by JSONbored
HeyClaude (formerly Claude Pro Directory) is a searchable collection of pre-built AI skills, agents, MCP servers, guides, hooks, statuslines, and other custom configs, designed to enhance Claude, Codex, Cursor, OpenClaw, and various other agentic workflows/platforms.
# Add to your Claude Code skills
git clone https://github.com/JSONbored/claudepro-directoryGuides for using ai agents skills like claudepro-directory.
Last scanned: 5/30/2026
{
"issues": [],
"status": "PASSED",
"scannedAt": "2026-05-30T15:33:40.741Z",
"npmAuditRan": false,
"pipAuditRan": true
}claudepro-directory is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by JSONbored. HeyClaude (formerly Claude Pro Directory) is a searchable collection of pre-built AI skills, agents, MCP servers, guides, hooks, statuslines, and other custom configs, designed to enhance Claude, Codex, Cursor, OpenClaw, and various other agentic workflows/platforms. It has 216 GitHub stars.
Yes. claudepro-directory passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.
Clone the repository with "git clone https://github.com/JSONbored/claudepro-directory" and add it to your Claude Code skills directory (see the Installation section above).
claudepro-directory is primarily written in MDX. It is open-source under JSONbored on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh claudepro-directory against similar tools.
No comments yet. Be the first to share your thoughts!
⚠️ Third-Party Software Notice
This skill is third-party open-source software developed and hosted independently on GitHub. SkillsLLM is an informational directory and does not control or maintain the underlying repository.
Any security checks, ratings, or warnings displayed by SkillsLLM are automated and limited in scope. They do not constitute a security certification or guarantee that the software is safe, error-free, or free from malicious code, vulnerabilities, compromised dependencies, or prompt-injection risks.
Review the source code, permissions, dependencies, and configuration before installing or running any third-party skill. Use is at your own risk. To the maximum extent permitted by applicable law, SkillsLLM is not liable for losses arising from third-party software.
Discover and share the best Claude configurations 381+ file-backed entries covering agents, MCP servers, tools, skills, hooks, rules, commands, guides, collections, and statuslines.
Website • Browse • Jobs • Submit • API • MCP • Discussions
Feeds • RSS • Atom • LLM export • Raycast • MCP endpoint • Claim/update
HeyClaude is a fast, GitHub-native directory for Claude assets.
| Section | Entries | Scope |
|---|---|---|
| Agents | 39 | Specialized Claude agents and expert roles. |
| MCP Servers | 45 | Model Context Protocol servers and integrations. |
| Tools | 52 | Apps, developer tools, services, and products for Claude-native builders. |
| Skills | 68 | Installable skill packs and reusable capabilities. |
| Rules | 29 | Prompt guardrails, project rules, and operating constraints. |
| Commands | 27 | Slash commands and reusable command prompts. |
| Hooks | 66 | Claude Code hook configs and automation helpers. |
| Guides | 19 | Long-form guides and practical walkthroughs. |
| Collections | 10 | Curated bundles of related assets. |
| Statuslines | 26 | Statusline scripts and workflow telemetry. |
/api/registry/feed/platformspackages/mcp/api/mcp/jobs/jobs/post/llms-full.txt/feed.xml/atom.xmlOption A (recommended): open Submit and use the category issue form.
Option B (direct): open a category issue form in GitHub under .github/ISSUE_TEMPLATE.
Option C (advanced): open a pull request with content files directly.
Free Claude resources use issue-first intake by default. Maintainers review, validate, and approve accepted submissions before automation opens an import PR. Tool/app/service promotion, listing claims, and jobs use the website lead forms instead of GitHub content issues.
content/<category>/pnpm --filter web run prebuildpnpm validate:content:strict, pnpm validate:issue-templates, pnpm validate:clean, pnpm audit:content, pnpm validate:emails, pnpm test:mcp, pnpm test:registry-artifacts, pnpm test:seo-jsonld, and pnpm test:commercial-intakepnpm generate:issue-templates and pnpm generate:readme if registry categories or content counts changed