Back to Details

checklist-generator

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Quality Checklist Generator

质量检查清单生成器

Overview

概述

Generate comprehensive, context-aware quality checklists combining IEEE 1028 standards (80-90%) with LLM-generated contextual items (10-20%). Ensures systematic quality validation before completion.
Core principle: Universal quality standards enhanced with project-specific context.
生成全面的、具备上下文感知能力的质量检查清单，其中80-90%的内容基于IEEE 1028标准，10-20%为大语言模型（LLM）生成的上下文特定项。确保在任务完成前进行系统化的质量验证。
核心原则： 通用质量标准结合项目特定上下文。

When to Use

适用场景

Always:
  • Before completing implementation tasks
  • During code review
  • QA validation phase
  • Pre-commit verification
  • Before marking tasks complete
Exceptions:
  • Throwaway prototypes
  • Configuration-only changes
始终适用：
  • 完成实现任务前
  • 代码评审期间
  • QA验证阶段
  • 提交前验证
  • 标记任务完成前
例外情况：
  • 一次性原型
  • 仅配置变更

Purpose

目标

  1. IEEE 1028 Base: Proven quality review standards (universal)
  2. Contextual Enhancement: LLM adds project-specific items
  3. Systematic Validation: Ensures comprehensive quality coverage
  1. IEEE 1028基础： 经过验证的通用质量评审标准
  2. 上下文增强： LLM添加项目特定项
  3. 系统化验证： 确保全面覆盖质量检查

IEEE 1028 Base Categories

IEEE 1028基础分类

The following categories are included in every checklist (80-90% of items):
以下分类会包含在所有检查清单中（占80-90%的项）：

Code Quality

代码质量

  • Code follows project style guide
  • No code duplication (DRY principle)
  • Cyclomatic complexity < 10 per function
  • Functions have single responsibility
  • Variable names are clear and descriptive
  • Magic numbers replaced with named constants
  • Dead code removed
  • 代码遵循项目风格指南
  • 无代码重复（DRY原则）
  • 每个函数的圈复杂度<10
  • 函数单一职责
  • 变量名称清晰且具有描述性
  • 魔法数替换为命名常量
  • 移除死代码

Testing

测试

  • Tests written first (TDD followed)
  • All new code has corresponding tests
  • Tests cover edge cases and error conditions
  • Test coverage ≥ 80% for new code
  • Integration tests for multi-component interactions
  • Tests are isolated and don't depend on order
  • 先编写测试（遵循TDD）
  • 所有新代码都有对应的测试
  • 测试覆盖边界情况和错误场景
  • 新代码的测试覆盖率≥80%
  • 多组件交互的集成测试
  • 测试相互独立，不依赖执行顺序

Security

安全

  • Input validation on all user inputs
  • No SQL injection vulnerabilities
  • No XSS vulnerabilities
  • Sensitive data encrypted at rest and in transit
  • Authentication and authorization checks present
  • No hardcoded secrets or credentials
  • OWASP Top 10 considered
  • 所有用户输入都经过验证
  • 无SQL注入漏洞
  • 无XSS漏洞
  • 敏感数据在静态存储和传输过程中加密
  • 存在身份验证和授权检查
  • 无硬编码的密钥或凭证
  • 考虑OWASP Top 10风险

Performance

性能

  • No obvious performance bottlenecks
  • Database queries optimized (no N+1 queries)
  • Appropriate caching used
  • Resource cleanup (close connections, release memory)
  • No infinite loops or recursion risks
  • Large data operations paginated
  • 无明显性能瓶颈
  • 数据库查询已优化（无N+1查询）
  • 使用了合适的缓存策略
  • 资源已清理（关闭连接、释放内存）
  • 无无限循环或递归风险
  • 大数据操作已分页

Documentation

文档

  • Public APIs documented
  • Complex logic has explanatory comments
  • README updated if needed
  • CHANGELOG updated
  • Breaking changes documented
  • Architecture diagrams updated if structure changed
  • 公共API已文档化
  • 复杂逻辑有解释性注释
  • 若有需要，已更新README
  • 已更新CHANGELOG
  • 破坏性变更已文档化
  • 若架构变更，已更新架构图

