Agent skills

Code Review & Quality skills

Read straight from the source repositories, not from submitted listings. Every skill shows what it does, what is inside, where it came from — and whether attention around its source is actually growing.

Toolclaude-code 29,140codex 4,755cursor 3,111copilot 976windsurf 55cline 34
CategoryWorkflow & Productivity 4,979AI & Agents 3,037Data & Analytics 2,345Code Review & Quality 1,376Backend & API 1,244Security 1,194Design & Presentation 1,154Documentation 965Content & Marketing 916Testing & QA 777DevOps & Cloud 576Databases 550Frontend 469Business & Finance 328Media & Video 257Other 9,833
2,936 found
9611,008 · page 21 / 62
m365-agents-tsMicrosoft 365 Agents SDK for TypeScript/Node.js. Build multichannel agents for Teams/M365/Copilot Studio with AgentApplication…majiayu000m365-agents-tsMicrosoft 365 Agents SDK for TypeScript/Node.js.majiayu000macos-menubar-tuist-appBuild, refactor, or review SwiftUI macOS menubar apps that use Tuist.sickn33magic-model-reviewEvaluates Magic Model (Triangle) frameworks for BlackBelt coaches using Ed Dale's frameworks. Produces Facebook-ready feedback…majiayu000writesmaintainx-debug-bundleComprehensive debugging toolkit for MaintainX integrations. Use when experiencing complex issues, need detailed logging, or…jeremylongshorewritesmanim-animation-makerCreate educational explainer videos with a Manim plus FFmpeg workflow. Use when the user asks for Manim animation…mingchen666markdown-mdxAdvanced Markdown and MDX processing for technical documentation. Parse, validate, lint, and transform Markdown content with…a5c-aiwritesmarket-news-analystThis skill should be used when analyzing recent market-moving news events and their impact on equity markets and commodities. Use…majiayu000mastraYou are an expert in Mastra, the TypeScript framework for building AI agents, RAG pipelines, and workflows. You help developers…majiayu000math-reviewVerify math-heavy code for correctness and numerical stability.majiayu000matlab-review-codeReview MATLAB code for quality, performance, maintainability, and adherence to MathWorks coding standards. Uses check_matlab_code…matlabmatlab-review-fi-codeReviews MATLAB fixed-point (fi) code for performance, code generation efficiency, and correctness. Identifies antipatterns and…matlabmeasuring-mutation-resistanceUse when measuring mutation resistance is required during quality work, especially when the result must be traceable…casioreview20-glitchmedia-crawler-bilibiliCollect Bilibili video and creator evidence with MediaCrawler through search, exact BV detail, comments, dynamics, contacts, and…tsingyuaimeta-analysis-forest-plotterUse when creating forest plots for meta-analyses, visualizing effect sizes across studies, or generating publication-ready…majiayu000writesmeta-protocol-writerGenerates a PROSPERO-compliant Meta-analysis protocol based on Title and PICOS. Use when the user wants to write a protocol for a…majiayu000metacognitive-self-modAnalyze and improve the improvement process. Use for detecting quality regressions and refining meta-optimization.majiayu000mistral-common-errorsDiagnose and fix Mistral AI common errors and exceptions. Use when encountering Mistral errors, debugging failed requests, or…majiayu000mittelstand-ma-tabellenreviewKanzlei prüft Dokumente Tabellen Formeln und Datenpunkte für Corporate/M&A mit interner Review-Matrix aus drei Perspektiven…majiayu000moai-foundation-philosopherStrategic thinking framework integrating First Principles Analysis, Stanford Design Thinking, and MIT Systems Engineering for…majiayu000model-debuggingDebug and diagnose model errors in Pollinations services. Analyze logs, find error patterns, identify affected users. For taking…majiayu000model-profile-resolutionResolve model profile (quality/balanced/budget) at orchestration start and map agents to specific models. Enables cost/quality…a5c-aimodelModel selection strategy and routing. Use when choosing between models for different task types, subagent configurations, or…majiayu000modular-design-principlesTechnology-agnostic guidance for modular systems: bounded contexts, clear boundaries, composability, state isolation, explicit…tech-leads-clubmoonshot-classify-taskClassifies a user request into task types (feature, modification, bugfix, refactor) and extracts intent keywords. Use at the…majiayu000multi-llm-advisorFetches additional perspectives from OpenAI Codex and Google Gemini for architecture, review, and debugging. Transparently…majiayu000multi-llm-advisorFetches additional perspectives