Agent Skill Exchange
agentskillexchange/skills
Catálogo confiável de skills para agentes IA com verificação de segurança
Ver no GitHubCatálogo aberto e curado de 2.500+ skills reutilizáveis para agentes IA, com suporte a Claude Code, Cursor, Gemini, MCP e outros. Cada skill encapsula uma ferramenta, API ou workflow real, passando por verificação de segurança e organizado em 17 categorias e 15 coleções por setor.
Instalação
npx convez-ai agentskillexchange/skills1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.
Métricas
Casos de uso
- Instalar e descobrir skills reutilizáveis para aumentar capacidades de agentes IA
- Acessar workflows pré-construídos organizados por indústria (mídia, finanças, legal, saúde, e-commerce)
- Integrar ferramentas e APIs documentadas em pipelines de agentes sem reconstruir do zero
Veredito

Repositório maduro e bem-mantido que resolve um problema real: centralizar skills verificadas para ecossistema de agentes. A cura manual (2.228 skills revisados para segurança) e coletas por setor agregam valor além de um simples dump. Recomendado para quem constrói agentes em escala.
README
A tradução para o português deste README ainda está na fila.
Agent Skill Exchange
Curated and trusted AI agent skills
Catalog · Live Browse · Categories · Industry Collections · Top Starred · Top Downloaded · Submit a Skill
2,586 published skills · 15 Industry Collections · 17 categories · Real ecosystem signals · Updated daily
What is this?
An open, curated catalog of trusted reusable skills for AI agents, not a generic dump. Each skill wraps a real tool, API, or workflow into a format that agents and runtimes like OpenClaw, Claude Code, Codex, Gemini, Cursor, MCP clients, LangChain, OpenAI Agents, Hermes, and custom agent workflows can install and use.
Every skill is backed by a real upstream project — a GitHub repo, npm package, or documented API. No synthetic entries.
Quick Start
# OpenClaw native install
clawhub install <slug>
# Manual install for other agents
git clone https://github.com/agentskillexchange/skills.git
cp -R skills/skills/<slug> ~/.agent-skills/<slug>
Optional Third-Party Installer
The skills npm package is maintained by Vercel Labs / third parties, not AgentSkillExchange. If you choose to use it, pin the package version:
npm exec --package=skills@1.5.7 -- skills add agentskillexchange/skills --skill <slug>
Skill of the Day
Scale agent retrieval workloads with Milvus — Use Milvus to create vector collections, ingest embeddings, and serve filtered similarity search for RAG and agent retrieval workloads.
Rotates daily across downloaded, starred, recent, verified, and industry-curated skills.
Industry Collections
Curated skill sets organized by industry vertical:
| Collection | Description | |
|---|---|---|
| 🎙️ | Media & Publishing Systems | Transcription, subtitles, podcast workflows, chaptering, localization, loudness cleanup, and final-mile publishing prep. |
| 💼 | Finance & Filings | Filings research, invoice intake, billing operations, reconciliation, and finance-adjacent reporting. |
| 🛒 | Ecommerce & Retail Operations | Catalog management, storefront automation, orders, inventory sync, marketplace support, and review-driven merchandising. |
| ⚖️ | Legal Ops & Compliance | Contract workflows, forms, document review, archive search, and evidence-oriented legal and compliance support. |
| 🩺 | Healthcare Documentation & Intake | Documentation intake, OCR, transcription, structured extraction, and biomedical literature support for paperwork-heavy workflows. |
| 📈 | Product Analytics & Growth Ops | Product analytics, feature flags, rollout checks, session replay, privacy-friendly web analytics, and experiment/evaluation workflows. |
| 📚 | DevRel & API Documentation Workflows | API docs, OpenAPI references, SDK generation, docs-site publishing, prose linting, and developer enablement workflows. |