Error Handling

错误处理

  • All error conditions handled
  • User-friendly error messages (4xx for user errors)
  • Detailed logs for debugging (5xx for system errors)
  • No swallowed exceptions
  • Graceful degradation implemented
  • Rollback procedures for failures
  • 所有错误场景都已处理
  • 用户友好的错误消息（用户错误返回4xx状态码）
  • 用于调试的详细日志（系统错误返回5xx状态码）
  • 无被吞噬的异常
  • 实现了优雅降级
  • 故障回滚流程

Contextual Addition Logic

上下文补充逻辑

The skill analyzes the current project context to add 10-20% contextual items:
本技能会分析当前项目上下文，添加10-20%的上下文特定项：

Detection Strategy

检测策略

  1. Read project files to identify:
    • Framework (React, Vue, Angular, Next.js, FastAPI, etc.)
    • Language (TypeScript, Python, Go, Java, etc.)
    • Patterns (REST API, GraphQL, microservices, monolith)
    • Infrastructure (Docker, Kubernetes, serverless)
  2. Generate contextual items based on findings:
TypeScript Projects:
  • [AI-GENERATED] TypeScript types exported properly
  • [AI-GENERATED] No 
    any
    types unless justified with comment
  • [AI-GENERATED] Strict null checks satisfied
React Projects:
  • [AI-GENERATED] Components use proper memo/useCallback
  • [AI-GENERATED] No unnecessary re-renders (React DevTools checked)
  • [AI-GENERATED] Hooks follow Rules of Hooks
  • [AI-GENERATED] Accessibility attributes (aria-*) on interactive elements
API Projects:
  • [AI-GENERATED] Rate limiting implemented
  • [AI-GENERATED] API versioning strategy followed
  • [AI-GENERATED] OpenAPI/Swagger docs updated
  • [AI-GENERATED] Request/response validation with schemas
Database Projects:
  • [AI-GENERATED] Migration scripts reversible
  • [AI-GENERATED] Indexes added for query performance
  • [AI-GENERATED] Database transactions used appropriately
  • [AI-GENERATED] Connection pooling configured
Python Projects:
  • [AI-GENERATED] Type hints on all public functions
  • [AI-GENERATED] Docstrings follow Google/NumPy style
  • [AI-GENERATED] Virtual environment requirements.txt updated
Mobile Projects:
  • [AI-GENERATED] Offline mode handled gracefully
  • [AI-GENERATED] Battery usage optimized (no constant polling)
  • [AI-GENERATED] Data usage minimized (compression, caching)
  • [AI-GENERATED] Platform-specific features tested
DevOps/Infrastructure:
  • [AI-GENERATED] Infrastructure as code (Terraform, CloudFormation)
  • [AI-GENERATED] Monitoring and alerting configured
  • [AI-GENERATED] Backup and disaster recovery tested
  • [AI-GENERATED] Security groups/firewall rules minimal access
  1. 读取项目文件以识别：
    • 框架（React、Vue、Angular、Next.js、FastAPI等）
    • 语言（TypeScript、Python、Go、Java等）
    • 模式（REST API、GraphQL、微服务、单体应用）
    • 基础设施（Docker、Kubernetes、无服务器架构）
  2. 基于检测结果生成上下文项：
TypeScript项目：
  • [AI生成] TypeScript类型导出正确
  • [AI生成] 除非有注释说明理由，否则不使用
    any
    类型
  • [AI生成] 满足严格空值检查要求
React项目：
  • [AI生成] 组件正确使用memo/useCallback
  • [AI生成] 无不必要的重渲染（已通过React DevTools检查）
  • [AI生成] Hooks遵循Hooks规则
  • [AI生成] 交互元素添加了可访问性属性（aria-*）
API项目：
  • [AI生成] 已实现速率限制
  • [AI生成] 遵循API版本控制策略
  • [AI生成] 已更新OpenAPI/Swagger文档
  • [AI生成] 使用Schema对请求/响应进行验证
数据库项目：
  • [AI生成] 迁移脚本可回滚
  • [AI生成] 为查询性能添加了索引
  • [AI生成] 合理使用数据库事务
  • [AI生成] 已配置连接池
Python项目：
  • [AI生成] 所有公共函数都有类型提示
  • [AI生成] 文档字符串遵循Google/NumPy风格
  • [AI生成] 虚拟环境的requirements.txt已更新
移动项目：
  • [AI生成] 离线模式处理优雅
  • [AI生成] 电池使用已优化（无持续轮询）
  • [AI生成] 数据使用已最小化（压缩、缓存）
  • [AI生成] 平台特定功能已测试
DevOps/基础设施：
  • [AI生成] 基础设施即代码（Terraform、CloudFormation）
  • [AI生成] 已配置监控和告警
  • [AI生成] 备份和灾难恢复已测试
  • [AI生成] 安全组/防火墙规则遵循最小权限原则

