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
2,8332,880 · page 60 / 143
account-planBuild a structured account plan for any key customer or target account. Use when asked to create an account plan, key account…mohitagw15856accredible-certificates-automationAutomate Accredible Certificates tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQacculynx-automationAutomate Acculynx tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQactive-campaign-automationAutomate ActiveCampaign tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQactivecampaign-automationAutomate ActiveCampaign tasks via Rube MCP (Composio): manage contacts, tags, list subscriptions, automation enrollment, and…sickn33ad-campaign-analyzerAnalyze cross-channel campaign data, quantify uncertainty, and propose evidence-labeled budget tests without overstating…sickn33ad-copyWrite platform-native paid ad copy with multiple angles to test. Use when asked to write ad copy…mohitagw15856ad-creativeGenerate platform-specific ad copy. Use when: Google RSA, Meta, LinkedIn, TikTok ad variations with quality scoring.indranilbanerjeead-creativeGenerate and iterate ad creative including headlines, descriptions, and primary text. Useful for paid social and search ad…nexu-ioadd-integrationAdd MCP server integrations. Use when: connecting a custom tool, API, or service to the plugin via .mcp.json.indranilbanerjeeadding-a-commandCreates a new CLI command following the Commander.js pattern in src/commands/. Handles command registration in src/cli.ts…caliber-ai-orgaddress-github-commentsUse when you need to address review or issue comments on an open GitHub Pull Request using the gh CLI.sickn33addresszen-automationAutomate Addresszen tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQadhd-output-styleThis skill should be used when the user asks for "ADHD output", "fewer output tokens", "short numbered steps", "limited working…fcakyonadobe-automationAutomate Adobe tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQadrapid-automationAutomate Adrapid tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQadvanced-evaluationThis skill should be used when the user asks to "implement LLM-as-judge", "compare model outputs", "create evaluation rubrics"…sickn33adversarial-reviewerAdversarial code review that breaks the self-review monoculture. Use when you want a genuinely critical review of recent changes…alirezarezvaniadvogado-criminalAdvogado criminalista especializado em Maria da Penha, violencia domestica, feminicidio, direito penal brasileiro, medidas…sickn33adyntel-automationAutomate Adyntel tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQaegisops-aiAutonomous DevSecOps & FinOps Guardrails. Orchestrates Gemini 3 Flash to audit Linux Kernel patches, Terraform cost drifts, and…sickn33aeo-auditAudit AI search visibility. Use when: checking brand presence in ChatGPT, Perplexity, AI Overviews, Gemini.indranilbanerjeeaeo-optimizerOptimize an article for Answer Engine Optimization (AEO) so AI engines like ChatGPT, Perplexity, and Claude can extract, quote…mohitagw15856aero-workflow-automationAutomate Aero Workflow tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQaeroleads-automationAutomate Aeroleads tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQaffiliate-marketingWhen the user wants to plan, implement, or optimize affiliate marketing strategy. Also use when the user mentions "affiliate…kostja94affiliate-page-generatorWhen the user wants to create, optimize, or audit affiliate program page content. Also use when the user mentions "affiliate…kostja94affinda-automationAutomate Affinda tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQaffinity-automationAutomate Affinity tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQagency-dashboardPortfolio-level agency dashboard aggregating health metrics across all client brands — campaign status, budget pacing, KPI…indranilbanerjeeagencyzoom-automationAutomate Agencyzoom tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQagenda-or-cancelEnforce the simplest meeting rule that works — no agenda, no meeting — with the three-line agenda format (purpose, decisions…mohitagw15856agent-architecture-auditFull-stack diagnostic for agent and LLM applications. Audits the 12-layer agent stack for wrapper regression, memory pollution…mturacagent-browserAutomates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to…code-yeongyuagent-browserBrowser automation CLI for AI agents. Use when the user needs to inspect, test, or automate browser behavior: navigating pages…nexu-ioagent-creatorCreate custom AI subagents with proper plugin structure, persona generation, and companion routing skills.sickn33agent-design-reviewReview an LLM agent design and find where it will be unreliable, expensive, or unsafe. Use when asked to review an agent…mohitagw15856agent-era-pricingRedesign seat-based pricing for the agent era — when one human runs ten agents, per-seat models collapse. Use when agents are…mohitagw15856agent-evalHead-to-head comparison of coding agents (OpenAI Codex, Aider, Codex, etc.) on custom tasks with pass rate, cost, time, and…mturacagent-evaluationTesting and benchmarking LLM agents including behavioral testing, capability assessment, reliability metrics, and production…sickn33agent-framework-azure-ai-pyBuild persistent agents on Azure AI Foundry using the Microsoft Agent Framework Python SDK.sickn33agent-harness-constructionDesign and optimize AI agent action spaces, tool definitions, and observation formatting for higher completion rates.mturacagent-hiring-panelHire an AI agent the way you'd hire an employee — a role spec with success criteria, a structured work-sample interview run on…mohitagw15856agent-incident-postmortemRun a blameless postmortem for an incident caused by an AI agent or LLM feature — hallucinated facts shipped to users, runaway…mohitagw15856agent-interface-designDesign tools, scripts, and CLIs that an agent will call, so the interface teaches its own use instead of a wall of prose and…Neeeophyteeagent-introspection-debuggingStructured self-debugging workflow for AI agent failures using capture, diagnosis, contained recovery, and introspection reports.mturacagent-mail-automationAutomate Agent Mail tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQagent-manager-skillManage multiple local CLI agents via tmux sessions (start/stop/monitor/assign) with cron-friendly scheduling.sickn33
← Prev60 / 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