All categories
Code Review & Quality
Code review, refactoring, debugging, maintainability, and engineering quality
- 15,936
- 664
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 13,561–13,584 of 15,936 skills
- Structured Output EnforcementEnforces deterministic agent output using JSON Schema, Pydantic models, and LLM-native format constraints to guarantee downstream consumers receive valid structured data.Votes: 0GitHub stars: 4
- Stripe AutomationImplements intelligent stripe automation with multi-factor skill selection,Votes: 0GitHub stars: 4
- Skill EngineeringDesigns high-fidelity OpenCode AI skills with precision trigger engineering,Votes: 0GitHub stars: 4
- Skill Documentation Best PracticesWrites high-fidelity SKILL.md documentation using instruction engineering patterns, typed code examples with BAD vs GOOD comparisons, and enforceable constraint design for AI agent skill systems.Votes: 0GitHub stars: 4
- Skill CompositionComposes multiple specialized skills into coherent workflows using sequentialVotes: 0GitHub stars: 4
- Requesting Code ReviewImplements intelligent requesting code review with multi-factor skillVotes: 0GitHub stars: 4
- Receiving Code ReviewImplements intelligent receiving code review with multi-factor skillVotes: 0GitHub stars: 4
- Prompt Engineering PatternsImplements advanced prompt engineering patterns (chain-of-thought, few-shot, ReAct, self-consistency, structured output) for crafting high-quality system prompts and agent instructions that reduce hallucination and improve task completion rates.Votes: 0GitHub stars: 4
- Pr WriterImplements intelligent pr writer with multi-factor skill selection, fallbackVotes: 0GitHub stars: 4
- Make Workflow AutomationBuilds and debugs automated workflows in Make (Integromat) using modules,Votes: 0GitHub stars: 4
- Iterate PrImplements intelligent iterate pr with multi-factor skill selection,Votes: 0GitHub stars: 4
- Git Pr Workflows Pr EnhanceImplements intelligent git pr workflows pr enhance with multi-factorVotes: 0GitHub stars: 4
- Exception Handling RecoveryImplements agent resilience patterns including retry logic with exponential backoff, fallback handler chains, state rollback, graceful degradation, and error escalation to maintain reliability under failure conditions.Votes: 0GitHub stars: 4
- Diff Quality AnalyzerImplements intelligent diff quality analyzer with multi-factor skillVotes: 0GitHub stars: 4
- Developer Pattern LibraryCurates and maintains a personal library of validated code patterns,Votes: 0GitHub stars: 4
- Coding Agent FrameworksImplements autonomous coding agent frameworks (automated refactoring, test generation, deployment pipeline management) for AI-augmented software development with 30%+ code generation targets.Votes: 0GitHub stars: 4
- Chroma ToolingImplements advanced tooling strategies for integrating Chroma libraries into AI/LLM workflows, covering collections, embeddings, queries, and persistence mechanisms.Votes: 0GitHub stars: 4
- Autonomous Coding LifecycleManages the complete autonomous coding lifecycle from code generation through self-review, test validation, failure repair, and deployment with state-machine orchestration.Votes: 0GitHub stars: 4
- ThermosLaunch both thermo-nuclear review subagents in parallel, then synthesize their findings. Use for thermos, double thermo review, or combined bug/security and code-quality branch audits.Votes: 0GitHub stars: 9,086
- Pr Review CanvasRender a PR diff review as a Cursor Canvas that groups changes by reviewer importance, separates boilerplate from core logic, and highlights tricky or unexpected code. Use when reviewing a pull request, summarizing a diff for review, or when the user asks for a PR review canvas, diff walkthrough, or change-set overview.Votes: 0GitHub stars: 9,086
- AdvisorAdvisor mode. Consult a stronger (or different) model at key checkpoints: before major decisions, when stuck on an error, and before declaring a task done. Use when the user types /advisor, asks to turn the advisor on or off, picks an advisor model, or explicitly asks for a second opinion from a stronger or different model. Never enable it on your own.Votes: 0GitHub stars: 9,086
- Pr ShepherdShepherd an existing PR through CI and review comments, then mark ready for review when clean. At activation, announce the skill name and scope in one line. Example: `[pr-shepherd] shepherding PR #97`. See `.skills/review-anti-patterns.md` for the shared rule set.Votes: 0GitHub stars: 37
- GptDelegate a task to OpenAI Codex through the Quest CLI runner from Claude-led sessions. Use when the user invokes /gpt, asks to use codex, or wants a second opinion from a different model.Votes: 0GitHub stars: 37
- CelebratePlay a quest completion celebration animation. Use when the user invokes /celebrate, asks to celebrate a quest, or when a quest reaches the complete/archived state.Votes: 0GitHub stars: 37