Output Format

输出格式

Checklists are returned as markdown with checkboxes:
markdown
undefined
检查清单以带复选框的Markdown格式返回：
markdown
undefined

Quality Checklist

Quality Checklist

Generated: {timestamp} Context: {detected frameworks/languages}
Generated: {timestamp} Context: {detected frameworks/languages}

Code Quality (IEEE 1028)

Code Quality (IEEE 1028)

  • Code follows project style guide
  • No code duplication
  • Cyclomatic complexity < 10
  • Code follows project style guide
  • No code duplication
  • Cyclomatic complexity < 10

Testing (IEEE 1028)

Testing (IEEE 1028)

  • Tests written first (TDD followed)
  • Test coverage ≥ 80%
  • Tests cover edge cases
  • Tests written first (TDD followed)
  • Test coverage ≥ 80%
  • Tests cover edge cases

Security (IEEE 1028)

Security (IEEE 1028)

  • Input validation on all user inputs
  • No hardcoded secrets
  • OWASP Top 10 considered
  • Input validation on all user inputs
  • No hardcoded secrets
  • OWASP Top 10 considered

Performance (IEEE 1028)

Performance (IEEE 1028)

  • No obvious performance bottlenecks
  • Database queries optimized
  • Appropriate caching used
  • No obvious performance bottlenecks
  • Database queries optimized
  • Appropriate caching used

Documentation (IEEE 1028)

Documentation (IEEE 1028)

  • Public APIs documented
  • README updated if needed
  • CHANGELOG updated
  • Public APIs documented
  • README updated if needed
  • CHANGELOG updated

Error Handling (IEEE 1028)

Error Handling (IEEE 1028)

  • All error conditions handled
  • User-friendly error messages
  • Detailed logs for debugging
  • All error conditions handled
  • User-friendly error messages
  • Detailed logs for debugging

Context-Specific Items (AI-Generated)

Context-Specific Items (AI-Generated)

{Detected: TypeScript + React + REST API}
  • [AI-GENERATED] TypeScript types exported properly
  • [AI-GENERATED] React components use proper memo
  • [AI-GENERATED] API rate limiting implemented
  • [AI-GENERATED] OpenAPI docs updated
Total Items: {count} IEEE Base: {ieee_count} ({percentage}%) Contextual: {contextual_count} ({percentage}%)
undefined
{Detected: TypeScript + React + REST API}
  • [AI-GENERATED] TypeScript types exported properly
  • [AI-GENERATED] React components use proper memo
  • [AI-GENERATED] API rate limiting implemented
  • [AI-GENERATED] OpenAPI docs updated
Total Items: {count} IEEE Base: {ieee_count} ({percentage}%) Contextual: {contextual_count} ({percentage}%)
undefined

