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 13,201–13,224 of 15,941 skills
- Plugin DevThis skill should be used when creating extensions for Claude Code or OpenCode, including plugins, commands, agents, skills, and custom tools. Covers both platforms with format specifications, best practices, and the ai-eng-system build system.Votes: 0GitHub stars: 8
- Knowledge CaptureDocument solved problems to build cumulative team knowledge. Systematically capture solutions with context, code examples, gotchas, and related links. Use after completing workflows to ensure learnings compound for future team members.Votes: 0GitHub stars: 8
- Incremental ImplementationDelivers changes in thin vertical slices. Use when implementing any feature or refactor that touches more than one file or feels too large to land safely in one pass.Votes: 0GitHub stars: 8
- Content OptimizationEnhance any content type using research-backed techniques. Optimize AI prompts with step-by-step approval, improve code quality, refine database queries, enhance documentation, optimize commit messages, and improve communication. Wraps incentive-prompting skill with content-type detection.Votes: 0GitHub stars: 8
- Code Review And QualityConducts multi-axis code review. Use before merging any change. Use when reviewing code written by yourself, another agent, or a human.Votes: 0GitHub stars: 8
- SimplifyReview recently changed files for code reuse, quality, and efficiency issues, then fix them. Use when simplifying code, removing complexity, improving readability, or after making changes.Votes: 0GitHub stars: 8
- Ralph WiggumContinuous iteration loop pattern for well-defined tasks with clear completion criteria. Use when getting tests to pass, implementing features with automatic verification, bug fixing with clear success conditions, or running automated development overnight. Provides prompt templates, safety guidelines, and integration patterns for ai-eng-system workflows.Votes: 0GitHub stars: 8
- Workflow From ChatsExtract durable working preferences from recent Cursor chats and convert them into skills, rules, or workflow docs. Use when asked to learn preferences, mine feedback, personalize workflows, or generate team/person-specific agent guidance.Votes: 0GitHub stars: 8
- Weekly ReviewProduce a weekly synthesis of authored commits with highlights by bugfix, tech debt, and net-new workVotes: 0GitHub stars: 8
- Using Agent SkillsDiscovery and invocation of all skills, commands, and agents. Decision tree for task-to-skill mapping. Core operating behaviors for agents. Use when unsure which skill or agent to use.Votes: 0GitHub stars: 8
- Poteto Modepoteto's agent style for concise, detailed responses, deliberate subagents, unslopped prose, simple code, and verified work. Use for poteto, /poteto-mode, or requests to work in this style.Votes: 0GitHub stars: 8
- Plugin DevThis skill should be used when creating extensions for Claude Code or OpenCode, including plugins, commands, agents, skills, and custom tools. Covers both platforms with format specifications, best practices, and the ai-eng-system build system.Votes: 0GitHub stars: 8
- Knowledge CaptureDocument solved problems to build cumulative team knowledge. Systematically capture solutions with context, code examples, gotchas, and related links. Use after completing workflows to ensure learnings compound for future team members.Votes: 0GitHub stars: 8
- Incremental ImplementationDelivers changes in thin vertical slices. Use when implementing any feature or refactor that touches more than one file or feels too large to land safely in one pass.Votes: 0GitHub stars: 8
- Eval HarnessAgent evaluation framework. Measure agent performance, identify weaknesses, and track improvement over time. Use when assessing agent quality, comparing approaches, or validating changes.Votes: 0GitHub stars: 8
- Code Review And QualityConducts multi-axis code review. Use before merging any change. Use when reviewing code written by yourself, another agent, or a human.Votes: 0GitHub stars: 8
- SimplifyReview recently changed files for code reuse, quality, and efficiency issues, then fix them. Alias for code-simplification skill with multi-agent review additions.Votes: 0GitHub stars: 8
- Ie Validate PlanValidate a plan, spec, or requirements document against the four intent-engineering lenses before implementation — surfacing surprising designs, non-idiomatic or reinvented approaches, needless complexity/scope, and missing UX decisions (states, flows, IA, accessibility). Returns dimensional 0-10 ratings and the gaps to resolve first. Use when a plan or spec doc exists.Votes: 0GitHub stars: 3
- Code ReviewBranch code review with structured scoring against project guidelines. Produces categorized findings with severity levels and LLM-generated fix prompts. Quality gate: only posts review to PR if score meets threshold. Triggers on: "code review", "review branch", "review PR", "review changes", "score code"Votes: 0GitHub stars: 229
- Tone TokenDesign or refactor a design token architecture — naming, tiers, and coverage. Use when asked to "design a token architecture", "fix token naming", or "refactor our tokens".Votes: 0GitHub stars: 71
- Serv ColdDiagnose and optimize Lambda/serverless cold start performance. Use when asked to "fix Lambda cold starts", "our functions are slow to start", or "reduce cold start latency".Votes: 0GitHub stars: 71
- Queue DesignDesign a message queuing or streaming architecture for a workload. Use when asked "should we use Kafka or SQS", "design a queue architecture", or "design event streaming".Votes: 0GitHub stars: 71
- Multi ReconSurvey existing cloud architecture for lock-in depth and portability gaps. Use when asked to "survey our cloud lock-in", "find portability gaps", or "how cloud-agnostic are we".Votes: 0GitHub stars: 71
- Agent Skills Best PracticesAgent-skill design conventions for focused scope, precise discovery, and progressive disclosure. Use when creating, restructuring, or reviewing `SKILL.md`-based skills.Votes: 0GitHub stars: 12