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
5,5215,568 · page 116 / 143
plan-my-dayTurn a messy to-do brain-dump into a realistic, time-blocked day — top priorities first, everything slotted with buffer, and an…mohitagw15856plan-orchestrateRead a plan document, decompose it into steps, design a per-step agent chain from the ecc catalogue, and emit ready-to-paste…mturacplan-writingStructured task planning with clear breakdowns, dependencies, and verification criteria. Use when implementing features…sickn33plankton-code-qualityWrite-time code quality enforcement using Plankton — auto-formatting, linting, and Codex-powered fixes on every file edit via…mturacplanning-and-task-breakdownBreaks work into ordered tasks. Use when you have a spec or clear requirements and need to break work into implementable tasks.…addyosmaniplanning-and-task-breakdownBreaks work into ordered tasks. Use when you have a spec or clear requirements and need to break work into implementable tasks.…sickn33plasmic-automationAutomate Plasmic tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQplaterecognizer-automationAutomate Platerecognizer tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQplatform-design300+ design rules from Apple HIG, Material Design 3, and WCAG 2.2 for cross-platform apps. Useful when shipping a single design…nexu-ioplisio-automationAutomate Plisio tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQplotlyInteractive visualization library. Use when you need hover info, zoom, pan, or web-embeddable charts. Best for dashboards…sickn33pm-allOrchestrate full governance scan with prerequisite gates; default noise-filtered summary; rebuild .pm/dashboard aggregate.wei63wpm-archScan project structure and generate Mermaid architecture diagrams + flowcharts under .pm/architecture/.wei63wpm-charterCreate, import, discover, approve, or skip project charter; integrates Spec Kit constitution. Trigger on /pm-charter and related…wei63wpm-discoverDeep-scan all enabled governance modules and refresh state (internal; used by pm-all / status --full).wei63wpm-doneClose a todo (TODO-xxx), sync completed.md, refresh overview Top3.wei63wpm-exportExport desensitized governance summary markdown for sharing or machine switch. Trigger on /pm-export and related English phrases…wei63wpm-fixAnalyze pasted logs/stacks/slow SQL from chat (or --path) into bugs findings and todos.wei63wpm-initInitialize local .pm governance workbench; detect new vs existing project; discover Spec Kit constitution; optional outline from…wei63wpm-nextClaim the single next governance todo (marks in_progress). Trigger on /pm-next and related English phrases for this command.wei63wpm-outlineGenerate detailed project outline and draft charter from user intent (empty/new projects). Trigger on /pm-outline and related…wei63wpm-statusShow governance health, iteration progress, and today's Top3 actionable todos. Primary daily entry.wei63wpm-weekly-reviewStructure a PM's weekly review and planning session. Use when doing a weekly PM review, writing a weekly update, preparing for…mohitagw15856pmf-strategyWhen the user wants to validate product-market fit, measure PMF, or plan before scaling. Also use when the user mentions "PMF,"…kostja94podcast-generationGenerate real audio narratives from text content using Azure OpenAI's Realtime API.sickn33podcast-marketingWhen the user wants to plan, create, or market a podcast. Also use when the user mentions "podcast," "podcast strategy," "podcast…kostja94polar-billingThis skill should be used when working on Polar billing system, Stripe integration, subscription lifecycle, checkout flows, or…fcakyonpolarsFast in-memory DataFrame library for datasets that fit in RAM. Use when pandas is too slow but data still fits in memory. Lazy…sickn33policy-drafterDraft an internal policy people can actually follow — the rule stated plainly with its reason, the bright lines separated from…mohitagw15856policy-memoWrite a decision-ready policy memo that frames an issue and recommends an option. Use when asked to write a policy memo, options…mohitagw15856policy-renewal-reviewRun a pre-renewal review of an insurance programme: scan coverage gaps against current operations, test limit adequacy against…mohitagw15856polis-protocol-a-self-optimizing-city-of-agentsPolis Protocol: A Self-Optimizing City of Agentssickn33polis-protocolCoordinate multi-vendor AI agents as a self-improving team — a learning router assigns work by track record and citizens can…sickn33polygon-automationAutomate Polygon tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQpolygon-io-automationAutomate Polygon IO tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQponytail-auditWhole-repo audit for over-engineering. Like ponytail-review, but scans the entire codebase instead of a diff: a ranked list of…0xwilliamortizponytail-debtHarvest every `ponytail:` comment in the codebase into a debt ledger, so the deliberate shortcuts and deferrals ponytail leaves…0xwilliamortizponytail-gainShow ponytail's measured impact as a compact scoreboard: less code, less cost, more speed, from the benchmark medians. One-shot…0xwilliamortizponytail-helpQuick-reference card for all ponytail modes, skills, and commands. One-shot display, not a persistent mode. Trigger…0xwilliamortizponytail-reviewCode review focused exclusively on over-engineering. Finds what to delete: reinvented standard library, unneeded dependencies…0xwilliamortizponytailForces the laziest solution that actually works, simplest, shortest, most minimal. Channels a senior dev who has seen everything…shobcoderpoptin-automationAutomate Poptin tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQpopup-croCreate and optimize popups, modals, overlays, slide-ins, and banners to increase conversions without harming user experience or…sickn33popup-generatorWhen the user wants to add, optimize, or audit popups or modals for lead capture or offers. Also use when the user mentions…kostja94portfolio-pageStructure a portfolio or case-study page that shows your work, not just lists it. Use when asked to write a portfolio page, a…mohitagw15856posix-shell-proExpert in strict POSIX sh scripting for maximum portability across Unix-like systems. Specializes in shell scripts that run on…sickn33postgres-patternsPostgreSQL database patterns for query optimization, schema design, indexing, and security. Based on Supabase best practices.mturacpostgresql-optimizationPostgreSQL database optimization workflow for query tuning, indexing strategies, performance analysis, and production database…sickn33
← Prev116 / 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