Usage

使用方法

Basic Invocation

基础调用

javascript
Skill({ skill: 'checklist-generator' });
This will:
  1. Analyze current project context
  2. Load IEEE 1028 base checklist
  3. Generate contextual items (10-20%)
  4. Return combined markdown checklist
javascript
Skill({ skill: 'checklist-generator' });
此调用会：
  1. 分析当前项目上下文
  2. 加载IEEE 1028基础检查清单
  3. 生成上下文项（10-20%）
  4. 返回合并后的Markdown检查清单

With Specific Context

指定上下文

javascript
// Provide explicit context
Skill({
  skill: 'checklist-generator',
  args: 'typescript react api',
});
javascript
// 提供明确上下文
Skill({
  skill: 'checklist-generator',
  args: 'typescript react api',
});

Integration with QA Workflow

与QA工作流集成

javascript
// Part of QA validation
Skill({ skill: 'checklist-generator' });
// Use checklist for systematic validation
Skill({ skill: 'qa-workflow' });
javascript
// QA验证的一部分
Skill({ skill: 'checklist-generator' });
// 使用检查清单进行系统化验证
Skill({ skill: 'qa-workflow' });

Integration Points

集成点

QA Agent

QA Agent

The 
qa
agent uses this skill for validation:
  1. Generate checklist at task start
  2. Validate each item systematically
  3. Report checklist completion status
qa
agent使用此技能进行验证：
  1. 在任务开始时生成检查清单
  2. 系统化验证每个项
  3. 报告检查清单完成状态

Verification-Before-Completion

完成前验证

Used as pre-completion gate:
  1. Generate checklist before marking task complete
  2. Ensure all items verified
  3. Block completion if critical items fail
作为完成前的关卡使用：
  1. 在标记任务完成前生成检查清单
  2. 确保所有项都已验证
  3. 如果关键项未通过，阻止任务完成

Code-Reviewer Agent

代码评审Agent

Used during code review:
  1. Generate checklist for PR
  2. Check each item against changes
  3. Comment on missing items
在代码评审期间使用：
  1. 为PR生成检查清单
  2. 对照变更检查每个项
  3. 对缺失项添加评论

Context Detection Algorithm

上下文检测算法

1. Read package.json or requirements.txt or go.mod
   → Extract dependencies

2. Glob for framework-specific files:
   - React: **/*.jsx, **/*.tsx, package.json with "react"
   - Vue: **/*.vue, package.json with "vue"
   - Next.js: next.config.js, app/**, pages/**
   - FastAPI: **/main.py with "from fastapi"
   - Django: **/settings.py, **/models.py

3. Analyze imports/dependencies:
   - TypeScript: tsconfig.json
   - GraphQL: **/*.graphql, **/*.gql
   - Docker: Dockerfile, docker-compose.yml
   - Kubernetes: **/*.yaml in k8s/ or manifests/

4. Generate contextual items based on detected stack
5. Mark all generated items with [AI-GENERATED]
1. Read package.json or requirements.txt or go.mod
   → Extract dependencies

2. Glob for framework-specific files:
   - React: **/*.jsx, **/*.tsx, package.json with "react"
   - Vue: **/*.vue, package.json with "vue"
   - Next.js: next.config.js, app/**, pages/**
   - FastAPI: **/main.py with "from fastapi"
   - Django: **/settings.py, **/models.py

3. Analyze imports/dependencies:
   - TypeScript: tsconfig.json
   - GraphQL: **/*.graphql, **/*.gql
   - Docker: Dockerfile, docker-compose.yml
   - Kubernetes: **/*.yaml in k8s/ or manifests/

4. Generate contextual items based on detected stack
5. Mark all generated items with [AI-GENERATED]

Example: TypeScript + React + API Project

示例：TypeScript + React + API项目

Input Context:
  • package.json
    contains: "react": "^18.0.0", "typescript": "^5.0.0"
  • Files include: 
    src/components/*.tsx
    , 
    src/api/*.ts
Generated Checklist:
markdown
undefined
输入上下文：
  • package.json
    包含："react": "^18.0.0", "typescript": "^5.0.0"
  • 文件包括：
    src/components/*.tsx
    , 
    src/api/*.ts
生成的检查清单：
markdown
undefined

