skillport and agent-skills
These are competitors—both provide skill/tool management frameworks for AI agents, but skillport offers broader multi-agent compatibility (CLI, MCP) and distribution, while agent-skills is purpose-built specifically for Anthropic's ecosystem (Claude, Clawdbot).
About skillport
gotalab/skillport
Bring Agent Skills to Any AI Agent and Coding Agent — via CLI or MCP. Manage once, serve anywhere.
Provides spec-compliant skill validation and full lifecycle management (install, update, remove) from GitHub or local sources, with programmatic metadata control. Implements a search-first architecture via MCP and CLI modes—metadata loads upfront while full skill instructions load on-demand—reducing context overhead when managing 50+ skills. Targets MCP-compatible clients (Cursor, Copilot, Windsurf, Cline) and agents with shell access, supporting category/tag filtering and per-client skill exposure through environment configuration.
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