Agent skills

Workflow & Productivity 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
11,684 found
865912 · page 19 / 244
tts-horusThis skill standardizes the end-to-end Horus voice workflow using uvx-stylemajiayu000tts-trainThis skill provides a general, composable workflow for building datasets and trainingmajiayu000twinmind-core-workflow-bExecute TwinMind secondary workflow: Action item extraction and follow-up automation. Use when automating meeting follow-ups…jeremylongshorewritestwinmind-cost-tuningOptimize TwinMind costs across Free, Pro ($10/mo), and Enterprise tiers with usage monitoring and tier selection guidance. Use…jeremylongshorewritestwinmind-enterprise-rbacConfigure TwinMind Enterprise with on-premise deployment, custom AI models, SSO integration, and team-wide transcript sharing.…jeremylongshorewritestwinmind-reference-architectureProduction architecture for meeting AI systems using TwinMind: transcription pipeline, memory vault, action item workflow, and…jeremylongshorewritestwinmind-webhooks-eventsHandle TwinMind meeting events including transcription completion, action item extraction, and calendar sync notifications. Use…jeremylongshorewritesuncertainty-routingRoute tasks to small model by default, escalate to large model only on low confidence detection, achieving 87% faster learning…majiayu000understand-intentDetect user's intent from their message and activate the right workflow silently.majiayu000unity-yaml-editingUnity YAML text serialization editing workflow. Use when Codex needs to directly inspect, modify, create, or repair Unity…FlameskyDexivemeeting-insights-analyzer分析会议记录和录像以发现行为模式、沟通洞察和可操作的反馈。识别您何时避免冲突、使用填充词、主导对话或错过倾听的机会。非常适合希望提高沟通和领导能力的专业人士。majiayu000user-story-mapping-workshopRun a user story mapping workshop with adaptive questions and a structured map output. Use when you need backbone activities…deanpetersvalidate-agentValidation agent that validates plan tech choices against current best practicesmajiayu000validate-agent-majiayu000-claude-skill-registrValidation agent that validates plan tech choices against current best practicesmajiayu000validate_paper_linksValidate paper note links against actual paper references and influencemajiayu000vaspExpert assistant for VASP (Vienna Ab initio Simulation Package) calculations - input file generation, parameter selection…majiayu000vector-store-skillPROTECTED: Vector store schema management. Changes require pre-modification checklist validation.'majiayu000vendor-evaluationEvaluate, select, and contract with vendors and SaaS tools. Use this skill when comparing alternatives, running an RFP, scoring…rampstackcoverification-suitePlan structure validation, phase completeness checks, reference integrity verification, and artifact existence confirmation.…a5c-aiverifyAI DevKit · Enforce evidence-based completion claims — require fresh command output before reporting success. Use when completing…codeaholicguyverify-proposed-diagVerify a proposed architecture diagram against the actual codebase, selectively checking existing vs new components. Use when…majiayu000verwandte-skills-vorschlagWenn es um /verwandte-skills-vorschlag — Verwandte-Skills-Empfehlung in Kanzlei-Builder-Hub geht: prüft Frist, Form…Klotzkettevet-estimate-decoderDecode a veterinary treatment estimate — what each line is for, which items are core vs precautionary, and how to have the…mohitagw15856vigil-instrumentInstrument a service with OpenTelemetry — RED metrics, structured logs, distributed tracing, and health checks. Outputs actual…jeremylongshorewriteswayfinder-mapsPlan a huge chunk of work — more than one agent session can hold — as a shared map of investigation tickets, and resolve them one…rengwuwhen-developing-ml-models-use-ml-expertSpecialized ML model development, training, and deployment workflowmajiayu000wiki-foldCreate a bounded, extractive, structurally idempotent rollup of recent Obsidian wiki log entries, with dry-run preview by default…AgriciDanielwiki-narrateTurn a wiki topic into a cited Markdown briefing, plain-language explanation, or progressive lecture. Use this skill for…Ar9avwireframe-sketch网格背景 + marker 笔触 + 多 tab + sticky note + scribble 图表nexu-iowireframe-sketchA hand-drawn wireframe exploration — graph-paper background, marker / pencil tone, multiple tab labels for variants, sticky-note…nexu-ioworkflow-analysisWorkflow d'Analyse Obligatoire. Use when working with workflow analysis.majiayu000workflow-analysisMandatory analysis workflow for understanding codebase before changesmajiayu000workflow-analysisWorkflow d'Analyse Obligatoire. Use when working with workflow analysis.majiayu000workflow-analyzeAnalyze issue and generate analysis.md with solution approaches. Use when starting a new task or feature to thoroughly analyze…majiayu000workflow-analyzeAnalyze issue and generate analysis.md with solution approaches. Use when starting a new task or feature to thoroughly analyze…majiayu000workflow-analyzer作業フローや手順を分析し、自動化可能な要素を特定する。ワークフロー分析時、自動化検討時、業務プロセス改善時、またはユーザーが作業フロー分析、自動化要素、業務手順、プロセス最適化に言及した際に使用する。majiayu000workflow-kaltstart-und-routingKaltstart und Routing im Plugin produktrecht: führt vom ersten Satz oder Dokument in den passenden Arbeitsweg, erkennt Rolle…majiayu000workflow-patternsUse this skill when implementing tasks according to Conductor's TDD workflow, handling phase checkpoints, managing git commits…sickn33workflow-patternsUse this skill when implementing tasks according to Conductor's TDD workflow, handling phase checkpoints, managing git commits…wshobsonworkflow-research-codebaseThis skill should be used when conducting comprehensive codebase research to answer questions, understand architecture, or…majiayu000working-with-ms-agent-frameworkUse when building AI agents with Microsoft Agent Framework (Semantic Kernel + AutoGen unified); when implementing memory or…majiayu000wow-applying-fixer-workflowComplete fixer agent workflow including report discovery, validation strategy (HIGH/MEDIUM/FALSE_POSITIVE confidence), fix…majiayu000xai-modelsxAI Grok model selection and capabilities guide. Use when choosing the right Grok model for your task, comparing model features…majiayu000001-fruehformen-zwoelftafelrechtWenn es um Römisches Recht: Frühformen Zwölftafelrecht sakrale Spruchform und Prozessformel in Römisches Recht geht: prüft Frist…Klotzkette001-fruehformen-zwoelftafelrecht-sakrale-spruchformWenn es um Rom Fruehformen Zwoelftafelrecht Sakrale Spruchform Und in Römisches Recht geht: prüft Frist, Form, Zuständigkeit…Klotzkette001-normnavigator-jede-pralr-norm-als-karte-erschliessWenn es um Pralr Normnavigator Jede Pralr Norm Als Karte Erschliess in Preußisches Allgemeines Landrecht geht: prüft Frist, Form…Klotzkette002-beurkundung-oder-unterschriftsbeglaubigung-richtigWenn es um Notariat im Alltag: Beurkundung oder Unterschriftsbeglaubigung – richtig einordnen in Notariat im Alltag geht: prüft…Klotzkette002-zwoelftafelgesetz-textzeugenWenn es um Römisches Recht: Zwölftafelgesetz Textzeugen Rekonstruktion und Vorsicht in Römisches Recht geht: prüft Frist, Form…Klotzkette
← Prev19 / 244Next →
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