agentsclimarketplace
Sign in

Quality

Skill xiaobei930/cc-best/skills/quality

Code quality assurance strategies. Parent skill for quality-related skills: security (security review) and debug (systematic debugging).From its SKILL.md

Install
npx -y skills add xiaobei930/cc-best --skill quality

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

SKILL.md

3.4 KB, ~1.0k tokens by cl100k_base, as published. Nobody here has run it

代码质量保障

关联 Agent: code-reviewer（代码质量审查）、code-simplifier（简化重构）、security-reviewer（安全与质量交叉）

本技能提供代码质量保障策略，整合安全审查和系统化调试方法。

质量保障维度

┌───────────────────────────────────────────────────────┐
│                  代码质量保障                          │
├──────────────┬──────────────┬─────────────────────────┤
│   安全性      │    可靠性     │     健康度              │
│   (/security) │    (/debug)  │   (code-health)        │
├──────────────┼──────────────┼─────────────────────────┤
│ • 认证授权   │ • 系统化调试 │ • 技术债务识别          │
│ • 输入验证   │ • 日志分析   │ • 量化优先级            │
│ • 密钥管理   │ • 性能诊断   │ • 热点文件检测          │
│ • API 安全   │ • 错误追踪   │ • 债务分类评估          │
└──────────────┴──────────────┴─────────────────────────┘

策略选择

场景推荐策略子技能
添加认证/授权功能安全审查/security
处理用户输入安全审查/security
创建 API 端点安全审查/security
调试代码问题系统化调试/debug
分析错误日志系统化调试/debug
排查性能问题系统化调试/debug
Sprint 规划评估健康评估code-health
重构决策分析健康评估code-health
技术债务盘点健康评估code-health

子技能

1. security（安全审查）

适用场景：

  • 认证授权实现
  • 用户输入处理
  • 密钥和敏感数据
  • API 端点设计

使用方式：/security 或参阅 skills/security/SKILL.md

2. debug（调试方法）

适用场景：

  • 代码问题调试
  • 错误日志分析
  • 性能问题诊断
  • 生产事故排查

使用方式：/debug 或参阅 skills/debug/SKILL.md

3. code-health（健康评估）

适用场景：

  • Sprint 规划时评估技术债务
  • 重构决策前分析热点文件
  • 代码复杂度趋势监控
  • 依赖健康状态检查

使用方式：参阅 skills/quality/code-health.md

质量检查清单

提交前必检

  • 无硬编码密钥/密码
  • 用户输入已验证/转义
  • 错误处理完善
  • 日志不泄露敏感信息
  • 测试覆盖关键路径

定期审查

  • 依赖安全更新
  • 权限最小化原则
  • 日志和监控完善
  • 错误处理一致性

记住：安全和可靠性不是事后补救，而是设计阶段就要考虑的核心需求。

What ships with it: 1 file

4.6 KB alongside SKILL.md

Gives 0 of the 12 instructions most debug triage skills give in ~1.0k tokens

Counted across 1,020 of the 1,639 authors here whose files we hold, read 2026-09-06

  • Find root cause before attempting any fixin 134 of 1020, across 118 files
  • Create a failing test case before implementing a fixin 109 of 1020, across 95 files
  • Read error messages and stack traces completelyin 102 of 1020, across 88 files
  • Reproduce the issue consistently before investigatingin 90 of 1020, across 77 files
  • Make the smallest possible change to test a hypothesisin 90 of 1020, across 76 files
  • Trace data flow backward to find the sourcein 84 of 1020, across 70 files
  • Form a single hypothesis before testingin 78 of 1020, across 64 files
  • Implement only one fix at a timein 76 of 1020, across 63 files
  • Question the architecture if three fixes failin 73 of 1020, across 59 files
  • Add diagnostic instrumentation at component boundariesin 68 of 1020, across 56 files
  • Compare broken code against working examplesin 68 of 1020, across 57 files
  • Write a regression test before applying the fixin 62 of 1020, across 55 files

Said here and by no other author read

  • validate all user inputs
  • sanitize all user inputs
  • remove hardcoded secrets
  • implement robust error handling
  • ensure logs do not leak sensitive data
  • verify test coverage for critical paths

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.