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
3,9373,984 · page 83 / 143
design-reviewDesigner Who Codes: visual audit then fixes with atomic commits and before/after screenshots. Useful for tightening shipped UI…nexu-iodesign-system-auditAudit a design system for consistency, coverage, and quality. Use when asked to audit a design system, review a component…mohitagw15856design-systemUse this skill to generate or audit design systems, check visual consistency, and review PRs that touch styling.mturacdesign-taste-frontendUse when building high-agency frontend interfaces with strict design taste, calibrated color, responsive layout, and motion rules.sickn33design-thinkingDirection and intent for frontend design. Use with design when defining purpose, tone, domain, color world, and review bar…sickn33design-uxUX / usability audit — heuristic evaluation of INTERACTIVE UIs (not just visual polish). Load with design when a UI "feels off"…sickn33designing-architectureDesigns software architecture and selects appropriate patterns for projects. Use when designing systems, choosing architecture…CloudAI-Xdesigning-testsDesigns and implements testing strategies for any codebase. Use when adding tests, improving coverage, setting up testing…CloudAI-Xdesk-research-sprintRun a timeboxed desk-research sprint that ends with an answer instead of forty tabs — the question decomposition, the source plan…mohitagw15856desktime-automationAutomate Desktime tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQdesktop-zeroClear the desktop that's become a hundred-icon guilt mosaic — the fast triage that empties it today, the honest read of what the…mohitagw15856deslopUse when user wants to clean AI slop from code. Use for cleanup, remove debug statements, find ghost code, repo hygiene.agent-shdeslopRemove AI-generated code slop, unnecessary comments, and over-engineering from the current branch diff. Cleans up boilerplate…rohitg00deterministic-designRender the UI and prove it's balanced + usable: a deterministic layout audit (centroid / optical-center / pixel-oracle balance…sickn33detrack-automationAutomate Detrack tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQdevcontainer-setupCreates devcontainers with Claude Code, language-specific tooling (Python/Node/Rust/Go), and persistent volumes. Use when adding…sickn33developer-growth-analysisAnalyzes your recent Claude Code chat history to identify coding patterns, development gaps, and areas for improvement, curates…ComposioHQdeveloper-onboarding-docWrite a developer onboarding document for a service, codebase, or team. Use when asked to write a developer guide, service…mohitagw15856developmentComprehensive web, mobile, and backend development workflow bundling frontend, backend, full-stack, and mobile development skills…sickn33devils-twinThe strongest possible case AGAINST what you just wrote — argued to win, not to check a box. Use when a document is about to ship…mohitagw15856devops-deployDevOps e deploy de aplicacoes — Docker, CI/CD com GitHub Actions, AWS Lambda, SAM, Terraform, infraestrutura como codigo e…sickn33devops-infrastructureGuides Docker, CI/CD pipelines, deployment strategies, infrastructure as code, and observability setup. Use when writing…CloudAI-Xdevops-troubleshooterExpert DevOps troubleshooter specializing in rapid incident response, advanced debugging, and modern observability.sickn33dialmycalls-automationAutomate Dialmycalls tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQdialpad-automationAutomate Dialpad tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQdictionary-api-automationAutomate Dictionary API tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQdictionary-lookupLook up word definitions, pronunciation, etymology and synonyms with zero API keys — the Free Dictionary API via curl, with…mohitagw15856diffbot-automationAutomate Diffbot tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQdifferential-reviewSecurity-focused code review for PRs, commits, and diffs.sickn33difficult-conversationPrepare for and script a hard conversation — conflict, bad news, a boundary, an apology. Use when asked to prepare for a…mohitagw15856digicert-automationAutomate Digicert tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQdigital-legacy-plannerPlan what happens to your digital life — the account inventory, the access plan that doesn't violate terms or law, platform…mohitagw15856digital-ocean-automationAutomate DigitalOcean tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQdirectory-listing-adsWhen the user wants to run paid ads within directories or marketplaces. Also use when the user mentions "Taaft ads," "Shopify App…kostja94directory-submissionWhen the user wants to submit a product or app to directories, curated lists, launch platforms, or app stores—and needs…kostja94disaster-recovery-planWrite a disaster recovery plan for a service or system — covering RPO/RTO targets, failure scenario runbooks, backup and restore…mohitagw15856discharge-summaryTurn a hospital stay into a complete, well-structured discharge summary. Use when asked to write a discharge summary, a hospital…mohitagw15856disclosure-page-generatorWhen the user wants to create, optimize, or audit an affiliate, sponsor, or paid partnership disclosure page. Also use when the…kostja94discord-automationAutomate Discord tasks via Rube MCP (Composio): messages, channels, roles, webhooks, reactions. Always search tools first for…sickn33discord-bot-architectSpecialized skill for building production-ready Discord bots. Covers Discord.js (JavaScript) and Pycord (Python), gateway…sickn33discordbot-automationAutomate Discordbot tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQdiscount-marketing-strategyWhen the user wants to plan, implement, or optimize discount and promotional pricing strategy. Also use when the user mentions…kostja94discover-tasksUse when user asks to \"discover tasks\", \"find next task\", \"prioritize issues\", \"what should I work on\", or \"list open…agent-shdiscovery-call-prepPrepare a structured discovery call plan for any prospect. Use when asked to prepare for a sales call, discovery call, prospect…mohitagw15856discovery-eyesRead your team's messages the way opposing counsel would in litigation discovery — prevention training that makes communication…mohitagw15856dispatchDelegate tasks to OpenAI Codex CLI and Google Antigravity CLI from Claude Code with topic-aware sessionssickn33dispatching-parallel-agentsUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciessickn33display-adsWhen the user wants to run display, banner, or ad network campaigns. Also use when the user mentions "display ads," "banner ads,"…kostja94
← Prev83 / 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