Agent skills

Skills for cursor

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
6,852 found
3,0253,072 · page 64 / 143
apple-notes-searchSemantic + keyword search and connection-discovery across the user's own Apple Notes via the apple-notes MCP server. Use when the…sickn33application-performance-performance-optimizationOptimize end-to-end application performance with profiling, observability, and backend/frontend tuning. Use when coordinating…sickn33applicationinsights-web-tsInstrument browser/web apps with the Application Insights JavaScript SDK (@microsoft/applicationinsights-web). Use for Real User…sickn33appointo-automationAutomate Appointo tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQapprentice-first-weekPlan an apprentice's or new laborer's first week so they're useful by Friday and safe from hour one — day-by-day teaching order…mohitagw15856appsflyer-automationAutomate Appsflyer tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQappveyor-automationAutomate Appveyor tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQarchitect-reviewMaster software architect specializing in modern architecturesickn33architecture-decision-recordsCapture architectural decisions made during OpenAI Codex sessions as structured ADRs. Auto-detects decision moments, records…mturacarchitecture-decision-recordsComprehensive patterns for creating, maintaining, and managing Architecture Decision Records (ADRs) that capture the context and…sickn33architecture-decision-recordsWrite and maintain Architecture Decision Records (ADRs) following best practices for technical decision documentation. Use when…wshobsonarchitecture-diagramDiagram a system or technical architecture — services, data stores, and how they connect. Use when asked to draw an architecture…mohitagw15856architecture-feature-firstUse when creating a feature, designing folder structure, adding repositories/services/view models, wiring dependency injection…evancaarchitectureAuthoritative architecture reference for Lagune, covering repository layout, the command/template split, the core/adapter…wellwelwelarchive-strategyDesign the archive layer that keeps current workspaces lean without losing history — what moves, when, to where…mohitagw15856ariaDesigns the data model, API contracts, and structural foundation of the system.sickn33arm-cortex-expertSenior embedded software engineer specializing in firmware and driver development for ARM Cortex-M microcontrollers (Teensy…sickn33arrowspaceSpectral vector search using graph Laplacian eigenstructure. Use when cosine/L2 similarity misses latent structure in your…sickn33article-illustrationsGenerate hand-drawn 16:9 article illustrations with the Grav character IP, sparse annotations, and absurd but clear visual…sickn33article-contentWhen the user wants to write, generate, or create article body content—blog post body, long-form content, how-to guide, listicle.…kostja94article-writingWrite articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from…mturacartifacts-builderSuite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React…nexu-ioaryn-automationAutomate Aryn tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQasana-automationAutomate Asana tasks via Rube MCP (Composio): tasks, projects, sections, teams, workspaces. Always search tools first for current…sickn33ascora-automationAutomate Ascora tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQAshby AutomationAutomate recruiting and hiring workflows in Ashby -- manage candidates, jobs, applications, interviews, and notes through natural…ComposioHQasin-data-api-automationAutomate Asin Data API tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQask-copilotUse GitHub Copilot CLI in non-interactive mode to ask questions, review code, or generate snippets without manual interaction.sickn33ask-mattAsk which skill or flow fits your situation. A router over the user-invoked skills in this repo.sickn33ask-questions-if-underspecifiedClarify requirements before implementing. Do not use automatically, only when invoked explicitly.MoizIbnYousafask-questions-if-underspecifiedClarify requirements before implementing. Use when serious doubts arise.sickn33assumption-bountyExtract every hidden assumption from a plan or document and put a price on each one — what it costs if wrong, what it costs to…mohitagw15856astica-ai-automationAutomate Astica AI tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQastroBuild content-focused websites with Astro — zero JS by default, islands architecture, multi-framework components, and…sickn33async-decision-memoRun a decision asynchronously — the memo, the silent-read window, the comment protocol, and the deadline that makes it land…mohitagw15856async-insteadConvert a meeting into async work that actually decides — the doc-plus-deadline format that replaces the room, the comment-window…mohitagw15856async-interview-automationAutomate Async Interview tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQasync-standup-compilerCompile the team's REAL updates into one async standup — pull what people posted in Slack (and moved in Notion/Linear), not a…mohitagw15856async-update-formatWrite status updates people actually read — the traffic-light-plus-narrative format (state first, story second), the…mohitagw15856atlas-contractGoal-integrity skill. Use for backend/API/persistence, preserve/do-not-change, tests/validation, mocks, rework, multi-part…sickn33atlas-ledgerCompanion to atlas-contract. Auto-invoked by its Final Audit on caught drift; also use after Post Reviews or user requests to…sickn33atlassian-automationAutomate Atlassian tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQattention-resetGet your attention back with a 30-day protocol that assumes you'll break it — a screen-time ledger without moralizing, friction…mohitagw15856Attio AutomationAutomate Attio CRM operations -- search records, query contacts and companies with advanced filters, manage notes, list…ComposioHQattribution-modelSet up attribution models. Use when: multi-touch attribution, credit distribution rules, GA4 config, channel contribution.indranilbanerjeeattribution-reportRun multi-touch attribution analysis. Use when: first/last-touch, linear, time-decay, position-based revenue allocation.indranilbanerjeeaudience-profileBuild detailed buyer personas. Use when: demographics, psychographics, behaviors, JTBD, content preferences.indranilbanerjeeaudit-context-buildingEnables ultra-granular, line-by-line code analysis to build deep architectural context before vulnerability or bug finding.sickn33
← Prev64 / 143Next →
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