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
385432 · page 9 / 244
alfworld-receptacle-operatorThis skill opens or closes a receptacle (like a fridge, cabinet, or microwave) to access its interior or secure it. It should be…zjunlpalfworld-search-verifierRe-examines previously visited locations to confirm the absence of a target object or to check for overlooked items. Use when an…zjunlpalfworld-tool-locatorThis skill searches for a specified tool or device (e.g., a desklamp) within the environment by checking relevant surfaces. It…majiayu000analyzeDeep analysis workflow for codebases, architectures, systems, products, markets, or research topics. Use when the user asks to…majiayu000analyzeDeep analysis workflow for codebases, architectures, systems, products, markets, or research topics. Use when the user asks to…majiayu000analyze-frictionOrchestrate 3-stage friction analysis workflow across conversations. Extracts raw friction, abstracts patterns, and presents for…majiayu000writesanalyzing-meetingsMUST BE USED when analyzing meeting transcripts or notes. Classifies input type, attributes speakers, and verifies names against…majiayu000android-playstore-scanScan Android project and generate Play Console setup checklist (analysis only, no file modifications)majiayu000anleiter-pruefwarteschlangeWenn es um Supervisoren-Prüfwarteschlange (Optional) in Plugin für die studentische Rechtsberatungsstelle geht: prüft Frist…KlotzketteanpassenWenn es um /anpassen in diesem Spezialbereich geht: prüft Frist, Form, Zuständigkeit, Rechtsweg und Sofortmaßnahmen; liefert eine…majiayu000anti-driftHierarchical coordination and drift detection with frequent checkpoints, shared memory coherence validation, role specialization…a5c-aiwritesdeep-researchExecute autonomous multi-step research using Google Gemini Deep Research Agent. Use for: market analysis, competitive…majiayu000antigravity-skill-orchestratorA meta-skill that understands task requirements, dynamically selects appropriate skills, tracks successful skill combinations…sickn33apex-planPlan and scope a project — discovery, challenge assumptions, present S/M/L options with token and cost estimates. Use when asked…jeremylongshorewritesargument-evaluationSystematic evaluation of arguments for structure, validity, soundness, and charitable interpretation. Covers premise…majiayu000ask_paperAnswer questions about a paper in the vault, using note first and arXiv HTML as fallbackmajiayu000assimilate-popular-workflowsThis skill should be used when the user asks to "find skills in the wild", "assimilate popular workflows", "discover SKILL.md…a5c-aiaufsichts-feed-monitorWenn es um Regulatorischer Feed-Watcher in Regulatorisches Recht – Plugin für deutsches geht: prüft Frist, Form, Zuständigkeit…KlotzketteautoAutonomous AI coding loop (Ralph Wiggum methodology). Use when running AI agents in unattended/autonomous mode to independently…majiayu000auto-router-patternsAuto router patterns for this project. Intelligent model selection via task classification, cost tier diversity, high-stakes…majiayu000autonomous-agentsAutonomous agents are AI systems that can independently decompose goals, plan actions, execute tools, and self-correct without…majiayu000autonomousExecute 1-2+ hour tasks autonomously with minimal supervision. Requires Task Contract (OUTCOME, EXCLUSIONS, DURATION, GUARDRAILS)…majiayu000autonomous-loop자율 실행 루프. Plan→Execute→Verify를 반복하여 복잡한 작업을 자율적으로 완성합니다. Ralph(완료 보장) 모드와 Autopilot(병렬 최대 성능) 모드를 지원합니다. Use when the user wants…majiayu000autonomous-skillUse when user wants to execute long-running tasks that require multiple sessions to complete. This skill manages task…majiayu000autonomous-skillExecute long-running, multi-session tasks autonomously using Claude Code headless mode or in-session hook-based loops. Supports…majiayu000autonomous-skillUse when user wants to execute long-running tasks that require multiple sessions to complete. This skill manages task…majiayu000axiom-modeODIN's compact-form conversation skill -- formal-logic English register with predicate claims, Hoare-triple framing, and ASCII…majiayu000beads-viewerGraph analysis with bv (Beads Viewer). Use when analyzing the task graph, finding blockers, getting recommendations, checking…majiayu000bid-strategy-plannerUse when the user asks to "pick a bid strategy", "set a tCPA/tROAS target", or "plan the learning-phase entry"; produces a…aaron-he-zhubmad-helpAnalyzes current state and user query to answer BMad questions or recommend the next workflow or agent. Use when user says what…majiayu000bookstrap-plan-researchAnalyze BRD and existing corpus to identify knowledge gaps, then generate prioritized research tasks for filling those gapsmajiayu000writesboost-promptInteractive prompt refinement workflow: interrogates scope, deliverables, constraints; copies final markdown to clipboard; never…majiayu000bot-channel-taskStandard flow for receiving channel tasks. Immediate acknowledgment, background execution, completion notification. Follow this…majiayu000building-agents-coreCore concepts for goal-driven agents - architecture, node types, tool discovery, and workflow overview. Use when starting agent…majiayu000campaign-planBuild multi-channel campaign plans. Use when: objectives, audience targeting, channel mix, budget, timeline, KPIs.indranilbanerjeecapability-diagnosticDiagnose agent failures by identifying missing capabilities. Use when an agent fails a task, produces wrong output, or needs…majiayu000catalyst-calendarMaintain calendar of upcoming catalysts for portfolio positions and watchlist. Earnings dates, ex-div dates, regulatory events…majiayu000catalyst-trackerBuild a catalyst list and event calendar for an asset.majiayu000catchupStructured method for quickly understanding recent changes in git repositories, meeting notes, sprint progress, document…majiayu000discover-researchGateway skill for research methodology - automatically loads relevant research skills based on task contextmajiayu000ce-factual-explainGenerate factual CE explanations and select the correct guarded versus standard factual workflow.majiayu000cfn-task-intelligenceClassify tasks (type/domain), estimate complexity/iterations, recommend specialists from feedback themesmajiayu000chat-namingGenerate descriptive chat titles from the first message using a fast LLM. Runs as a background workflow step after the main…majiayu000Chatbot IntegrationAI-powered chatbots use language models to provide conversational interfaces for customer support, information retrieval, and…majiayu000churn-analysisAnalyse customer churn for a product or cohort and produce a structured churn report. Use when asked to analyse churn, understand…majiayu000clade-core-workflow-bRedirect to claude-embeddings-search for tool use (function calling) and agentic loop patterns with Claude. Use when looking for…jeremylongshoreclaim-denial-decoderDecode an insurance claim denial letter — what the cited reason actually means, whether it's commonly overturnable, and the…mohitagw15856task-classifierAnalyzes task descriptions and classifies them into categories for agent selectionmajiayu000
← Prev9 / 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