Agent skills

Skills for cursor

6,852 skills that declare support for cursor. The SKILL.md format is shared, so most of these work in the other agents too — the declaration only says where the author tested it.

Toolclaude-code 62,644codex 9,699cursor 6,852copilot 2,269windsurf 126cline 82
CategoryWorkflow & Productivity 11,684AI & Agents 4,965Data & Analytics 4,693Code Review & Quality 2,936Security 2,762Backend & API 2,480Design & Presentation 2,329Documentation 2,157Content & Marketing 2,001Testing & QA 1,723DevOps & Cloud 1,266Databases 1,124Frontend 1,015Business & Finance 706Media & Video 507Other 21,420
6,852 found
6,4816,528 · page 136 / 143
tile-designWeb and App implementation guide for Tile Design. Trigger when user wants Microsoft Metro style, sharp square information units…sickn33time-ledgerNatural-language time tracking: parse what the user says they did into Activity/Minutes/Date rows in their own Notion database —…sickn33timecamp-automationAutomate Timecamp tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQtimekit-automationAutomate Timekit tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQtimelinesai-automationAutomate Timelinesai tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQtimelink-automationAutomate Timelink tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQtimely-automationAutomate Timely tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQtinyurl-automationAutomate Tinyurl tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQtisane-automationAutomate Tisane tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQtitle-tagWhen the user wants to optimize the title tag, page title, or SERP title. Also use when the user mentions "title tag," "meta…kostja94tmuxExpert tmux session, window, and pane management for terminal multiplexing, persistent remote workflows, and shell scripting…sickn33to-issuesBreak a plan, spec, or PRD into independently-grabbable issues on the project issue tracker using tracer-bullet vertical slices.sickn33to-prdTurn the current conversation into a PRD and publish it to the project issue tracker — no interview, just synthesis of what…sickn33toc-generatorWhen the user wants to add, optimize, or audit table of contents (TOC) for long-form content. Also use when the user mentions…kostja94todoist-automationAutomate Todoist task management, projects, sections, filtering, and bulk operations via Rube MCP (Composio). Always search tools…sickn33Toggl AutomationAutomate time tracking workflows in Toggl Track -- create time entries, manage projects, clients, tags, and workspaces through…ComposioHQtoken-budget-advisorOffers the user an informed choice about how much response depth to consume before answering. Use this skill when the user…mturactoken-dietCut LLM output tokens 40–70% by stripping grammatical scaffolding while preserving every fact — telegraphic output modes, when…mohitagw15856token-efficiencyReduce token waste by 40-60% through anti-sycophancy rules, tool-call budgets, one-pass coding, task profiles, and…rohitg00token-metrics-automationAutomate Token Metrics tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQtomba-automationAutomate Tomba tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQtomtom-automationAutomate Tomtom tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQtone-fixerRewrite a message to the tone you actually want — less harsh, more confident, warmer, firmer, or shorter — without losing your…mohitagw15856toneden-automationAutomate Toneden tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQtool-permission-reviewReview what an agent is actually allowed to do before you turn it loose — the tool-by-tool audit (each capability's blast…mohitagw15856tool-procurement-evalEvaluate a new tool before it joins the stack — the problem-first framing (tools answer needs, not demos), the trial designed…mohitagw15856tooling-risk-assessmentAssess an injection-mold or production tooling decision before cutting steel — soft vs hard tooling tradeoff, tool life vs…mohitagw15856tools-page-generatorWhen the user wants to create, optimize, or audit free tools pages. Also use when the user mentions "free tools," "tools page,"…kostja94tools-page-seo-optimizerFramework-agnostic SEO workflow for any site with multiple tool, product, or feature pages. Covers duplicate content, unique meta…sickn33top-banner-generatorWhen the user wants to add, optimize, or audit a top announcement bar or sticky banner. Also use when the user mentions…kostja94top-web-vulnerabilitiesProvide a comprehensive, structured reference for the 100 most critical web application vulnerabilities organized by category.…sickn33tpscheck-automationAutomate Tpscheck tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQtrace-and-isolateApplies systematic tracing and isolation techniques to pinpoint exactly where a bug originates in code. Use when a bug is hard to…rohitg00analytics-trackingWhen the user wants to set up, audit, or optimize analytics tracking (GA4, events, conversions). Also use when the user mentions…kostja94trade-quote-builderBuild a trade quote that wins the job and protects the margin — materials and labor itemized, assumptions and exclusions stated…mohitagw15856trading-ledgerA trading journal that captures the decision, not just the fill: thesis, plan, and emotion at the moment of entry, written to the…sickn33traffic-analyzerAnalyze website traffic, global rank, engagement metrics, and traffic sources for any domain. Use this skill to evaluate…Affitortraffic-analysisWhen the user wants to analyze website traffic sources, attribution, or dark traffic. Also use when the user mentions "traffic…kostja94transcreationTranscreate marketing/brand copy for another language and culture — recreate the impact, not the words. Use when asked to adapt a…mohitagw15856translate-contentTranslate marketing content. Use when: localizing with brand voice preservation, quality scoring, or transcreation.indranilbanerjeetranslationWhen the user wants to translate content, create translation workflows, manage terminology, or optimize translation quality. Also…kostja94travel-briefTurn a business trip into a one-page brief that runs itself — the itinerary with buffers and failure modes, the meeting logistics…mohitagw15856travel-health-analyzer分析旅行健康数据、评估目的地健康风险、提供疫苗接种建议、生成多语言紧急医疗信息卡片。支持WHO/CDC数据集成的专业级旅行健康风险评估。sickn33writestreatment-plan-estimateBuild a veterinary treatment plan with tiered options and a cost estimate to discuss with a pet owner. Use when asked to prepare…mohitagw15856tree-ring-memoryUse Tree Ring Memory for local-first AI-agent memory lifecycle work: recall, evidence, audit, forgetting, and consolidation…sickn33trello-automationAutomate Trello boards, cards, and workflows via Rube MCP (Composio). Create cards, manage lists, assign members, and search…sickn33trending-content-scoutScan social platforms for top-performing content by engagement before you create anything. Use this skill when the user wants to…Affitortrigger-devTrigger.dev expert for background jobs, AI workflows, and reliable async execution with excellent developer experience and…sickn33
← Prev136 / 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