from OpenAI Codex and Google Gemini for architecture, review, and debugging. Transparently…majiayu000multi-queryUse when search queries need better recall through query expansion - generates multiple query variants, retrieves with each, and…majiayu000multi-reviewer-patternsCoordinate parallel code reviews across multiple quality dimensions with finding deduplication, severity calibration, and…wshobsonmusic-supervision-scoringProvider-independent music supervision and scoring direction for AI agents producing generated videos, ads, trailers, explainers…calesthionamed-persona-adversarial-reviewCode review through the lens of real engineers' documented philosophies (Torvalds, Thompson, Carmack, Kent Beck, Jobs, Cagan).…alirezarezvaninansen-holder-analysisIs this token held by quality wallets or retail noise? SM holder ratio, flow breakdown by label, and recent buyer quality.internet-courtnda-analyserAnalyse a Non-Disclosure Agreement (NDA) and flag key terms, unusual provisions, and negotiation points. Use when asked to review…majiayu000network-exam-practiceUse this skill whenever the user wants computer network exam preparation, final review, 408-style networking practice, chapter…mingchen666network-performanceExpert skill for network performance analysis and optimization. Analyze packet captures, identify network latency bottlenecks…a5c-aiwritesnfr-reviewReview an existing HLD against NFR reference and generate gap reportmajiayu000nla-arbitrateManually arbitrate NLA escrow fulfillments as an alternative to the automated oracle. Use when the user wants to review pending…internet-courtnodejs-profilingExpert skill for Node.js-specific profiling and optimization. Use V8 CPU profiler, analyze heap snapshots, configure clinic.js…a5c-aiwritesnovel-evaluatorRigorously and meticulously evaluate and score story text, analyzing quality from market potential, innovation attributes, and…majiayu000nw-research-methodologyResearch output templates, distillation workflow, and quality standards for evidence-driven researchmajiayu000observability-analyze-logsParses OpenTelemetry-formatted logs to reconstruct execution traces, extract errors with call chains, and provide AI-powered root…majiayu000writesobsidian-debug-bundleCollect Obsidian plugin debug evidence for support and troubleshooting. Use when encountering persistent issues, preparing bug…jeremylongshorewritesobsidian-observabilityImplement structured logging, metrics, error tracking, and a debug panel for Obsidian plugins. Use when adding debug logging…jeremylongshorewritesobsidian-prod-checklistPre-release plugin verification checklist for Obsidian community plugins. Use when preparing to release, reviewing before…jeremylongshoreoclif-scaffolderGenerate oclif CLI framework projects with plugin support, topics, hooks, and TypeScript. Creates enterprise-grade CLI…a5c-aiwritesoffer-claims-registryUse when the user asks to "register this claim", "log our current offers", or "where is the proof for this figure"; curates claim…aaron-he-zhuoffer-diamond-reviewEvaluates Offer Diamonds for BlackBelt coaches using Ed Dale's frameworks. Produces Facebook-ready feedback comments.majiayu000writeson-call-handoff-patternsMaster on-call shift handoffs with context transfer, escalation procedures, and documentation. Use this skill when transitioning…wshobson
← Prev21 / 62Next →
How the catalog works
What is an agent skill?

A folder with a SKILL.md inside — instructions, and often scripts and assets, that an AI agent loads when the task matches. Claude Code, Codex, Cursor and Copilot all read the same format, so one skill usually works across them.

Where does this catalog come from?

We read 660 source repositories straight from their file trees rather than from submitted listings — what you see is what is actually published. 98 repositories were rejected because they advertise skills but contain none: link lists, not folders.

Why is there no install counter?

Because install counts live in the registry that serves `npx skills add`, and that is not ours — publishing a number we cannot verify would be worse than showing none. Instead we show where a skill comes from and whether attention around its source is actually growing, measured from our own weekly snapshots.

Do you deduplicate?

Yes, and it matters more than expected. Aggregator repositories republish the same skill in several places — one source carried 6,317 SKILL.md files for 2,001 actual skills. We collapse by folder name and keep the canonical copy, so the catalog counts things, not copies.

Keep going