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
481528 · page 11 / 244
deep-analysisDeep exploration and synthesis workflow using Agent Teams with dynamic planning and hub-and-spoke coordination. Use when asked…majiayu000writesdeep-analysisReusable deep exploration and synthesis workflow. Use when asked for "deep analysis", "deep understanding", "analyze codebase"…majiayu000writesdeep-research-planUse deep-research-plan for repo-change plans needing downloaded projects, articles, or papers, per-reference analysis, graphify…Optim-Agentdeep-researchExecute autonomous multi-step research using Google Gemini Deep Research Agent. Use for: market analysis, competitive…majiayu000deep-researchRun autonomous research tasks that plan, search, read, and synthesize information into comprehensive reports.majiayu000deep-researchDeep, iterative, multi-source research that explores a topic from multiple perspectives, detects contradictions, and produces a…majiayu000writesdeepagents-todolistUsing TodoListMiddleware for task planning and tracking progress with the write_todos tool in Deep Agents for complex multi-step…majiayu000deeper-researchComprehensive 6-phase research funnel — 8-10 parallel survey agents sweep wide, a synthesizer compiles evidence, deep-dive and…majiayu000deepgram-core-workflow-bImplement real-time streaming transcription with Deepgram WebSocket. Use when building live transcription, voice interfaces…jeremylongshorewritesdeepgram-prod-checklistExecute Deepgram production deployment checklist. Use when preparing for production launch, auditing production readiness, or…jeremylongshorewritesdev-buddy-rcaRoot cause analysis for bugs. Dispatches RCA executors in parallel, consolidates findings, and appends RCA Diagnosis to the plan…majiayu000writesdev-commitAI DevKit · Safe git commit workflow for AI coding agents. Use when the user asks to commit, prepare a commit, stage changes…codeaholicguydev-exploreThis skill should be used when the user asks to 'explore the codebase', 'map architecture', 'find similar features', or in Phase…majiayu000dev-planningAI DevKit · Planning phase guidance for creating and reconciling feature task plans. Use when the user wants to create an…codeaholicguydiffDeterministic git diff inspection. Converts natural language intent into an explicit, auditable diff plan and emits a bounded…majiayu000world-model-workflowBuild a rigorous world model with state, dynamics, uncertainty, and provenance. Use when creating digital twins, constructing…majiayu000writesdigital-twin-sync-workflowRun the digital twin sync loop to synchronize real-world signals with a digital model. Use when updating digital twins, detecting…majiayu000writesdiligence-risk-burndownRun diligence as a fast risk burn-down: build a ranked risk register (max 4), execute the fastest tests, and produce…majiayu000disciplineBulletproof agent operating protocol. 15 failure-prevention rules distilled from 120+ real sessions and 10 agent definitions.…avdiscover-agenticAutomatically discover agentic workflow skills when building AI agents, implementing tool use patterns, managing context windows…majiayu000discover-solution-spaceDeeply explore the solution space to find the optimal approach before committing to a plan.majiayu000discovery-question-formStructured clarification form for unresolved material requirements.nexu-iodiscussBrainstorms and debates approaches, then drives toward an actionable decision. Use whenever someone needs a thinking partner for…majiayu000documenso-core-workflow-aImplement Documenso document creation and recipient management workflows. Use when creating documents, managing recipients…jeremylongshorewritesdogpileDeep research aggregator that searches Brave (Web), Perplexity (AI), GitHub (Code/Issues), ArXiv (Papers), YouTube (Videos), and…majiayu000down-skillingDistill Opus-level reasoning into optimized instructions for Haiku 4.5 (and Sonnet). Generates explicit, procedural prompts with…majiayu000drama-workflow协调情节点戏剧功能分析流程,管理文本预处理、并行分析、结果整合。适用于长文本的情节点和戏剧功能分析、需要结构化分析报告的场景majiayu000Reality AnalysisThis skill should be used when the user asks about "plan drift", "reality check", "comparing docs to code", "project state…majiayu000ds-implementREQUIRED Phase 3 of /ds workflow. Enforces output-first verification at each step.majiayu000ds-implementPhase 3 of /ds workflow. Execute analysis tasks with output-first verification.majiayu000writesecosystem-mappingReading a habitat — identifying biome, plant community, food web structure, successional stage, and the keystone species that…majiayu000edge-verifierVerifies relationships between a source text (e.g. Episode, Task) and existing Knowledge Graph lessons. Runs KNN/Hybrid search to…majiayu000writesedge-verifierVerifies relationships between a source text (e.g. Episode, Task) and existing Knowledge Graph lessons. Runs KNN/Hybrid search to…majiayu000writeseffective-promptingMaster effective prompting techniques for Claude Code. Use when learning prompt patterns, improving task descriptions, optimizing…majiayu000effortDynamic effort level management. Use when: - User mentions "think harder", "be thorough", "quick fix", "max effort" - Task…majiayu000writeselnora-agentThis skill should be used when the user asks about "Elnora agent capabilities", "what can the agent do", "agent tools", "web…majiayu000esper:exploreExplore an idea before committing to a plan. Investigates feasibility, trade-offs, and approaches — codebase-aware or open-ended…majiayu000evernote-sdk-patternsAdvanced Evernote SDK patterns and best practices. Use when implementing complex note operations, batch processing, search…jeremylongshorewritesevernote-webhooks-eventsImplement Evernote webhook notifications and sync events. Use when handling note changes, implementing real-time sync, or…jeremylongshorewritesexam-prep-plannerBuild a realistic exam-prep schedule with spaced repetition and retrieval practice — the plan that survives contact with an…mohitagw15856EXECUTIONA high-precision implementation mode for the Claude-type AI to execute the plan with zero errors.majiayu000existing-solution-mapdescription: Produce existingsolutionmap.md to ground task generation in the current repo.'majiayu000expense-filerTurn a pile of receipts into a filed expense report through a tool-using agent — extraction, policy checks, and categorization…mohitagw15856experience-libraryCapture task outcomes, score performance, and derive rules as token priors for continual learning without model weight changes.…majiayu000experiment-planTurn a refined research proposal or method idea into a detailed, claim-driven experiment roadmap. Use after `research-refine`, or…majiayu000writesexperiment-planTurn a refined research proposal or method idea into a detailed, claim-driven experiment roadmap. Use after `research-refine`, or…majiayu000explain-thisExplain whatever the user is pointing at right now in plain language: a pending question, a piece of code, an error, a command…majiayu000explain-thisExplain whatever the user is pointing at right now in plain language: a pending question, a piece of code, an error, a command…majiayu000
← Prev11 / 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