Skill_Seekers and claude-codex-settings
These are complements: A provides the infrastructure to automatically convert various knowledge sources into Claude skills, while B showcases a curated collection of pre-built skills, commands, and MCP servers that exemplify the kinds of artifacts A enables users to create.
About Skill_Seekers
yusufkaraaslan/Skill_Seekers
Convert documentation websites, GitHub repositories, and PDFs into Claude AI skills with automatic conflict detection
Implements Model Context Protocol (MCP) for direct Claude integration and supports 17+ source types (docs sites, repos, PDFs, videos, notebooks, OpenAPI specs, wikis) with intelligent chunking that preserves code context. Exports unified knowledge assets to Claude Skills, RAG frameworks (LangChain, LlamaIndex, Haystack), vector databases, and coding assistants (Cursor, Windsurf, Cline) through a single preprocessing pipeline. Built on Python 3.10+ with 2,540+ tests and 24+ framework-specific presets for production-ready deployments.
About claude-codex-settings
fcakyon/claude-codex-settings
My personal Claude Code and OpenAI Codex setup with battle-tested skills, commands, hooks, agents and MCP servers that I use daily.
Provides modular Claude Code plugins with 20+ integrated MCP servers (Slack, MongoDB, Azure, GitHub, Linear, Supabase, Paper Search) and domain-specific skill bundles for frontend design, academic research, React development, and browser automation. Organizes agents, skills, commands, and hooks through Claude Code's plugin marketplace system with cross-tool compatibility via CLAUDE.md symlinks. Includes production templates for feature development workflows, code architecture analysis, document processing (PDF/Word/Excel), and LLM routing via ccproxy/LiteLLM.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work