awesome-skills and agent-skills
Both tools are collections of AI agent skills, making them competitors where a user would likely choose one over the other based on the specific skills offered and the maturity of the project (as suggested by the star count).
About awesome-skills
gmh5225/awesome-skills
A curated list of Agent Skills, resources, and tools for AI coding agents like Claude Code, Codex, Gemini CLI, GitHub Copilot, and more.
The collection organizes Skills using a **progressive disclosure architecture** where agents first scan lightweight metadata (~100 tokens) to identify relevance, then load full instructions (<5k tokens) and bundled resources on-demand—minimizing token overhead. Skills are standardized as folders with `SKILL.md` metadata files plus optional scripts, templates, and resources, enabling dynamic discovery across 15+ agent platforms (Claude Code, Copilot, Cursor, Gemini CLI, Codex, and conversational tools like Coze). The registry maps platform-specific skill directories and includes official implementations from Anthropic, OpenAI, HuggingFace, and Vercel teams.
About agent-skills
jdrhyne/agent-skills
A collection of AI agent skills for Clawdbot, Claude Code, Codex
Includes modular skills for analytics (GA4, Google Ads), project management (JIRA), document processing (Nutrient), and system orchestration, each with security scanning via AgentVerus to detect prompt injection and data exfiltration. Skills are organized by compatibility tier—79% work universally across OpenClaw, Claude Code, and Codex through a standardized read/write/exec interface, while platform-specific variants enable deeper integrations. The architecture supports both structured workflow tools and pure instruction prompts, with MCP server support for document automation and external API integrations.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work