缺失的错误处理
  • 潜在的边界情况

输出格式

运行所有阶段后,生成验证报告:

验证报告==================
构建:     [通过/失败]类型:     [通过/失败] (X 处错误)代码检查:  [通过/失败] (X 条警告)测试:     [通过/失败] (X/Y 通过,覆盖率 Z%)安全:     [通过/失败] (X 个问题)差异:      [X 个文件被修改]
总体:     [就绪/未就绪] 提交 PR
待修复问题:1. ...2. ...

持续模式

对于长时间会话,每 15 分钟或在重大更改后运行验证:

markdown
设置一个心理检查点:- 完成每个函数后- 完成一个组件后- 在移动到下一个任务之前
运行: /verify

与钩子的集成

此技能补充 PostToolUse 钩子,但提供更深入的验证。 钩子会立即捕获问题;此技能提供全面的审查。

Source and attribution

Source:affaan-m/ECCindocs/zh-CN/skills/verification-loopat commitef648e0

License: No license

Content belongs to its original authors. SourceWeft indexes it from a public repository.

Report or request removal