Quality Checklist

Quality Checklist

Generated: 2026-01-28 10:30:00 Context: TypeScript, React, REST API
Generated: 2026-01-28 10:30:00 Context: TypeScript, React, REST API

Code Quality (IEEE 1028)

Code Quality (IEEE 1028)

  • Code follows project style guide
  • No code duplication
  • Cyclomatic complexity < 10
  • Functions have single responsibility
  • Variable names clear and descriptive
  • Magic numbers replaced with constants
  • Dead code removed
  • Code follows project style guide
  • No code duplication
  • Cyclomatic complexity < 10
  • Functions have single responsibility
  • Variable names clear and descriptive
  • Magic numbers replaced with constants
  • Dead code removed

Testing (IEEE 1028)

Testing (IEEE 1028)

  • Tests written first (TDD)
  • All new code has tests
  • Tests cover edge cases
  • Test coverage ≥ 80%
  • Integration tests present
  • Tests isolated (no order dependency)
  • Tests written first (TDD)
  • All new code has tests
  • Tests cover edge cases
  • Test coverage ≥ 80%
  • Integration tests present
  • Tests isolated (no order dependency)

Security (IEEE 1028)

Security (IEEE 1028)

  • Input validation on all inputs
  • No SQL injection risks
  • No XSS vulnerabilities
  • Sensitive data encrypted
  • Auth/authz checks present
  • No hardcoded secrets
  • OWASP Top 10 reviewed
  • Input validation on all inputs
  • No SQL injection risks
  • No XSS vulnerabilities
  • Sensitive data encrypted
  • Auth/authz checks present
  • No hardcoded secrets
  • OWASP Top 10 reviewed

Performance (IEEE 1028)

Performance (IEEE 1028)

  • No performance bottlenecks
  • Database queries optimized
  • Caching used appropriately
  • Resource cleanup (connections)
  • No infinite loop risks
  • Large data paginated
  • No performance bottlenecks
  • Database queries optimized
  • Caching used appropriately
  • Resource cleanup (connections)
  • No infinite loop risks
  • Large data paginated

Documentation (IEEE 1028)

Documentation (IEEE 1028)

  • Public APIs documented
  • Complex logic has comments
  • README updated
  • CHANGELOG updated
  • Breaking changes documented
  • Public APIs documented
  • Complex logic has comments
  • README updated
  • CHANGELOG updated
  • Breaking changes documented

Error Handling (IEEE 1028)

Error Handling (IEEE 1028)

  • All errors handled
  • User-friendly error messages
  • Detailed logs for debugging
  • No swallowed exceptions
  • Graceful degradation
  • Rollback procedures
  • All errors handled
  • User-friendly error messages
  • Detailed logs for debugging
  • No swallowed exceptions
  • Graceful degradation
  • Rollback procedures

TypeScript (AI-Generated)

TypeScript (AI-GENERATED)

  • [AI-GENERATED] Types exported from modules
  • [AI-GENERATED] No 
    any
    types (justified if used)
  • [AI-GENERATED] Strict null checks satisfied
  • [AI-GENERATED] Interfaces prefer over types
  • [AI-GENERATED] Types exported from modules
  • [AI-GENERATED] No 
    any
    types (justified if used)
  • [AI-GENERATED] Strict null checks satisfied
  • [AI-GENERATED] Interfaces prefer over types

React (AI-GENERATED)

React (AI-GENERATED)

  • [AI-GENERATED] Components use React.memo appropriately
  • [AI-GENERATED] Hooks follow Rules of Hooks
  • [AI-GENERATED] No unnecessary re-renders
  • [AI-GENERATED] Keys on list items
  • [AI-GENERATED] Components use React.memo appropriately
  • [AI-GENERATED] Hooks follow Rules of Hooks
  • [AI-GENERATED] No unnecessary re-renders
  • [AI-GENERATED] Keys on list items

