ComposioHQ — 11 Open-Source AI Agent Skills
ComposioHQ is the organization behind 11 open-source AI agent skills and MCP servers spanning mcp-server, codex-skill, claude-skill, agent-tool, with a combined 130,821+ GitHub stars. On AgentSkillsHub each is quality-scored (avg 69/100) and security-graded — 10 verified safe.
Top skills by ComposioHQ
- awesome-claude-skills — A curated list of awesome Claude Skills, resources, and tools for customizing Claude AI workflows (75.3k★ · quality 67/100 · security: safe)
- composio — Composio powers 1000+ toolkits, tool search, context management, authentication, and a sandboxed workbench to help you build AI agents that (30.3k★ · quality 67/100 · security: safe)
- awesome-codex-skills — A curated list of practical Codex skills for automating workflows across the Codex CLI and API. (9.7k★ · quality 69/100 · security: safe)
- agent-orchestrator — Agentic orchestrator for parallel coding agents — plans tasks, spawns agents, and autonomously handles CI fixes, merge conflicts, and cod (7.4k★ · quality 76/100 · security: safe)
- open-claude-cowork — Open Source version of Claude Cowork with 500+ SaaS app integrations (4.1k★ · quality 76/100 · security: safe)
- awesome-claude-plugins — A curated list of Plugins that let you extend Claude Code with custom commands, agents, hooks, and MCP servers through the plugin system. (1.6k★ · quality 68/100 · security: safe)
- secure-openclaw — A personal 24x7 AI assistant like OpenClaw that runs on your messaging platforms. Send a message on WhatsApp, Telegram, Signal, or iMessage (1.2k★ · quality 77/100 · security: safe)
- trustclaw — A self-hostable personal AI agent with vector memory, Composio tools, and Telegram. (873★ · quality 65/100 · security: safe)
View ComposioHQ on GitHub · Explore audited agent skills