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 62,644codex 9,699cursor 6,852copilot 2,269windsurf 126cline 82
CategoryWorkflow & Productivity 11,684AI & Agents 4,965Data & Analytics 4,693Code Review & Quality 2,936Security 2,762Backend & API 2,480Design & Presentation 2,329Documentation 2,157Content & Marketing 2,001Testing & QA 1,723DevOps & Cloud 1,266Databases 1,124Frontend 1,015Business & Finance 706Media & Video 507Other 21,420
21,420 found
4,4654,512 · page 94 / 447
response-compressionEliminates response bloat including emojis, filler words, hedging language, hype, and unnecessary framing. Includes termination…majiayu000response-formatEnsure all AI responses are well-formatted, easy to understand, and actionable for the user.majiayu000responsibility-mapper作業の責任範囲を整理し、エージェント定義に必要な情報を抽出する。エージェント設計時、責任範囲整理時、またはユーザーが責任範囲、役割分担、責任境界、エージェント構成に言及した際に使用する。majiayu000restaurant-bookingBook restaurant reservations via browser automation. Use when asked to make dinner reservations, book a table, or find…gooseworks-airesult-integrator整合多情点分析结果为综合报告,通过去重、分类、排序、总结生成高质量分析。适用于整合多分析源、生成统一报告majiayu000synapse-result-schemasExplains result schema classes for Synapse plugin actions. Use when the user mentions "TrainResult", "InferenceResult"…majiayu000resumeResume a paused experiment. Checkout the experiment branch, read results history, continue iterating.majiayu000retention-analysisCohort analysis and retention optimization framework. Identifies retention drivers and churn factors.majiayu000retention-optimization-expertReduce churn and improve retention through cohort analysis, at-risk user identification, win-back campaigns, and customer success…majiayu000retrieval-judgeEvaluate and filter recall_search results for relevancemajiayu000Retrieval Playbook for AIกลยุทธ์การ retrieve context ให้ AI อย่างมีประสิทธิภาพ - เลือกอะไร ไม่เลือกอะไร และจัดลำดับอย่างไรmajiayu000retroAnalyze completed Linear cycles for retrospectives. Identifies velocity trends, scope creep, and patterns to improve future…majiayu000retroエージェントの振り返りを実行し、スキル化候補・サブエージェント増設提案・コンテキスト肥大化チェックをレポートするmajiayu000retrocausal-pullAttractor-based reasoning engine. The fixed point of IN(f) exerts pull on every iteration before it. Systems with bracket=1 don't…majiayu000retrospectAnalysis for a run and its results, process, suggestions for process improvements, process optimizations, fixes, etc. for the…majiayu000retrospectiveStructured retrospective after completing a delivery increment or diamond. Captures learning for continuous improvement.majiayu000reverse-engineering레거시 코드베이스 리버스 엔지니어링 워크플로우. 문서가 없는 프로젝트를 체계적으로 분석하여 아키텍처, 비즈니스 로직, 의존성을 파악합니다. Use when analyzing legacy code or understanding…majiayu000reverse-engineeringソフトウェアのリバースエンジニアリングレポートを作成するスキル。リポジトリの構造や機能を調査し、外部仕様・内部実装・使用方法を明確にするレポートを作成します。「リバースエンジニアリングレポートを作成して」「コードベースを分析して」「プロジェクトの構造を調査して…majiayu000reverse-engineering-toolkitUnderstand undocumented systems through static/dynamic analysis, dependency mapping, and pattern recognitionmajiayu000writesreverse-outlinerReverse-engineer published books into structured scene-by-scene outlines for study. Use when analyzing craft, learning story…majiayu000reversible-computingJanus and reversible languages: run programs backwards, time-symmetric computation.majiayu000rezk-typesRezk types (complete Segal spaces). Local univalence: categorical isomorphisms ≃ type-theoretic identities.majiayu000rfp-evaluateEvaluate RFP opportunities using the 6-dimension scoring framework. Use when modifying evaluation criteria, adjusting keyword…majiayu000rideAnalyze codebase to extract reality into Loa artifactsmajiayu000risk-analysisRisk analysis using risk registers, probability/impact matrices, and mitigation planning. Identifies, assesses, and manages…majiayu000risk-assessmentIdentify, analyze, and prioritize project risks using qualitative and quantitative methods. Develop mitigation strategies to…majiayu000Risk AssessorIdentify, analyze, and mitigate project risks using systematic risk management frameworksmajiayu000riskUnified risk engine with VaR, stress testing, volatility regimes, and automated controlsmajiayu000risk-metrics-calculationCalculate portfolio risk metrics including VaR, CVaR, Sharpe, Sortino, and drawdown analysis. Use when measuring portfolio risk…majiayu000risk-metrics-calculationCalculate portfolio risk metrics including VaR, CVaR, Sharpe, Sortino, and drawdown analysis. Use when measuring portfolio risk…majiayu000risk-metrics-calculationCalculate portfolio risk metrics including VaR, CVaR, Sharpe, Sortino, and drawdown analysis. Use when measuring portfolio risk…majiayu000risk-metrics-calculationCalculate portfolio risk metrics including VaR, CVaR, Sharpe, Sortino, and drawdown analysis. Use when measuring portfolio risk…majiayu000risk-metrics-calculationCalculate portfolio risk metrics including VaR, CVaR, Sharpe, Sortino, and drawdown analysis. Use when measuring portfolio risk…majiayu000risk-metrics-calculationCalculate portfolio risk metrics including VaR, CVaR, Sharpe, Sortino, and drawdown analysis. Use when measuring portfolio risk…majiayu000risk-metrics-calculationCalculate portfolio risk metrics including VaR, CVaR, Sharpe, Sortino, and drawdown analysis. Use when measuring portfolio risk…majiayu000risk-metrics-calculationCalculate portfolio risk metrics including VaR, CVaR, Sharpe, Sortino, and drawdown analysis. Use when measuring portfolio risk…sickn33risk-metrics-calculationCalculate portfolio risk metrics including VaR, CVaR, Sharpe, Sortino, and drawdown analysis. Use when measuring portfolio risk…majiayu000risk-metrics-calculationCalculate portfolio risk metrics including VaR, CVaR, Sharpe, Sortino, and drawdown analysis. Use when measuring portfolio risk…wshobsonrisk-portfolio-managerAI-powered portfolio risk management and optimization. Use when sizing positions, managing portfolio allocation, calculating risk…majiayu000risoA playful, joyful, two-color risograph print aesthetic built on a single warm off-white paper surface running through every…bergsiderlmRecursive Language Models (RLM) CLI - enables LLMs to recursively process large contexts by decomposing inputs and calling…majiayu000rlooReinforcement Learning with Leave-One-Out estimation for policy optimization. Covers RLOOTrainer, reward function integration…majiayu000Roadmap VisualizationGenerate roadmap visualizations and planning artifacts for product planninga5c-aiwritesroadrunner-import-sceneImport HD Map or OpenDRIVE files into a RoadRunner scene using MATLAB. Use when loading driving scenes in RoadRunner or…matlabroguelikeBuild a roguelike: turn-based grid movement, procedural dungeons, permadeath, field-of-view, and loot tables. Use for a…gamedev-skillsrole-infoКомпактная сводка прав роли 1С из Rights.xml — объекты, права, RLS, шаблоны ограничений. Используй для аудита прав — какие…majiayu000writesroleLoad specific role(s) for focused work. Use when user says "role [name]" or wants to work with specific roles. Supports single or…majiayu000role-software-engineerRole definition for software engineer agents. Defines responsibilities, principles, required skills, and success criteria. Use to…majiayu000
← Prev94 / 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