Categories Β· Industry Collections Β· Top Starred Β· Top Downloaded Β· Catalog Β· Submit a Skill
2,471 published skills Β· 17 categories Β· Real ecosystem signals Β· Updated hourly
An open, machine-readable catalog of reusable skills for AI coding agents. Each skill wraps a real tool, API, or workflow into a format that agents like Claude Code, Cursor, Codex, and OpenClaw can install and use.
Every skill is backed by a real upstream project β a GitHub repo, npm package, or documented API. No synthetic entries.
# 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>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>Route Claude Code requests across models and providers with Claude Code Router β Run Claude Code through Claude Code Router to route coding-agent requests by task, provider, or model while preserving terminal workflows and adding provider-specific transformations.
Rotates daily by UTC date from the Security Reviewed pool.
Curated skill sets organized by industry vertical:
| Collection | Description | |
|---|---|---|
| ποΈ | Media & Publishing Systems | Transcription, subtitles, podcast workflows, chaptering, localization, loudness cleanup, and final-mile publishing prep. |
| πΌ | Finance & Filings | Filings research, invoice intake, billing operations, reconciliation, and finance-adjacent reporting. |
| π | Ecommerce & Retail Operations | Catalog management, storefront automation, orders, inventory sync, marketplace support, and review-driven merchandising. |
| βοΈ | Legal Ops & Compliance | Contract workflows, forms, document review, archive search, and evidence-oriented legal and compliance support. |
| π©Ί | Healthcare Documentation & Intake | Documentation intake, OCR, transcription, structured extraction, and biomedical literature support for paperwork-heavy workflows. |
| π | Product Analytics & Growth Ops | Product analytics, feature flags, rollout checks, session replay, privacy-friendly web analytics, and experiment/evaluation workflows. |
| π | DevRel & API Documentation | API docs, OpenAPI references, SDK generation, docs-site publishing, prose linting, and developer enablement workflows. |
| π§ | Customer Support & Success | Helpdesk queues, ticket triage, conversation lookup, knowledge-base workflows, customer context, CRM sync, and reply-drafting support. |
| π | Real Estate Workflows | Property research support, transaction paperwork, signature routing, document intake, CRM context, and listing follow-up workflows for real-estate operations. |
See the full overlay index in industries/README.md.
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 | β Stars | Category |
|---|---|---|---|
| Route Claude Code requests across models and providers with Claude Code Router | route-claude-code-requests-across-models-and-providers-with-claude-code-router | 33.9k | Developer Tools |
| Parse local PDFs into agent-ready text, JSON, and screenshots with LiteParse | parse-local-pdfs-into-agent-ready-text-json-and-screenshots-with-liteparse | 5.1k | Data Extraction & Transformation |
| Run long-horizon spec-driven coding agent workflows with GSD 2 | run-long-horizon-spec-driven-coding-agent-workflows-with-gsd-2 | 7.3k | Templates & Workflows |
| Build and inspect MCP apps and servers with mcp-use | build-and-inspect-mcp-apps-and-servers-with-mcp-use | 9.9k | Integrations & Connectors |
| Preserve coding-agent context by sandboxing bulky tool output and retrieving only relevant session state with Context Mode | preserve-coding-agent-context-by-sandboxing-bulky-tool-output-and-retrieving-only-relevant-session-state-with-context-mode | 10k | Developer Tools |
| Find likely duplicate GitHub issues through parallel search and evidence filtering with Claude Code dedupe | find-likely-duplicate-github-issues-through-parallel-search-and-evidence-filtering-with-claude-code-dedupe | 116.8k | Templates & Workflows |
| Trace, evaluate, and monitor agentic workflows with Opik | trace-evaluate-and-monitor-agentic-workflows-with-opik | 19.1k | Monitoring & Alerts |
| Build temporal context graphs for agent memory from evolving facts with Graphiti | build-temporal-context-graphs-for-agent-memory-from-evolving-facts-with-graphiti | 24.9k | Library & API Reference |
| Run long-horizon research and coding agent workflows with DeerFlow | run-long-horizon-research-and-coding-agent-workflows-with-deerflow | 67.5k | Code Quality & Review |
| Run stealth Chromium browser automation with CloakBrowser | run-stealth-chromium-browser-automation-with-cloakbrowser | 10.2k | Browser Automation |
| Preserve agent session context with Claude Mem | preserve-agent-session-context-with-claude-mem | 74.5k | Library & API Reference |
| Optimize prompt and agent pipelines with DSPy programs and evaluators | optimize-prompt-and-agent-pipelines-with-dspy-programs-and-evaluators | 34.3k | Code Quality & Review |
| Category | Skills | What's inside | |
|---|---|---|---|
| π οΈ | Developer Tools | 314 | CLI tools, scaffolders, dev environment setup |
| π | Security & Verification | 226 | Vulnerability scanning, auth setup, compliance |
| π§ | CI/CD Integrations | 192 | Pipeline configs, deployment automation, build tooling |
| β | Code Quality & Review | 183 | Linting, code review, test generators, coverage |
| π | Data Extraction & Transformation | 170 | ETL pipelines, parsing, format conversion |
| π | Runbooks & Diagnostics | 169 | Incident response, troubleshooting, system diagnostics |
| π | Templates & Workflows | 158 | Scaffolders, boilerplate generators, workflow templates |
| π | Monitoring & Alerts | 129 | Metrics, alerting rules, observability |
| π | Calendar, Email & Productivity | 122 | Email automation, calendar management, task coordination |
| π | Library & API Reference | 121 | SDK docs, API parsers, symbol resolvers |
| π | Integrations & Connectors | 118 | Third-party API bridges, webhooks, service connectors |
| π | Browser Automation | 106 | Web scraping, UI testing, headless browser control |
| π | Research & Scraping | 104 | Web research, content discovery, data collection |
| ποΈ | Media & Transcription | 98 | Audio/video processing, speech-to-text |
| π° | WordPress & CMS | 96 | Theme/plugin dev, WP-CLI automation, CMS management |
| π¨ | Image & Creative Automation | 89 | Image generation, asset processing, design automation |
| βοΈ | Content Writing & SEO | 77 | SEO content, blog automation, editorial workflows |
| View | What you'll find | |
|---|---|---|
| β | Top Starred | Skills backed by the most popular GitHub repos |
| π₯ | Top Downloaded | Skills backed by the most-used npm packages |
| π | Full Catalog | Every skill, sorted by category and stars |
| π | JSON Index | Machine-readable catalog for programmatic access |
skills.json contains every skill with metadata and signals:
{
"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"
}
}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>Every skill is backed by a real tool, repo, or package. New skills require real provenance before publishing.
| Tier | Count | Meaning |
|---|---|---|
| π Published | 2,471 | In the catalog β every skill is backed by a real tool, repo, or package |
| π‘οΈ Security Reviewed | 2,466 | Scanned for malicious patterns, prompt injection, and unsafe instructions |
More: verification/
Two ways to add a skill:
- 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
Submit through agentskillexchange.com/create-skill β auto-synced to this repo hourly.
Each skill is a directory with a SKILL.md:
skills/
playwright-mcp-browser-automation/
SKILL.md
See the full spec and template.