REST API (AI-GENERATED)

REST API (AI-GENERATED)

  • [AI-GENERATED] Rate limiting implemented
  • [AI-GENERATED] API versioning in URLs
  • [AI-GENERATED] Request/response validation
  • [AI-GENERATED] OpenAPI/Swagger updated
Total Items: 38 IEEE Base: 30 (79%) Contextual: 8 (21%)
undefined
  • [AI-GENERATED] Rate limiting implemented
  • [AI-GENERATED] API versioning in URLs
  • [AI-GENERATED] Request/response validation
  • [AI-GENERATED] OpenAPI/Swagger updated
Total Items: 38 IEEE Base: 30 (79%) Contextual: 8 (21%)
undefined

Best Practices

最佳实践

DO

建议

  • Start with IEEE 1028 base (universal quality)
  • Analyze project context before generating
  • Mark all LLM items with [AI-GENERATED]
  • Keep contextual items focused (10-20%)
  • Return actionable checklist (not generic advice)
  • 从IEEE 1028基础开始（通用质量标准）
  • 生成前先分析项目上下文
  • 所有LLM生成项标记[AI-GENERATED]
  • 上下文项保持聚焦（10-20%）
  • 返回可执行的检查清单（而非通用建议）

DON'T

不建议

  • Generate checklist without context analysis
  • Exceed 20% contextual items (dilutes IEEE base)
  • Forget [AI-GENERATED] prefix
  • Include items that can't be verified
  • Make checklist too long (>50 items)
  • 不进行上下文分析就生成检查清单
  • 上下文项占比超过20%（削弱IEEE基础的作用）
  • 忘记添加[AI-GENERATED]前缀
  • 包含无法验证的项
  • 检查清单过长（超过50项）

Iron Law

铁律

NO TASK COMPLETION WITHOUT CHECKLIST VALIDATION
Use 
verification-before-completion
skill to enforce this.
NO TASK COMPLETION WITHOUT CHECKLIST VALIDATION
使用
verification-before-completion
技能强制执行此规则。

Related Skills

相关技能

  • qa-workflow
    - Systematic QA validation with fix loops
  • verification-before-completion
    - Pre-completion gate
  • tdd
    - Test-driven development (testing checklist items)
  • security-architect
    - Security-specific validation
  • qa-workflow
    - 包含修复循环的系统化QA验证
  • verification-before-completion
    - 完成前关卡
  • tdd
    - 测试驱动开发（对应检查清单中的测试项）
  • security-architect
    - 安全特定验证

Assigned Agents

关联Agent

This skill is used by:
  • qa
    - Quality assurance validation
  • developer
    - Pre-completion checks
  • code-reviewer
    - Code review criteria
本技能由以下Agent使用：
  • qa
    - 质量保证验证
  • developer
    - 完成前检查
  • code-reviewer
    - 代码评审标准

Memory Protocol (MANDATORY)

内存协议（强制要求）

Before starting: Read 
.claude/context/memory/learnings.md
Check for:
  • Previously generated checklists
  • Project-specific quality patterns
  • Common quality issues in this codebase
After completing:
  • New checklist pattern → 
    .claude/context/memory/learnings.md
  • Quality issue found → 
    .claude/context/memory/issues.md
  • Context detection improvement → 
    .claude/context/memory/decisions.md
ASSUME INTERRUPTION: If it's not in memory, it didn't happen.
开始前： 读取
.claude/context/memory/learnings.md
检查以下内容：
  • 之前生成的检查清单
  • 项目特定的质量模式
  • 此代码库中常见的质量问题
完成后：
  • 新的检查清单模式 → 写入
    .claude/context/memory/learnings.md
  • 发现的质量问题 → 写入
    .claude/context/memory/issues.md
  • 上下文检测的改进 → 写入
    .claude/context/memory/decisions.md
假设会被中断：如果未存入内存，就视为未发生过。