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
577624 · page 13 / 244
introWalk through the Elixir/Phoenix plugin commands, workflow, and features in 6 interactive sections. Use when a new user wants to…oliver-kriskainvestigation-workflow6-phase investigation workflow for understanding existing systems. Auto-activates for research tasks. Optimized for exploration…majiayu000issue-triageTriage a raw, vague issue or bug report into a structured document that names what is known, what is missing, and what to do…testdoublewriteskata-list-phase-assumptionsSurface Claude's assumptions about a phase approach before planning, checking what Claude thinks, or validating understanding…majiayu000writeskeine-researchUse this skill only when the user explicitly requests deep research or a detailed report on a topic — phrases like "research X"…majiayu000kiro-verify-completionVerify completion and success claims with fresh evidence. Use before claiming a task is complete, a fix works, tests pass, or a…gotalabkitt-create-subagentsExpert guidance for creating, building, and using Claude Code subagents and the Task tool. Use when working with subagents…majiayu000ksim-rlRL training library for humanoid locomotion and manipulation built on MuJoCo and JAX. Provides PPO, AMP, and custom task…majiayu000mastering-langgraphBuild stateful AI agents and agentic workflows with LangGraph in Python. Covers tool-using agents with LLM-tool loops, branching…majiayu000langgraph-checkpointLangGraph checkpoint and persistence configuration for stateful workflow managementa5c-aiwriteslanggraphLangGraph workflow patterns for agent orchestrationmajiayu000langgraph-stateLangGraph state management patterns. Use when designing workflow state schemas, using TypedDict vs Pydantic, implementing…majiayu000launch-pruefungWenn es um Produkt-Launch-Freigabeprüfung in Produkthaftung und Produktrecht geht: prüft Frist, Form, Zuständigkeit, Rechtsweg…Klotzkettelearning-needs-analysisConduct comprehensive learning needs analysis including stakeholder interviews, performance gap identification, job/task…majiayu000lifecycle-hooksBehavioral rules and lifecycle event handlers for the core-tools package. Defines automated behaviors that trigger at specific…majiayu000lifecycle-hooksBehavioral rules and lifecycle event handlers for the dev-tools package. Defines automated behaviors that trigger at specific…majiayu000lifecycle-hooksBehavioral rules and lifecycle event handlers for the core-tools package. Defines automated behaviors that trigger at specific…majiayu000lifecycle-hooksBehavioral rules and lifecycle event handlers for the core-tools package. Defines automated behaviors that trigger at specific…majiayu000lindy-core-workflow-aCore Lindy workflow for creating and configuring AI agents. Use when building new agents, defining agent behaviors, or setting up…majiayu000writeslindy-core-workflow-aBuild and configure multi-step Lindy AI agent workflows. Use when creating agents with triggers, actions, conditions, knowledge…jeremylongshorewriteslindy-core-workflow-bConfigure Lindy triggers, scheduling, multi-agent delegation, and automation. Use when setting up trigger-based workflows…jeremylongshorewriteslindy-hello-worldCreate your first Lindy AI agent with a real trigger and action. Use when starting with Lindy, testing your setup, or learning…jeremylongshorewriteslindy-prod-checklistProduction readiness checklist for Lindy AI agent deployments. Use when preparing agents for production, auditing live agents, or…jeremylongshorewriteslinking-notesDiscover and add wiki-links between notes. Use when asked to "find connections", "link this note", "what should I link to", or…majiayu000llm-councilMulti-LLM collaborative brainstorming and planning. Use when user explicitly requests consultation with multiple AI models…majiayu000llm-councilRun Fireworks-hosted open-weight model councils that compare responses and synthesize a final answer.sickn33writesllm-fine-tuningFine-tune large language models efficiently using LoRA, QLoRA, and PEFT methods. Use for domain adaptation, instruction tuning…majiayu000LLM Model Selection SkillChoosing the right model for the task — power vs. cost vs. speed.majiayu000llm-wikiThe foundational knowledge distillation pattern for building and maintaining an AI-powered Obsidian wiki. Based on Andrej…Ar9avln-001-standards-researcherResearches standards and patterns via MCP Ref for Story Technical Notes. Use when Story needs standards research before task…majiayu000ln-002-session-analyzerAnalyzes current or recent session for errors, inefficiencies, and improvement opportunities across skills, tools, hooks, and…majiayu000writesln-002-session-analyzerAnalyzes current or recent session for errors, inefficiencies, and improvement opportunities across skills, tools, hooks, and…majiayu000writesln-002-session-analyzerAnalyzes current or recent session for errors, inefficiencies, and improvement opportunities across skills, tools, hooks, and…majiayu000writesln-002-session-analyzerAnalyzes current or recent session for errors, inefficiencies, and improvement opportunities across skills, tools, hooks, and…majiayu000writeslokalise-core-workflow-aExecute Lokalise primary workflow: Upload source files and manage translation keys. Use when uploading translation files…jeremylongshorewriteslokalise-core-workflow-bManage Lokalise secondary workflow: Download translations and integrate with app. Use when downloading translation files…jeremylongshorewriteslongbridge-flowsSmart-money and ownership-flow signals for a single stock via Longbridge Securities — SEC 13F institutional portfolios + position…majiayu000longbridge-ipoIPO full-lifecycle management via Longbridge Securities — HK/US IPO calendar, subscription/pending/listed rosters, individual IPO…majiayu000longbridge-market-tempMarket-level state from Longbridge Securities — market temperature index (0–100, higher = more bullish), trading session times…majiayu000longbridge-options-advancedAdvanced options strategy framework via Longbridge — volatility surface concepts (SABR/local vol), dynamic Delta hedging…majiayu000longbridge-sec-filingsSEC EDGAR filing analysis via Longbridge — 10-K annual report, 10-Q quarterly, 8-K material events, proxy statement, insider Form…majiayu000lp-do-analysisThin orchestrator for decision-grade approach selection. Converts evidence-first fact-finds into a chosen approach, rejected…majiayu000lp-do-briefingProduce an understanding-only system briefing — how something works now, traced end-to-end with evidence pointers. No planning…majiayu000m4-researchStart a structured clinical research session. Triggers on "/research", "start research", "new study", "analyze cohort"…majiayu000machine-learning-foundationsSupervised and unsupervised learning, bias-variance tradeoff, cross-validation, decision trees, ensemble methods, neural network…majiayu000macos-notarization-workflowAutomate Apple notarization with xcrun notarytool for macOS application distributiona5c-aiwritesmaintainx-core-workflow-aExecute MaintainX primary workflow: Work Order lifecycle management. Use when creating, updating, and managing work orders…jeremylongshorewritesmaintainx-core-workflow-bExecute MaintainX secondary workflow: Asset and Location management. Use when managing equipment assets, organizing…jeremylongshorewrites
← Prev13 / 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