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 1,873–1,896 of 15,941 skills
- Angular DeveloperGenerates Angular code and provides architectural guidance. Trigger when creating projects, components, or services, or for best practices on reactivity (signals, linkedSignal, resource), forms, dependency injection, routing, SSR, accessibility (ARIA), animations, styling (component styles, Tailwind CSS), testing, or CLI tooling.Votes: 0GitHub stars: 36
- Alterlab TorchdrugBuilds PyTorch-native graph neural networks with TorchDrug for molecules and proteins, exposing custom GNN architectures, task/dataset abstractions, molecular generation, retrosynthesis planning, and knowledge-graph reasoning. Use when developing custom graph model layers, predicting protein properties from sequence or structure, or building retrosynthesis and drug-repurposing pipelines; for ready-made featurizers, MoleculeNet benchmarks, and pre-trained models with less code prefer alterlab-...Votes: 0GitHub stars: 36
- Alterlab Cdm PreproductionThis skill should be used when the user asks about "pre-production", "shot list", "storyboard", "shooting schedule", "call sheet", "script breakdown", "scene breakdown", "production planning", "act as a pre-production planner", "pre-production mode", "location scouting", "crew planning", "shooting day schedule", "camera setup list", or needs expertise in pre-production planning, shot design, script breakdowns, and shooting logistics. Part of the AlterLab FC Skills collection (Cinema & Digital...Votes: 0GitHub stars: 36
- Agent EvaluationUse when testing skills, commands, or agents for quality. Use after creating new skills, before deploying agents, or when debugging inconsistent agent behavior. Triggers on "evaluate", "test quality", "is this skill working", or QA of AI workflows.Votes: 0GitHub stars: 36
- Eloquent PatternsEloquent ORM best practices: query builders, scopes, relations, N+1 prevention, batch operations, soft deletes, model events, raw queries when needed. Apply when: writing or reviewing Eloquent queries and model interactions. Activated automatically by laravel-plugin/stack.md as a convention skill for the development phase.Votes: 0GitHub stars: 35
- 3380p Code Review评审 Chroma 3380P ATE 的 `.pln`、`.dec`、`.pat`、helper header 和生成的测试程序草稿，重点检查 bug、可维护性风险、cleanup 缺失、multi-site 处理缺失、无依据假设、测试或验证缺口。用于代码评审、检查清单评审、审计、质量门禁，以及根据重复反馈维护 3380P 评审检查清单。Votes: 0GitHub stars: 2
- N8n Mcp Tools ExpertExpert guide for using n8n-mcp MCP tools effectively. Use when searching for nodes, validating configurations, accessing templates, managing workflows, or using any n8n-mcp tool. Provides tool selection guidance, parameter formats, and common patterns.Votes: 0GitHub stars: 16
- Writing Beats写作·利用（exploit）：把原始素材组装成一段节拍（beat）之旅，在每个节拍依赖某个术语之前先把它讲透。Votes: 0GitHub stars: 2
- Retro对一次编码会话进行复盘（retrospective）。Votes: 0GitHub stars: 2
- Code Review沿两条轴线审查自某个固定点（提交、分支、标签或 merge-base）以来的变更——标准（代码是否遵循本仓库文档化的编码规范？）与规格（代码是否符合原始 issue/spec 的要求？）。两个审查由并行子代理执行并并排汇报。当用户想审查一个分支、PR、进行中的改动，或要求“自 X 起审查”（review since X）时使用。Votes: 0GitHub stars: 2
- Android Profiler管理 Android 性能剖析与调试。当用户要求录制或分析 Android 性能数据（如系统 trace、堆转储、方法录制、调用栈采样、内存分配），排查 Android 上的瓶颈、卡顿（jank）、内存泄漏、应用启动问题，或要求编写、调试、执行临时 SQL 查询时触发。适用于用户应用和系统应用/服务。Votes: 0GitHub stars: 2
- Posix Shell ProExpert in strict POSIX sh scripting for maximum portability across Unix-like systems. Specializes in shell scripts that run on any POSIX-compliant shell (dash, ash, sh, bash --posix).Votes: 0GitHub stars: 666
- Analyze ProjectForensic root cause analyzer for Antigravity sessions. Classifies scope deltas, rework patterns, root causes, hotspots, and auto-improves prompts/health.Votes: 0GitHub stars: 666
- Github Code ReviewComprehensive GitHub code review with AI-powered swarm coordinationVotes: 0GitHub stars: 812
- PacePACE 路由与 4 核心 + 5 条件 stage 全景。面包屑失效或需全景时 Read。Votes: 0GitHub stars: 188
- Athena ReviewPACE 实现后一次原生多维 review。进入 review stage 时触发。不要跑 critic/evaluator/spec-compliance。Votes: 0GitHub stars: 188
- RoadmapPACE 可选 stage。存在 ≥2 个可独立验收交付的切片，或用户明确要求拆分时触发。Votes: 0GitHub stars: 188
- PacePACE 路径、阶段、门禁与 athena CLI 的全景；分诊后要确定下一步、被门禁拦下、或恢复中断任务时读。Votes: 0GitHub stars: 188
- BrainstormPACE 最早的可选 stage。想法模糊、写不出验收标准时触发。一次一问 + 推荐答 + 先查库再问人。Votes: 0GitHub stars: 188
- RoadmapPACE 可选 stage。至少两个可独立验收交付切片或用户明确要求拆分时触发。Votes: 0GitHub stars: 188
- PolishPACE Refactor/System polish；runtime-verify 完成后、最终 review 前清理代码并更新架构。Votes: 0GitHub stars: 188
- PacePACE 路由与 4 核心 + 5 条件 stage 全景。面包屑失效或需全景时 Read。Votes: 0GitHub stars: 188
- BrainstormPACE 最早的可选 stage。想法模糊、写不出验收标准时触发。一次一问 + 推荐答 + 先查库再问人。Votes: 0GitHub stars: 188
- Athena Runtime Verifyimpl 之后的运行时验证环。System/Refactor 强制；需要实跑接口而非只跑单测时触发。Votes: 0GitHub stars: 188