affaan-m/ECC/docs/zh-CN/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
一个全面的 Claude Code 会话验证系统。
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/zh-CN/skills/verification-loop"Inspect the Agent Skill "verification-loop" from https://github.com/affaan-m/ECC/blob/4e973d3eaf92d97f8d2e2d8abb39d8bdc8711b38/docs/zh-CN/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
何时使用
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
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 - 02
验证阶段
Review the “验证阶段” section in the pinned source before continuing.
Review and apply the “验证阶段” source section. - 03
阶段 1:构建验证
Review the “阶段 1:构建验证” section in the pinned source before continuing.
Review and apply the “阶段 1:构建验证” 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 | 56/100 | 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 | catalog record | Editorial | Generated or reviewed according to the visible evidence level |
Pinned source
Provenance and original SKILL.md
- Repository
- affaan-m/ECC
- Skill path
- docs/zh-CN/skills/verification-loop/SKILL.md
- Commit
- 4e973d3eaf92d97f8d2e2d8abb39d8bdc8711b38
- License
- MIT
- Collected
- 2026-07-28
- Default branch
- main
View the original SKILL.md
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
# Check if project builds
npm run build 2>&1 | tail -20
# OR
pnpm 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
# TypeScript projects
npx tsc --noEmit 2>&1 | head -30
# Python projects
pyright . 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
# JavaScript/TypeScript
npm run lint 2>&1 | head -30
# Python
ruff check . 2>&1 | head -30
阶段 4:测试套件
# Run tests with coverage
npm 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
# 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
阶段 6:差异审查
# Show what changed
git diff --stat
git 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:
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。
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.