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
625672 · page 14 / 244
researchResearch a task, problem, bug, or feature by exploring the codebase. Use when starting new work, encountering bugs, or needing to…majiayu000make-traceTurn any source that describes how a kind of task gets done (a SKILL.md, a chat log, a runbook, plain prose) into a runnable…AIScientists-Devmandant-aufnahmeWenn es um /mandant-aufnahme in Plugin für die studentische Rechtsberatungsstelle geht: prüft Frist, Form, Zuständigkeit…Klotzkettemathematical-problem-solvingPolya's four-phase method applied to mathematical problems, extended with Schoenfeld's control/monitoring layer. Covers…majiayu000matlab-build-toolboxExecute the build plan — introspect buildfile.m, run its dependency chain, and produce the .mltbx toolbox package. Mechanical…matlabmcp-masteryComplete MCP tool reference and usage patterns. Load this skill to become an expert in all 80+ GoodVibes MCP tools. Use when you…majiayu000meeting-feedbackPost-meeting effectiveness feedback and continuous improvementmajiayu000meeting-insights-analyzerAnalyzes meeting transcripts and recordings to uncover behavioral patterns, communication insights, and actionable feedback.…majiayu000meeting-insights-analyzerAnalyzes meeting transcripts and recordings to uncover behavioral patterns, communication insights, and actionable feedback.…majiayu000meeting-notesMeeting notes page — title bar with attendees, agenda checklist, decisions block, action items table with owners + dates, and a…nexu-iomeeting-prep-ccGenerate a pre-meeting prep brief in Claude Code. Researches participants, pulls vault context, builds agenda, surfaces sharp…majiayu000cog-meeting-processingProcess meeting recordings and transcripts into decisions, action items, and team dynamicsa5c-aimeeting-synthesisUse when extracting product signals from meeting transcripts - systematically identifies asks, problems, quotes, and evidence…majiayu000meeting-synthesizerProcesses meeting notes or transcripts to extract structured information. Use after meetings to quickly generate action items…majiayu000meeting-transcript-analysisAnalyze meeting transcripts to extract action items, decisions, key points, and generate summariesmajiayu000memoryAI DevKit · Use the memory CLI as a durable knowledge layer. Search before non-trivial work, store verified reusable knowledge…codeaholicguymetathinkMetathink - Optimize Claude Code usage through metacognitive strategies. Use extended thinking, context engineering, task…majiayu000mission-podExecute a single task with Pathfinder/Builder/Inspector crew. Self-fetches work from Beads.majiayu000mistral-core-workflow-bExecute Mistral AI embeddings, function calling, and RAG pipelines. Use when implementing semantic search, RAG applications…jeremylongshorewritesmistral-core-workflow-bExecute Mistral AI secondary workflows: Embeddings and Function Calling. Use when implementing semantic search, RAG applications…majiayu000writesml-experiment-trackerPlan reproducible ML experiment runs with explicit parameters, metrics, and artifacts. Use before model training to standardize…majiayu000moai-core-agent-guideComplete guide to MoAI-ADK agents, delegation patterns, and agent orchestration for intelligent task distributionmajiayu000moaiMoAI super agent - unified orchestrator for autonomous development. Routes natural language or explicit subcommands (plan, run…majiayu000writesmoaiMoAI super agent - unified orchestrator for autonomous development. Routes natural language or explicit subcommands (plan, run…majiayu000writesmoai-library-toonTOON Format Specialist - YAML-based token-efficient agent/workflow definitions inspired by BMAD Method patternsmajiayu000moai-workflow-thinkingSequential Thinking MCP and UltraThink mode for deep analysis, complex problem decomposition, and structured reasoning workflowsmajiayu000moai-workflow-thinkingSequential Thinking MCP and UltraThink mode for deep analysis, complex problem decomposition, and structured reasoning workflows.…majiayu000model-comparison-toolUse when asked to compare multiple ML models, perform cross-validation, evaluate metrics, or select the best model for a…majiayu000model-mergingMerge multiple fine-tuned models using mergekit to combine capabilities without retraining. Use when creating specialized models…majiayu000model-recommendationAnalyze chatmode or prompt files and recommend optimal AI models based on task complexity, required capabilities, and…majiayu000model-recommendationAnalyze chatmode or prompt files and recommend optimal AI models based on task complexity, required capabilities, and…majiayu000model-routerChoose model tier by task complexity. Keep routine work cheap. Escalate only when required.majiayu000model-routingIntelligent model selection - routes tasks to Haiku (fast/cheap), Sonnet (balanced), or Opus (complex/strategic) based on task…majiayu000moonshot-evaluate-complexityEvaluates complexity (simple, medium, complex) based on estimated files/lines/time. Use after task classification.majiayu000mteb-retrieveGuidance for text embedding retrieval tasks using sentence transformers or similar embedding models. This skill should be used…majiayu000Multi-Robot Coordination SkillCoordination and task allocation for multi-robot systems and fleetsa5c-aiwritesmyagents-task-automation让 Agent 建立 MyAgents Task 自动化的完整产品心智模型,并创建、验证和治理所有“以后再做”的工作:理解 Task 解决什么问题、与立即执行/Thought/Goal 的边界,以及何时到点直接唤醒 AI(always)、何时先用本地…hAcKlycnavan-enterprise-rbacConfigure Navan admin roles, travel policies, approval workflows, and department-level access controls. Use when setting up…jeremylongshorewritesnl-routerRoute natural language requests to appropriate skills and workflows. Use when relevant to the task.majiayu000nlp-engineeringUse this skill when building NLP pipelines, implementing text classification, semantic search, embeddings, or summarization.…majiayu000nw-agent-creation-workflowDetailed 5-phase workflow for creating agents - from requirements analysis through validation and iterative refinementmajiayu000obsidian-ci-integrationSet up GitHub Actions CI/CD for Obsidian plugin development. Use when automating builds, tests, and releases for your plugin, or…jeremylongshorewritesobsidian-core-workflow-aCreate an Obsidian plugin from scratch with full project scaffolding. Covers Plugin class, ribbon icons, commands, settings tab…jeremylongshorewritesobsidian-enterprise-rbacImplement team vault access patterns and role-based controls. Use when managing shared vaults, implementing access controls, or…jeremylongshorewritesobsidian-multi-env-setupConfigure multiple Obsidian environments for development, testing, and production. Use when managing separate vaults, testing…jeremylongshorewritesobsidian-performance-tuningOptimize Obsidian plugin performance for smooth operation in large vaults. Use when experiencing lag, memory issues, slow…jeremylongshorewritesobsidian-project-bootstrapThis skill should be used when the user asks to start a new research project, import an existing code-plus-Markdown repository…brycewang-stanfordobsidian-synthesis-mapUse this skill when generating higher-level synthesis notes such as literature reviews, comparison matrices, project summaries…majiayu000
← Prev14 / 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