agent-skills-cli and agent-skills
The two tools are competitors, as the significantly more popular `agent-skills-cli` aims to be a universal interface for accessing a vast range of skills from a marketplace and syncing them to various agent platforms, while `agent-skills` offers a more limited collection of skills for specific AI agents.
About agent-skills-cli
Karanjot786/agent-skills-cli
Universal CLI for Agent Skills. Access 40,000+ skills from SkillsMP and sync them to Cursor, Claude Code, GitHub Copilot, OpenAI Codex, and Antigravity.
Provides token-aware context budgeting, conflict detection, and quality scoring (0–100) across skills before installation. Syncs deterministically via lockfiles and supports private Git repos, npm registries, and 45+ AI agents through platform-specific config files. Built around a modular skill composition system allowing merging, chaining, and conditional loading with integrated testing and sandbox preview capabilities.
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