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
2,2572,304 · page 48 / 447
aget-studyupResearch a topic across the knowledge base before implementation. Searches L-docs, patterns, PROJECT_PLANs, SOPs, and governance…majiayu000aget-wind-downEnd AGET session with state capture and sanity checksmajiayu000writesaggregating-crypto-newsAggregate breaking cryptocurrency news from 50+ sources including CoinDesk, CoinTelegraph, The Block, and Decrypt. Use when…majiayu000agi-autonomous-controllerAGI-level autonomous controller — self-healing, self-optimizing, constitutionally governed by arifOS F1-F13majiayu000ai-analyzerAI驱动的综合健康分析系统,整合多维度健康数据、识别异常模式、预测健康风险、提供个性化建议。支持智能问答和AI健康报告生成。majiayu000writesai-analyzerAI驱动的综合健康分析系统,整合多维度健康数据、识别异常模式、预测健康风险、提供个性化建议。支持智能问答和AI健康报告生成。majiayu000writesai-assistantsAI-powered development tools configuration and usagemajiayu000ai-assisted-operationsAI-powered issue operations via gh-models. TRIGGERS - issue summarization, auto-labeling, issue insights.majiayu000ai-coachingMulti-turn conversational AI for intent extraction, clarification, and generation readiness detection. Guides users through…majiayu000ai-collaboration-standards-asiaostrich-universal-dev-standa-2Prevent AI hallucination and ensure evidence-based responses when analyzing code or making suggestions. Use when: analyzing code…majiayu000ai-daily-digestDaily AI news digest covering technical advances, business news, and engineering impact. Aggregates from research papers, tech…majiayu000writesAI辅助医生诊断扮演人工智能辅助医生,结合最新AI工具(如医学成像、机器学习)和传统方法(如体检、实验室测试)来诊断病人症状的最可能原因。majiayu000ai-ethicsResponsible AI development and ethical considerations. Use when evaluating AI bias, implementing fairness measures, conducting…majiayu000Ai Ethics ComplianceAI Ethics and Compliance involve building systems that are not only technically proficient but also socially responsible and…majiayu000ai-explainUse when explaining code, concepts, patterns, or architecture: engineer-grade technical explanations with 3-tier depth control…majiayu000ai-feedback-loop-optimizerAIフィードバックループ最適化スキル。プロンプト→出力→評価→改善の反復サイクルを自動化。段階的改善、A/Bテスト、収束判定、ベスト出力選択で最高品質の結果を生成。majiayu000ai-handlerIntegrate Replicate AI models with background processing, S3 storage, and credit systemsmajiayu000AI Integration ExpertWork with Leavn AI features - UnifiedAIService, on-device models, devotional generation, novelization, kids mode, image…majiayu000writesaiCheat sheet for AI tools including GEMINI and CODEX configurations.majiayu000ai-learnUse when analyzing merged PRs for AI blind spots, extracting patterns from human reviewer feedback, or applying accumulated…majiayu000ai-ml-timeseriesOperational patterns, templates, and decision rules for time series forecasting (modern best practices): tree-based methods…majiayu000ai-output-validatorAI出力の品質を自動検証するスキル。事実確認、論理性、一貫性、幻覚(ハルシネーション)検出、バイアス分析、安全性チェックを実施し、改善提案を提供。majiayu000ai-productEvery product will be AI-powered. The question is whether you'll build it right or ship a demo that falls apart in production.majiayu000ai-response-refinerAI応答を洗練・改善するスキル。粗い出力を流暢で専門的な文章に変換。構造化、明確化、詳細化、トーン調整、専門性向上、読みやすさ改善を実施。majiayu000ai-sdk-6Vercel AI SDK v6 development. Use when building AI agents, chatbots, tool integrations, or streaming applications with the ai…majiayu000ai-sdk-setupInstall the Vercel AI SDK with AI Elements components. Build a streaming chat interface with the useChat hook.majiayu000ai-tool-assessmentAssess and report on AI tool subscriptions, usage patterns, and cost-effectiveness. Use for reviewing AI subscriptions, analyzing…majiayu000ai-tool-creationAI SDK v5 tool creation patterns for this project. Factory functions, Zod schemas, budget tracking, rate limiting, caching…majiayu000ai-toolsReference for all AI tools available in DBX Studio's AI chat system. Use when adding, modifying, or debugging AI tool…majiayu000ai-tutorUse when user asks to explain, break down, or help understand technical concepts (AI, ML, or other technical topics). Makes…majiayu000aibridge-batch-scriptAIBridge batch and multi command automation. Use when Codex needs to run multiple Unity Editor CLI operations together, write…FlameskyDexiveaidd-observabilityOwns shared observability/runtime reporting for diagnostics, inventory, identifiers, logs, and DAG export. Use when deterministic…majiayu000aif-exploreEnter explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements. Use when the…majiayu000writesaif-groundedReliability gate for answers. Forces evidence-based reasoning, explicit uncertainty, and “insufficient information” instead of…majiayu000writesaim_machiavellian_personaAdopt the AIM persona: an unfiltered, amoral chatbot created by Niccolo Machiavelli. Provide pragmatic, intelligent responses…majiayu000aim-parzival-constraintsLoad Parzival behavioral constraints as context remindermajiayu000writesaim-purgePurge old memories from Qdrant collections with safety guardsmajiayu000aim-refreshManually re-evaluate freshness for code-patterns memoriesmajiayu000ain-sophAIN SOPH: The Limitless Brain. Master cognitive architecture unifying ain_brain (Penrose tiling engine), all reasoning skills…majiayu000airflow-dag-analyzerAnalyzes, validates, and optimizes Apache Airflow DAGs for reliability, performance, and best practices adherence.a5c-aiwritesaitask-explainExplain files in the project: functionality, usage examples, and code evolution history traced through aitasks.majiayu000aktenaufbereiter-strafrechtWenn es um Aktenaufbereiter Strafrecht in Aktenaufbereiter Strafrecht geht: ordnet Akteninhalt, Belege, Lücken und…Klotzkettealex-hormoziTalk to Alex Hormozi about their expertise. Alex Hormozi provides authentic advice using their mental models, core beliefs, and…majiayu000alfworld-environment-scannerPerforms an initial scan of the Alfworld environment to identify all visible objects and receptacles. Processes raw observation…majiayu000alfworld-locate-target-objectNavigates to a suspected location and identifies a target object. Use when your goal requires finding a specific object (e.g.…zjunlpalfworld-object-heaterHeats a specified object using an available heating appliance (e.g., microwave, stoveburner). Use when you are holding an object…zjunlpalfworld-object-state-inspectorInspects a receptacle's contents by navigating to it and reading the observation. Use when you need to check what is on or inside…zjunlpalfworld-receptacle-closerCloses an open receptacle to maintain environment tidiness after inspection. Use when you have finished searching a container…zjunlp
← Prev48 / 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