| 🎧 | Customer Support & Success | Helpdesk queues, ticket triage, conversation lookup, knowledge-base workflows, customer context, CRM sync, and reply-drafting support. |
| 🏠 | Real Estate Workflows | Property research support, transaction paperwork, signature routing, document intake, CRM context, and listing follow-up workflows for real-estate operations. |
| 🎓 | Education & Research Workflows | Literature review, citation context, research synthesis, paper drafting, replication checks, and evidence packets for academic and technical teams. |
| 📣 | GTM & RevOps Workflows | Demand generation, SEO and content operations, lifecycle email, CRM enrichment, lead routing, scheduling, feedback capture, and sales/revenue operations workflows. |
| 🧭 | AI Agency Operations & FDE Workflows | Client-facing AI delivery, forward deployed engineering workflows, browser automation, implementation systems, documentation, spreadsheets, proposals, and client handoff workflows. |
| 🛠️ | Infrastructure, SRE & Incident Operations | Production reliability workflows for Kubernetes, incidents, observability, backups, deploy safety, infrastructure drift, alerts, and runbook-driven debugging. |
| 🛡️ | Security Operations & GRC Workflows | Security operations and governance workflows for dependency risk, secrets, CI hardening, agent guardrails, approvals, policy evidence, threat hunting, red-team checks, and audit-ready releases. |
| 🗄️ | Data Platform & Analytics Engineering | Data engineering and analytics operations workflows for SQL, dbt, Airflow, warehouses, Postgres, CSV cleanup, schema quality, backups, lineage, dashboards, and query tuning. |
See the full overlay index in industries/README.md.
Featured Skills
Mirrors the live ASE homepage featured shelf: recent-popular, diversified across tools and categories, rather than a frozen all-time-stars list. See TOP-STARS.md and TOP-DOWNLOADS.md for raw rankings.
| Skill | Tool | ⭐ Stars | Category |
|---|---|---|---|
| Run durable agent tasks and event-driven workflows with Hatchet | run-durable-agent-tasks-and-event-driven-workflows-with-hatchet | 7.2k | Templates & Workflows |
| Render interactive MCP tool UIs with mcp-ui | render-interactive-mcp-tool-uis-with-mcp-ui | 4.9k | Integrations & Connectors |
| Build managed document parsing pipelines with LlamaCloud Services | build-managed-document-parsing-pipelines-with-llamacloud-services | 4.2k | Data Extraction & Transformation |
| Use A2A for agent-to-agent interoperability workflows | use-a2a-for-agent-to-agent-interoperability-workflows | 24.1k | Integrations & Connectors |
| Extract OCR-ready Markdown from documents with Zerox | extract-ocr-ready-markdown-from-documents-with-zerox | 12.2k | Data Extraction & Transformation |
| Use Flowise for visual agent workflow orchestration | use-flowise-for-visual-agent-workflow-orchestration | 53.3k | Templates & Workflows |
| Run terminal-native coding agent workflows with GitHub Copilot CLI | run-terminal-native-coding-agent-workflows-with-github-copilot-cli | 10.6k | Developer Tools |
| Run autonomous deep research workflows with GPT Researcher | run-autonomous-deep-research-workflows-with-gpt-researcher | 27.4k | Research & Scraping |
| Give coding agents persistent project memory with AgentMemory | give-coding-agents-persistent-project-memory-with-agentmemory | 17.2k | Developer Tools |
| Gate agent inputs and outputs with Superagent safety checks | gate-agent-inputs-and-outputs-with-superagent-safety-checks | 6.6k | Security & Verification |
| Use Prompt Flow for LLM workflow testing and evaluation | use-prompt-flow-for-llm-workflow-testing-and-evaluation | 11.1k | Monitoring & Alerts |
| Read Google Drive files and edit Sheets through MCP | read-google-drive-files-and-edit-sheets-through-mcp | 280 | Calendar, Email & Productivity |
Categories
| Category | Skills | What's inside | |
|---|---|---|---|
| 🛠️ | Developer Tools | 337 | CLI tools, scaffolders, dev environment setup |
