anthropics — 8 Open-Source AI Agent Skills

anthropics is the organization behind 8 open-source AI agent skills and MCP servers spanning claude-skill, with a combined 376,167+ GitHub stars. On AgentSkillsHub each is quality-scored (avg 62/100) and security-graded — 8 verified safe.

Top skills by anthropics

• skills — Public repository for Agent Skills (175.7k★ · quality 63/100 · security: safe)
• claude-code — Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine (146.9k★ · quality 63/100 · security: safe)
• claude-plugins-official — Official, Anthropic-managed directory of high quality Claude Code Plugins. (36.5k★ · quality 64/100 · security: safe)
• claude-code-action — (8.9k★ · quality 48/100 · security: safe)
• claude-code-security-review — An AI-powered security review GitHub Action using Claude to analyze code changes for security vulnerabilities. (6.3k★ · quality 73/100 · security: safe)
• launch-your-agent — Claude Code skills that take a founder from idea to a live Claude Managed Agent: interview, scope a v0, launch in their own account, grade i (927★ · quality 63/100 · security: safe)
• life-sciences — Repo for the Claude Code Marketplace to use with the Claude for Life Sciences Launch. This will continue to host the marketplace.json long-t (566★ · quality 67/100 · security: safe)
• claude-ai-mcp — Report issues related to MCP integration with Claude here. (432★ · quality 53/100 · security: safe)

View anthropics on GitHub · Explore audited agent skills