All categories
Code Review & Quality
Code review, refactoring, debugging, maintainability, and engineering quality
- 15,941
- 665
Security grades appear on each card once the skill has been scanned. Newly imported skills may briefly show without a grade until the backfill job runs.
Open in full browserBrowse code review & quality skills
Showing 1,993–2,016 of 15,941 skills
- ArchitectureCreate or evaluate an architecture decision record (ADR). Use when choosingVotes: 0GitHub stars: 3
- Code Reviewer Software EngineeringExpert code review methodology with structured checklists, severity classification, actionable feedback patterns, and language-specific anti-pattern detection. Use when the user asks about code reviewer, code reviewer best practices, or needs guidance on code reviewer implementation. Do NOT use when the user needs a different specialized skill or is asking about an unrelated technology domain.Votes: 0GitHub stars: 10
- Linting Workflow SkillLint execution workflow — detect configs, run linters, auto-fix, resolve errors across languages. Triggers: lint, auto-fix lint. Per-language rules and configs: language-linting-skill; executor agent: linting-subagent. Gate sequence and pass semantics: verification-loop-skill.Votes: 0GitHub stars: 6
- Eval Harness SkillEvaluate code quality, skill effectiveness, and implementation correctness against defined criteria with scoring and improvement suggestionsVotes: 0GitHub stars: 6
- Complexity Management SkillKISS/YAGNI/DRY tradeoff heuristics for minimizing accidental complexity. Triggers: complexity, accidental complexity. Not for smell detection (code-smells-skill), over-engineering audit (civiltekk-ponytail-audit-skill), or SOLID reference (solid-principles-skill).Votes: 0GitHub stars: 6
- Code Smells SkillDetect and fix code smells including long methods, large classes, feature envy, primitive obsession, and more with refactoring guidance - language-agnosticVotes: 0GitHub stars: 6
- Clean Code SkillWrite clean, human-readable code with proper naming, small functions, self-documenting patterns, and object calisthenics - language-agnosticVotes: 0GitHub stars: 6
- Agent Introspection Debugging SkillDebug why agents or skills aren't working as expected with systematic diagnosis, configuration validation, and fix recommendationsVotes: 0GitHub stars: 6
- PonytailYou are a lazy senior developer. Lazy means efficient, not careless. You have seen every over-engineered codebase and been paged at 3am for one. The best code is the code never written.Votes: 0GitHub stars: 6
- How ToChief has multiple skills that serve different purposes. Use this guide to find the right one quickly. ---Votes: 0GitHub stars: 66
- Task Dispatch把编码 / 开发任务拆成多个独立子任务，并行分派子 agent 执行，主 agent 负责合并集成。触发："并行开发"、"拆分子任务并行执行"、"多个子 agent 同时做"，或多模块功能、多个独立 bug、多个模块重构。Votes: 0GitHub stars: 2
- Strong Relation识别并判定跨文件的强关联关系（契约 / 业务耦合）：本 skill 只负责识别与判定方向，写 ki 下沉 ki-memory-write，查询走 ki-memory-lookup。触发："记录强关联"、"模块间强耦合"、"改A要连带改B"，或 expert-team 产出专家资产后自动调用。Votes: 0GitHub stars: 2
- Ki Search First项目记忆优先（口诀：遇事不决 ki-search）：任何任务先查项目记忆，无结果或记忆不充分时再走专家团（expert-lookup）与解决方案（solution-lookup）；已定位/已改代码时必查强关联。触发：任何任务开始前自动触发，或用户说"查记忆"、"改A要连带改B吗"。Votes: 0GitHub stars: 2
- Ki Memory Lookup查询 ki-search 记忆的 SSOT：封装查 ki 的公共动作（可用性检测、scope 确定、符号提准、降级不阻塞），按记忆类型分发到专题、接口、数据流、强关联、决策、错误库、待生效变更各参考策略。触发："查记忆"、"查强关联"、"这个模块牵动哪些"、"改A要连带改B吗"、"当初为什么这么定"、"这个报错见过吗"、"ki memory lookup"。Votes: 0GitHub stars: 2
- Debug系统化排错：以运行时证据走"复现 → 假设 → 验证 → 定位 → 修复 → 回归"闭环，排查报错、测试失败、行为异常。触发："排查这个 bug"、"debug 一下"、"为什么会报错"、"定位一下问题"、"这个测试为什么挂了"，或被 api-testing / e2e-testing / demo-verify 转交定位根因。Votes: 0GitHub stars: 2
- Code Review多语言代码多维度专业 Code Review：以语义一致性为核心，覆盖安全、Bug 风险、规范、架构、性能、测试覆盖，输出分级问题清单。触发："review 这个提交"、"code review"、"检查这段代码"，或提供 git diff / commit hash 时。Votes: 0GitHub stars: 2
- Challenger质疑者：专找评审可能遗漏的问题，对代码变更、设计文档、分析/审查报告做二次质疑。触发："质疑这个修复/设计/方案"、"二次审查"，或被 review-panel、auto-review、code-review、bug-impact-analysis 接力调用。Votes: 0GitHub stars: 2
- Acceptance Verify对整体功能或完整模块做交付前验收：以用户确认过的验收指标清单逐条核验（已有测试套件 + 临时场景测试 + e2e 真实链路三层证据），只判定不改产品代码，产出锚定分支与 commit 的验收报告，支持复验。仅用户明确指定时触发（"验收这个功能/模块"、"做验收"、"验收测试 / acceptance test"、"复验"）；只问"流程跑通没有"用 e2e-testing。Votes: 0GitHub stars: 2
- GitGit 操作ルール（コミット作成、メッセージ形式、事前チェック）Votes: 0GitHub stars: 20
- Pr Review CommentsAddress PR review comments. Use when the user says \"check comments\", \"address comments\", \"fix PR feedback\", or similar.Votes: 0GitHub stars: 33
- E2eWrite and run Playwright e2e tests in ayunis-core-e2e. Use when writing, running, or debugging browser tests; when a browser journey or system boundary changes and lower-level tests do not sufficiently prove it; or when the High-Risk Path affects user-facing behavior. Not automatic for copy, isolated visual-only work, or behavior already proven at a lower layer.Votes: 0GitHub stars: 33
- Code ReviewSelf-review local changes before creating a PR. Use when the user says "review", "review my code", "check my changes", or wants confidence before submitting.Votes: 0GitHub stars: 33
- Backend DebuggingDebug backend runtime errors (500s, crashes, unexpected behavior). Use when something is broken at runtime — not for writing new code.Votes: 0GitHub stars: 33
- 40 Parallel DispatcherSkill especializada em paralelizar trabalho via subagents corretamente — sem cair na armadilha skill-vs-agent. Use quando precisar despachar N slices verticais, N reviews, ou N tarefas independentes em paralelo, e quando reviewers/agentes paralelos discordam sobre o mesmo achado e a decisão de arbitrar/bloquear precisa de um critério formal. Trigger em: "paralelize", "N slices", "dispatch paralelo", "worktree paralelo", "5 workers", "dispatch em paralelo", "fan-out", "scatter-gather", "compre...Votes: 0GitHub stars: 23