| 🔒 | Security & Verification | 232 | Vulnerability scanning, auth setup, compliance |
| 🔧 | CI/CD Integrations | 192 | Pipeline configs, deployment automation, build tooling |
| 🔄 | Data Extraction & Transformation | 188 | ETL pipelines, parsing, format conversion |
| ✅ | Code Quality & Review | 184 | Linting, code review, test generators, coverage |
| 📄 | Templates & Workflows | 180 | Scaffolders, boilerplate generators, workflow templates |
| 📋 | Runbooks & Diagnostics | 173 | Incident response, troubleshooting, system diagnostics |
| 📊 | Monitoring & Alerts | 138 | Metrics, alerting rules, observability |
| 🔗 | Integrations & Connectors | 130 | Third-party API bridges, webhooks, service connectors |
| 📅 | Calendar, Email & Productivity | 124 | Email automation, calendar management, task coordination |
| 📚 | Library & API Reference | 122 | SDK docs, API parsers, symbol resolvers |
| 🔍 | Research & Scraping | 112 | Web research, content discovery, data collection |
| 🌐 | Browser Automation | 111 | Web scraping, UI testing, headless browser control |
| 🎙️ | Media & Transcription | 100 | Audio/video processing, speech-to-text |
| 📰 | WordPress & CMS | 96 | Theme/plugin dev, WP-CLI automation, CMS management |
| 🎨 | Image & Creative Automation | 89 | Image generation, asset processing, design automation |
| ✍️ | Content Writing & SEO | 79 | SEO content, blog automation, editorial workflows |
Browse The Catalog
| View | What you'll find | |
|---|---|---|
| 🧭 | Live Browse | Search, filters, skill detail panels, and install links on agentskillexchange.com |
| ⭐ | Top Starred | Skills backed by the most popular GitHub repos |
| 🔥 | Top Downloaded | Skills backed by the most-used npm packages |
| 📖 | Full Catalog | Every skill, sorted by category and stars |
| 🔌 | JSON Index | Machine-readable catalog for programmatic access |
Programmatic Access
JSON Index
skills.json contains every skill with metadata and signals:
{
"name": "Playwright MCP Browser Automation",
"slug": "playwright-mcp-browser-automation",
"title": "Playwright MCP Browser Automation",
"description": "Official Playwright-powered browser control for agent workflows.",
"category": ["Browser Automation"],
"framework": ["Claude Code", "Cursor", "MCP", "OpenClaw"],
"verification": "security_reviewed",
"signals": {
"tool": "playwright",
"github_stars": 84874,
"npm_weekly_downloads": 39806814,
"license": "Apache-2.0"
}
}
Optional Third-Party Installer
The skills npm package is maintained by Vercel Labs / third parties, not AgentSkillExchange. If you choose to use it, pin the package version:
# List all skills
npm exec --package=skills@1.5.7 -- skills add agentskillexchange/skills --list
# Search
npm exec --package=skills@1.5.7 -- skills add agentskillexchange/skills --search kubernetes
# Install
npm exec --package=skills@1.5.7 -- skills add agentskillexchange/skills --skill <slug> -a <agent>
Trust & Safety
Every skill is backed by a real tool, repo, or package. New skills require real provenance before publishing.
| Tier | Count | Meaning |
|---|---|---|
| 📋 Published | 2,586 | In the catalog — every skill is backed by a real tool, repo, or package |
| 🛡️ Security Reviewed | 2,228 | Scanned for malicious patterns, prompt injection, and unsafe instructions |
More: verification/
Submit a Skill
Two ways to add a skill:
Option 1: Pull Request
- Fork this repo
- Copy
template/SKILL.mdtoskills/your-skill-slug/SKILL.md - Fill in the frontmatter and content (see spec/SKILL_SPEC.md)
- Open a PR
Requirements:
- Skill must wrap a real, existing tool (GitHub repo, npm package, documented API)
- Content must be 100+ words with real technical detail
- Must fit an existing category and framework
Option 2: Create Skill Wizard
Use agentskillexchange.com/create-skill to generate a repo-ready SKILL.md, then open a pull request with the generated file.
Skill Format
Each skill is a directory with a SKILL.md:
skills/
playwright-mcp-browser-automation/
SKILL.md
See the full spec and template.