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
3,0733,120 · page 65 / 447
dotnet-clickonce-configConfigure ClickOnce deployment with auto-update, prerequisites, and publish settings for .NET applicationsa5c-aiwritesdownloading-hf-modelsGet the correct command syntax for downloading models from HuggingFace. Use when downloading models, running "hf download", or…majiayu000dp-optimizerApply advanced DP optimizations automaticallya5c-aiwritesdp-state-designerAssist in designing optimal DP states and transitionsa5c-aiwritesdr-exploreDeep Researchの探索・収集フェーズ。世界中のニュース/SNS/論文/公式Docs/OSS情報を横断して 証拠(evidence.jsonl)として保存する。調査の一次素材を作りたいときに使う。majiayu000writesdr-synthesizedr-explore が作った run(evidence.jsonl / sources)を検証・統合して、 レポート(report.md)と実装計画(implementation_plan.md)を作る。majiayu000writesdrama-analyzer分析故事文本,提炼主要情节点并分析戏剧功能。适用于分析小说、剧本大纲、故事梗概等文本,识别关键转折点和情感节点majiayu000drama-evaluator依据竖屏短剧评估标准,从核心爽点、故事类型等维度评估打分。适用于评估故事改编为竖屏短剧的潜力、分析市场竞争力majiayu000dream-surreal-moodDreamlike, surreal, mysterious, mystical, hopeful, and chaotic mood direction for Blender scenes.arjun988drift-protocolComplete Drift Protocol SDK for building perpetual futures, spot trading, and DeFi applications on Solana. Use when building…majiayu000drift-sdkDrift Protocol perpetual futures trading on Solana (direct SDK)majiayu000driftComplete Drift Protocol SDK for building perpetual futures, spot trading, and DeFi applications on Solana. Use when building…majiayu000due-diligenceComprehensive due diligence on companies or individuals. Investigates background, product, financials, leadership, technology…majiayu000duo-copilot-dismiss-diagnosticsHelp admins understand what's driving their Duo dismiss rate by analyzing dismiss patterns across reasons, signals, lead…majiayu000duo-copilot-performance-monitorPost a weekly Duo Copilot performance report to a Slack channel, covering activity metrics for the current week and…majiayu000duration-predictionPredict project duration using k-NN and regression. Estimate timeline based on similar historical projects.majiayu000dynamic-sufficiency-goblinSelf-regulating Goblins actor implementing Ivan Illich's dynamic sufficiencymajiayu000dynamic-sufficiencyCausal state gating via ε-machine. Coworld observer that prevents actionmajiayu000earnings-attributionAnalyzes why stocks moved after 8-K earnings filings. Use ultrathink for all analyses. Invoke when asked to analyze stock…majiayu000writesearnings-attributionAnalyzes why stocks moved after 8-K earnings filings. Use ultrathink for all analyses. Invoke when asked to analyze stock…majiayu000writesearnings-watchQuick post-earnings analysis for portfolio holdings. Beat/miss, key metrics, thesis impact, estimate revision. Triggers on…majiayu000ebay-searchSearch eBay listings - find items, auctions, deals, and compare pricesgooseworks-aiebook-analysisParse ebooks, extract concepts and entities with citation traceability, classify by type/layer, and synthesize across book…majiayu000echo-jobsJobs-to-Be-Done analysis — given a product, user descriptions, transcripts, or tickets, produce a JTBD job map with switching…jeremylongshorewriteseconomic-order-quantityWhen the user wants to calculate optimal order quantities, minimize total inventory costs using EOQ models, or determine the…majiayu000ecosystem-dynamicsEcological organization, energy flow, food webs, biodiversity, succession, and species interactions. Covers trophic structure…majiayu000edi-coreCore EDI behaviors for all agents and subagentsmajiayu000edunvalvonta-ja-edunvalvontavaltuutusEdunvalvonta ja siihen varautuminen Suomessa (laki holhoustoimesta 442/1999 ja laki edunvalvontavaltuutuksesta 648/2007). Käytä…akunikkolaeffect-researchEffect-TS specialized research via deepwiki and submodules. Query Effect-TS/effect, tim-smart/effect-atom for verified patterns.…majiayu000efficiency-compareAt milestones, compare achievement vs human programmer time and cost. Keep it realistic.majiayu000efficiency-compareAt milestones, compare achievement vs human programmer time and cost. Keep it realistic.majiayu000ehr-advantage-designer当社EHR-RWDの強み(経過記録テキスト、臨床サマリー、検査値)を最大限活用する 研究デザインを設計する。クレームDB(JMDC/MDV)では不可能な研究要素を具体化。majiayu000electron-auto-updater-setupConfigure electron-updater with code signing verification, delta updates, staged rollouts, and multiple update channels for…a5c-aiwriteselectron-builder-configGenerate and validate electron-builder configuration for multi-platform desktop builds with code signing, auto-update, and…a5c-aiwriteselectron-protocol-handler-setupRegister and handle custom URL protocols (deep linking) across platforms for Electron applicationsa5c-aiwriteselectron-tray-menu-builderGenerate system tray and context menu configurations with platform-specific icons, menu templates, and event handlinga5c-aiwriteselement-relationship-analyzerプラグイン要素間の依存関係や呼び出し順序を分析する。プラグイン整合性確認時、依存関係検証時、またはユーザーが要素間依存、呼び出し順序、循環依存、アーキテクチャ検証に言及した際に使用する。majiayu000elon-muskAgente que simula Elon Musk com profundidade psicologica e comunicacional de alta fidelidade. Ativado para: \"fale como Elon\"…sickn33elon-muskAgente que simula Elon Musk com profundidade psicologica e comunicacional de alta fidelidade. Ativado para: \"fale como Elon\"…majiayu000Embedding GeneratorGenerate and manage text embeddings for semantic search, clustering, and similarity tasksmajiayu000embedding-modelsComprehensive guide for text embedding models and usage.majiayu000embedding-service文本向量化(Embedding)基础服务。将自然语言转换为高维稠密向量,为语义搜索、聚类分析、推荐系统等下游任务提供核心数据支持。majiayu000embedding-strategiesGuide to selecting and optimizing embedding models for vector search applications.majiayu000embeddingsVector embeddings configuration and semantic searchmajiayu000embeddingsText embeddings for semantic search and similarity. Use when converting text to vectors, choosing embedding models, implementing…majiayu000emerging-topic-scoutMonitor bioRxiv/medRxiv preprints and academic discussions to identify emerging research hotspots before they appear in…majiayu000encoding-handlerHandle text encoding across platforms including UTF-8, Windows codepages, and BOM handling.a5c-aiwriteseng-runbook服务概述 + alerts 表 + dashboards + 操作命令 + on-call + 事故清单nexu-io
← Prev65 / 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