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
4,1294,176 · page 87 / 143
enhance-claude-memoryUse when improving CLAUDE.md or AGENTS.md project memory files.agent-shenhance-cross-fileUse when checking cross-file consistency: tools vs frontmatter, agent references, duplicate rules, contradictions.agent-shenhance-docsUse when improving documentation structure, accuracy, and RAG readiness.agent-shenhance-hooksUse when reviewing hooks for safety, timeouts, and correct frontmatter.agent-shenhance-orchestratorUse when coordinating multiple enhancers for /enhance command. Runs analyzers in parallel and produces unified report.agent-shenhance-pluginsUse when analyzing plugin structures, MCP tools, and plugin security patterns.agent-shenhance-promptImprove prompts with design specs and UI/UX vocabulary. Useful for design-to-code workflows and clarifying requests for visual…nexu-ioenhance-promptTransforms vague UI ideas into polished, Stitch-optimized prompts. Enhances specificity, adds UI/UX keywords, injects design…sickn33writesenhance-promptsUse when improving general prompts for structure, examples, and constraints.agent-shenhance-skillsUse when reviewing SKILL.md files for structure and trigger quality.agent-shenigma-automationAutomate Enigma tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQentelligence-automationAutomate Entelligence tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQenterprise-agent-opsOperate long-lived agent workloads with observability, security boundaries, and lifecycle management.mturacentity-auditAudit brand entity consistency. Use when: checking Wikidata, Knowledge Panel, or directory discrepancies.indranilbanerjeeentity-relationship-diagramTurn a data model into an entity-relationship (ER) diagram. Use when asked to design a schema, model data, show how…mohitagw15856entity-seoWhen the user wants to optimize for entity recognition, Knowledge Graph, or entity-based SEO. Also use when the user mentions…kostja94environment-setup-guideGuide developers through setting up development environments with proper tools, dependencies, and configurationssickn33eodhd-apis-automationAutomate Eodhd Apis tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQepic-games-automationAutomate Epic Games tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQepic-progress-reportReport on an epic or initiative deeper than a status bullet — child work broken down by status, the riskiest unfinished pieces…mohitagw15856error-debugging-multi-agent-reviewUse when working with error debugging multi agent reviewsickn33error-decoderDecode an error message or stack trace into a plain-English cause, the exact fix, and how to prevent it. Use when asked to…mohitagw15856error-diagnostics-smart-debugUse when working with error diagnostics smart debugsickn33error-handlingImplements error handling patterns, structured logging, retry strategies, circuit breakers, and graceful degradation. Use when…CloudAI-Xerror-handlingPatterns for robust error handling across TypeScript, Python, and Go. Covers typed errors, error boundaries, retries, circuit…mturacerror-message-writerWrite clear, helpful error messages that tell users what happened and how to fix it. Use when asked to write an error message…mohitagw15856escalation-emailEscalate an issue up the chain without burning the person you're escalating past — the facts-first structure, the tried-already…mohitagw15856escalation-treeDesign a support/incident escalation tree — who handles what, when it escalates, and to whom. Use when asked to design an…mohitagw15856esg-disclosure-draftDraft an honest, audit-ready ESG disclosure section in a CSRD/ESRS-flavored structure, adaptable to other frameworks. Use when…mohitagw15856esignatures-io-automationAutomate Esignatures IO tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQespocrm-automationAutomate Espocrm tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQesputnik-automationAutomate Esputnik tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQestate-planning-kitGet your affairs in order before you need to — a will/beneficiary/healthcare-directive checklist and the 'what my family needs to…mohitagw15856estate-settlement-organizerOrganize an executor's work — the settlement ladder from will-to-probate-to-distribution, the asset/debt inventory, the creditor…mohitagw15856etermin-automationAutomate Etermin tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQethical-hacking-methodologyMaster the complete penetration testing lifecycle from reconnaissance through reporting. This skill covers the five stages of…sickn33eulogy-writerHelp someone write a eulogy — the hardest writing most people ever do, at the worst possible time. Use when someone must speak at…mohitagw15856euthanasia-conversationGuide a veterinary team through a compassionate end-of-life conversation with a pet owner — quality-of-life assessment, the…mohitagw15856eval-configConfigure content eval settings. Use when: adjusting score thresholds, dimension weights, or auto-reject rules.indranilbanerjeeeval-contentEvaluate content quality. Use when: scoring drafts, checking hallucinations, or assessing brand voice compliance.indranilbanerjeeeval-harnessFormal evaluation framework for OpenAI Codex sessions implementing eval-driven development (EDD) principlesmturaceval-injection-testSkill with injected eval patterns for security testingrohitg00eval-rubric-designerDesign a scoring rubric and LLM-as-judge prompt to evaluate the quality of an AI feature's output. Use when asked to create an…mohitagw15856eval-suiteBatch evaluate multiple content pieces. Use when: scoring a content library, campaign assets, or deliverable set.indranilbanerjeeevaluationBuild evaluation frameworks for agent systems. Use when testing agent performance systematically, validating context engineering…sickn33evenium-automationAutomate Evenium tasks via Rube MCP (Composio). Always search tools first for current schemas.ComposioHQevent-sourcing-architectExpert in event sourcing, CQRS, and event-driven architecture patterns. Masters event store design, projection building, saga…sickn33event-staffing-complianceAssess worker-classification and compliance risk for temporary event staffing in the US and Canada — W-2 vs 1099…sickn33
← Prev87 / 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