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
529576 · page 12 / 62
stata-lintRun static analysis on a Stata .do or .ado file and report style and best-practice issues.brycewang-stanfordswiftui-gesturesImplement, review, or improve SwiftUI gesture handling. Use when adding tap, long press, drag, magnify, or rotate gestures…dpearson2699swiftui-liquid-glassImplement, review, or improve SwiftUI Liquid Glass effects for iOS 26+. Covers glassEffect modifier, GlassEffectContainer, glass…dpearson2699swiftui-liquid-glassImplement or review SwiftUI Liquid Glass APIs with correct fallbacks and modifier order.sickn33triageTriage issues through a state machine driven by triage roles. Use when user wants to create an issue, triage issues, review…stevesolunutility-pm-workflow-builderGuides a contributor from a workflow idea to a complete Workflow Implementation Packet (draft workflow file, draft workflow…product-on-purposevercel-common-errorsDiagnose and fix common Vercel deployment and function errors. Use when encountering Vercel errors, debugging failed deployments…jeremylongshorevercel-known-pitfallsIdentify and avoid Vercel anti-patterns and common integration mistakes. Use when reviewing Vercel code for issues, onboarding…jeremylongshorevisualizeCreate publication-quality figures that meet journal submission standards. APA 7th defaults with journal-specific overrides.…brycewang-stanfordwidgetkitImplement, review, or improve WidgetKit widgets and controls. Use when building Home Screen, Lock Screen, StandBy, or CarPlay…dpearson2699docx-processing-superdocEdit, query, and transform Word documents with the SuperDoc CLI v1 operation surface. Use when the user asks to read, search…lawve-ai00-build-evaluation-skillCreate a reusable skill for evaluating fine-tuned models, benchmarking performance, and detecting quality regressionsmajiayu000literature-review帮助用户撰写高质量的文献综述类论文。提供从选题、文献检索、评估筛选、结构规划到最终写作的全流程指导。适用于需要撰写独立文献综述论文或学术论文中文献综述部分的用户。brycewang-stanfordfive-whysRoot cause analysis for software bugs using the 5 Whys technique. Use when the user wants to find the underlying cause of a bug…majiayu000academic-researchSystematic academic literature search with source prioritization and APA 7th edition citations. Use when the user needs to…majiayu000acm-observabilityAgent-actionable reference for ACM-AI's 6-tool observability stack. Teaches how to query traces, inspect graph state, debug…majiayu000advanced-elicitationUse when you want to improve response quality through meta-cognitive reasoning. Applies 15+ reasoning methods to reconsider and…majiayu000advanced-evaluationThis skill should be used when the user asks to "implement LLM-as-judge", "compare model outputs", "create evaluation rubrics"…majiayu000advanced-evaluationThis skill should be used when the user asks to "implement LLM-as-judge", "compare model outputs", "create evaluation rubrics"…majiayu000advanced-evaluationMaster LLM-as-a-Judge evaluation techniques including direct scoring, pairwise comparison, rubric generation, and bias…majiayu000advanced-evaluationThis skill should be used when the user asks to "implement LLM-as-judge", "compare model outputs", "create evaluation rubrics"…majiayu000adversarial-reviewFresh adversarial code review with binary PASS/FAIL verdicts, evidence citations, and anchoring bias prevention via fresh…a5c-aiwritesafter-action-reportRun a structured after-action review (postmortem, retrospective) on a launch, incident, or completed project to capture timeline…rampstackcoagent-creatorCreates specialized AI agents with optimized system prompts using the official 4-phase SOP methodology from Desktop .claude-flow…majiayu000agent-creatorCreate production-grade agent .md files aligned with the Anthropic 2026 spec (16-field schema). Also validates existing agents…jeremylongshorewritesagent-cross-reviewStructured cross-review protocol between specialized agents. Ensures scope alignment, priority calibration, and domain-aware…majiayu000agent-curatorDeep curation of a single agent definition through structured human conversation. Coordinates knowledge research, persona…majiayu000agent-customizationCreate, update, review, fix, or debug VS Code agent customization files (.instructions.md, .prompt.md, .agent.md, SKILL.md…majiayu000agent-debuggingDebug and troubleshoot ElevenLabs conversational AI agents and Twilio calls. Use when diagnosing agent issues, analyzing failed…majiayu000writesagent-evalsDesign and implement evaluation frameworks for AI agents. Use when testing agent reasoning quality, building graders, doing error…majiayu000agent-init-deepInitialize or migrate to nested CLAUDE.md structure for progressive disclosure. Claude auto-loads CLAUDE.md from any directory it…majiayu000agent-md-refactorRefactor bloated AGENTS.md, CLAUDE.md, or similar agent instruction files to follow progressive disclosure principles. Splits…softaworksagent-output-formatsStandardized output formats for research, planning, implementation, and review agents. Use when generating agent outputs or…majiayu000Agent Reasoning & Decision-MakingDesign effective reasoning processes for AI agents and optimize decision-making strategies. Use when designing agent prompts…majiayu000agent-sdk-developmentCentral authority for Claude Agent SDK (TypeScript and Python SDKs). Covers SDK installation, authentication (Anthropic key…majiayu000agent-tuningOptimize ElevenLabs conversational AI agents for real estate applications. Use when creating new agents, improving conversation…majiayu000writesagents-md-proCreate, optimize, update, and validate AGENTS.md files with maximum token efficiency. Use when the user asks to (1) create new…majiayu000agentskill-expertiseAgent Skill design knowledge base — mechanisms, philosophy, patterns, pitfalls. Use when: designing new skills, reviewing skill…majiayu000agentv-eval-analyzerAnalyze evaluation results for quality improvements — identify LLM-judge evaluators replaceable with deterministic assertions…majiayu000ai-evaluation-suiteComprehensive AI/LLM evaluation toolkit for production AI systems. Covers LLM output quality, prompt engineering, RAG evaluation…majiayu000writesai-legal-opsPlant KI-Einsatz mit Datenklassen, Freigaben, Human Review und Wirtschaftlichkeit. Für Managing Partner, Management Committee…majiayu000alibaba-wan-videoPlan, implement, and review Alibaba Wan video generation using Alibaba Cloud Model Studio/DashScope hosted APIs or official Wan…calesthiobio-alignment-filteringFilter alignments by flags, mapping quality, and regions using samtools view and pysam. Use when extracting specific reads…majiayu000bio-alignment-statisticsCalculate alignment statistics including sequence identity, conservation scores, substitution matrices, and similarity metrics.…majiayu000bio-microbiome-amplicon-processingAmplicon sequence variant (ASV) inference from 16S rRNA or ITS amplicon sequencing using DADA2. Covers quality filtering, error…majiayu000bio-microbiome-amplicon-processingAmplicon sequence variant (ASV) inference from 16S rRNA or ITS amplicon sequencing using DADA2. Covers quality filtering, error…majiayu000analyseInvestigate codebase, debug issues, or analyze patternsmajiayu000writesanalysis-swarmMulti-persona analytical framework for comprehensive code review and decision-makingmajiayu000
← Prev12 / 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