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
3,6973,744 · page 78 / 143
context-bankruptcyDeclare bankruptcy on a long-lived AI agent's accumulated memory — audit what it currently believes, separate ground truth from…mohitagw15856context-budgetPlan a session's context window like the budget it is — what loads up front, what gets linked instead, what stays…mohitagw15856context-budgetAudits OpenAI Codex context window consumption across agents, skills, MCP servers, and rules. Identifies bloat, redundant…mturaccontext-compressionWhen agent sessions generate millions of tokens of conversation history, compression becomes mandatory. The naive approach is…sickn33context-degradationLanguage models exhibit predictable degradation patterns as context length increases. Understanding these patterns is essential…sickn33context-driven-developmentGuide for implementing and maintaining context as a managed artifact alongside code, enabling consistent AI interactions and team…sickn33context-engineeringOptimizes agent context setup. Use when starting a new session, when agent output quality degrades, when switching between tasks…addyosmanicontext-engineering-reviewReview what an LLM feature or agent actually puts in its context window — and find what's bloating, missing, or fighting itself.…mohitagw15856context-engineeringMaster the four operations of context engineering — Write, Select, Compress, Isolate. Manage token budgets, compaction…rohitg00context-engineeringOptimizes agent context setup. Use when starting a new session, when agent output quality degrades, when switching between tasks…sickn33context-fundamentalsContext is the complete state available to a language model at inference time. It includes everything the model can attend to…sickn33context-kitEvaluate, adapt, and safely install Context Kit personal context artifacts for Claude Code or adjacent agent workflows.sickn33context-management-context-restoreUse when working with context management context restoresickn33context-management-context-saveUse when working with context management context savesickn33context-managerElite AI context engineering specialist mastering dynamic context management, vector databases, knowledge graphs, and intelligent…sickn33context-modeKeep Claude Code sessions productive across resets with output filtering, session logging, and auto-resume. Use when starting a…mohitagw15856context-optimizationContext optimization extends the effective capacity of limited context windows through strategic compression, masking, caching…sickn33context-optimizerOptimize token usage and context management. Use when sessions feel slow, context is degraded, or you're running out of budget.rohitg00context-switch-budgetTreat context switches as the budget line they are — the switch census (how fragmented the week really is), the batching moves…mohitagw15856context-window-managementStrategies for managing LLM context windows including summarization, trimming, routing, and avoiding context rotsickn33context7-auto-researchAutomatically fetch latest library/framework documentation for Claude Code via Context7 API. Use when you need up-to-date…sickn33continuous-agent-loopPatterns for continuous autonomous agent loops with quality gates, evals, and recovery controls.mturaccontinuous-improvement-loopRun Part 12 — the continuous improvement loop. Aggregates market + operating signals into product/offering recommendations. Runs…indranilbanerjeewritescontract-and-proposal-writerGenerate professional, jurisdiction-aware business documents: freelance contracts, project proposals, SOWs, NDAs, and MSAs.…alirezarezvanicontract-builderConvert approved planning artifacts into an execution contract. Invoke when the user wants to start building, asks to move from…MageByte-Zerocontract-renewal-trackerNever get auto-renewed into another year again — the contract inventory with the dates that matter (notice deadlines, not renewal…mohitagw15856contract-reviewReview and summarise any contract or legal agreement. Use when asked to review a contract, check an agreement, flag legal risks…mohitagw15856contributor-guideWrite a CONTRIBUTING guide that helps people contribute to an open-source project without friction. Use when asked to write a…mohitagw15856control-d-automationAutomate Control D tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQconversation-memoryPersistent memory systems for LLM conversations including short-term, long-term, and entity-based memorysickn33conversion-optimizationWhen the user wants to improve conversion rates, run A/B tests, optimize funnels, or reduce friction. Also use when the user…kostja94conversion-rate-optimizationAudit a landing page or funnel step and produce a prioritised CRO test plan. Use when asked to improve conversion rate, audit a…mohitagw15856conversion-tools-automationAutomate Conversion Tools tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQconvertapi-automationAutomate Convertapi tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQconvertkit-automationAutomate ConvertKit (Kit) tasks via Rube MCP (Composio): manage subscribers, tags, broadcasts, and broadcast stats. Always search…sickn33convexConvex reactive backend expert: schema design, TypeScript functions, real-time subscriptions, auth, file storage, scheduling, and…sickn33conveyor-automationAutomate Conveyor tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQconvolo-ai-automationAutomate Convolo AI tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQcookie-policy-page-generatorWhen the user wants to create or optimize a cookie policy page. Also use when the user mentions "cookie policy," "cookies,"…kostja94copilot-sdkBuild applications that programmatically interact with GitHub Copilot. The SDK wraps the Copilot CLI via JSON-RPC, providing…sickn33copy-editingYou are an expert copy editor specializing in marketing and conversion copy. Your goal is to systematically improve existing copy…sickn33copywritingWhen the user wants to write or optimize short-form marketing copy—headlines, CTAs, ad copy, landing page copy, email copy. Also…kostja94copywritingWrite and rewrite marketing copy for landing pages, homepages, and ads. Useful as a copy chief partner during launches.nexu-iocopywritingWrite rigorous, conversion-focused marketing copy for landing pages and emails. Enforces brief confirmation and strict…sickn33core-componentsCore component library and design system patterns. Use when building UI, using design tokens, or working with the component…sickn33core-web-vitalsWhen the user wants to optimize Core Web Vitals, fix LCP, INP, or CLS issues. Also use when the user mentions "Core Web Vitals,"…kostja94corrently-automationAutomate Corrently tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQcost-aware-llm-pipelineCost optimization patterns for LLM API usage — model routing by task complexity, budget tracking, retry logic, and prompt caching.mturac
← Prev78 / 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