Agent skills

Other 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
21,420 found
2,6892,736 · page 57 / 447
cli-table-formatterGenerate table formatters for structured CLI output with column alignment, borders, and responsive sizing.a5c-aiwritesclick-scaffolderGenerate Click-based Python CLI applications with decorators, groups, context, and modern Python patterns. Creates complete…a5c-aiwritesclient-explanation-translator-larissa-meredith-flisterTurn complex legal analysis into clear, commercially useful client-facing advice. Use this whenever the user has dense legal…lawve-aiclimate-scienceClimate physics, forcing, feedback, and attribution. Covers the greenhouse effect and radiative forcing, climate sensitivity…majiayu000clinical-decision-supportGenerate professional clinical decision support (CDS) documents for pharmaceutical and clinical research settings, including…majiayu000clinical-decision-supportGenerate professional clinical decision support (CDS) documents for pharmaceutical and clinical research settings, including…majiayu000writesclinical-research-pitfallsAvoid common methodological mistakes in clinical research with MIMIC-IV and eICU databases. Covers immortal time bias…majiayu000clinical-value研究案の臨床的価値を評価する。患者アウトカム改善への貢献度、臨床意思決定への影響、 ガイドライン・治療戦略変更の可能性を多角的に評価。majiayu000clonalstatsGenerate comprehensive clonality statistics and diversity visualizations for TCR/BCR repertoire analysis. Quantifies clonal…majiayu000cloud-cost-analysisMulti-cloud cost analysis and optimization expertise for FinOps practicesa5c-aiwritescloudflare-ai-searchCloudflare AI Search for semantic search and vector embeddings in Workersmajiayu000cloudflare-workers-aiProduction-ready knowledge domain for building AI-powered applications with Cloudflare Workers AI.majiayu000cloudkit-syncGenerate CloudKit sync infrastructure using CKSyncEngine with conflict resolution, sharing, and account monitoring. Use when…rshankraswritesbio-single-cell-clusteringDimensionality reduction and clustering for single-cell RNA-seq using Seurat (R) and Scanpy (Python). Use for running PCA…majiayu000clustermarkersofallcellsFinds marker genes for clusters of ALL cells before T/B cell selection. This process identifies differentially expressed genes…majiayu000clustermarkersFinds differentially expressed genes (markers) for clusters of T/B cells using Seurat's FindMarkers function. Performs…majiayu000co2-carbon-footprint-datadrivenconstructi-ddc-skills-for-ai-ag-2Calculate and track CO2 emissions and carbon footprint for construction projects.majiayu000co2-chunkingApply CO2 Chunking to group related elements into meaningful units to reduce cognitive load.majiayu000cobra-scaffolderGenerate Cobra/Viper-based Go CLI applications with persistent flags, subcommands, and configuration management. Creates…a5c-aiwritescobrapyConstraint-based metabolic modeling (COBRA). FBA, FVA, gene knockouts, flux sampling, SBML models, for systems biology and…majiayu000code-analysisCheck if code is readable by non-developers - clear names, plain English comments, no jargonmajiayu000code-analysisComprehensive code analysis guidelines for ACE Engine (OpenHarmony ArkUI) development.majiayu000code-analysis지정된 디렉토리 또는 파일을 분석하여 문제점, 모호한 점, 개선이 필요한 사항을 식별하고 각각을 GitHub 이슈로 등록합니다.majiayu000code-communitiesDetects architectural clusters and coupling boundaries via community detection on the code graph. Use when identifying module…majiayu000code-complexity-analyzerAnalyze code complexity metrics including cyclomatic complexity, code smells, and technical debta5c-aiwritescode-explorerUse when asked to trace existing codepaths or explicitly asked to run the code-explorer subagent.majiayu000code-flow-viz用于梳理和可视化代码流程,生成清晰的 ASCII 流程图、数据流图和表格分析。适用于已有代码的梳理、新功能设计的说明、以及技术文档的编写。majiayu000code-generationMinimal, pattern-matching code output. Write the least code that satisfies requirements. Match existing project patterns. Use…a5c-aiwritescode-profilerProfile code performance and identify bottlenecksa5c-aiwritescode-refactoring-tech-debtYou are a technical debt expert specializing in identifying, quantifying, and prioritizing technical debt in software projects.…majiayu000code-signing-setupConfigure code signing for macOS and Windows binaries with notarization.a5c-aiwritescode-simplifierSimplify and clean up code after changes are complete. Reduces complexity, improves readability, and ensures consistency.brycewang-stanfordcode-smell-detectorAutomated detection of code smells and anti-patterns to identify refactoring opportunitiesa5c-aiwritescode-statsAnalyze codebase with tokei (fast line counts by language) and difft (semantic AST-aware diffs). Get quick project overview…majiayu000writescode-summarizerGenerate concise summaries of source code at multiple scales. Use when users ask to summarize, explain, or understand code -…majiayu000code-surgeon-context-researcherUse when analyzing a codebase to select relevant files, build dependency maps, and extract architectural patterns for informed…majiayu000code-visualizerAuto-generates code flow diagrams from Python module analysis. Detects when architecture diagrams become stale (code changed…majiayu000codebase-analysisAnalyzes codebase to find similar features, reusable utilities, and architectural patternsmajiayu000writescodebase-analysisProduce a structured codebase analysis report with architecture overview, critical files, patterns, and actionable…majiayu000codebase-classificationClassify codebases before modification to choose appropriate development approachmajiayu000codebase-explainerAnalyse le code source du projet pour comprendre l'architecture, les patterns utilisés et le contexte technique. Utiliser après…majiayu000writescodebase-explorerDeep codebase exploration using semantic search and relationship mapping. Use when you need to understand the current codebase.majiayu000codebase-graph**CODEBASE GRAPH v1.0** - '의존성', '그래프', '코드베이스 분석', '함수 관계', '모듈 관계', '아키텍처 분석', 'import 분석' 요청 시 자동 발동. 프로젝트 시작 시 자동 생성. 온톨로지 기반…majiayu000writescodebase-locatorFind and document file locations in the codebase. Use when you need to locate implementation files, tests, configurations, or any…majiayu000codebase-locatorFind and document file locations in the codebase. Use this when you need to locate implementation files, tests, configurations…majiayu000codebaseDescobre melhorias e oportunidades de refatoração baseada em padrões existentes no código. Use quando quiser analisar o codebase…majiayu000writescodebase-mappingGenerate structured codebase maps with dependency graphs, file relationships, and architectural patterns. Use when exploring…majiayu000codebase-navigatorSemantic code search using osgrep for understanding codebases, finding implementations, and navigating large projects. Use when…majiayu000
← Prev57 / 447Next →
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