eval

Evaluate and rank agent results by metric or LLM judge for an AgentHub session. Use when the user runs /hub:eval or asks to score, compare, or pick a winner among completed AgentHu

Skills for Claude Code · Analytica Claude.

All skills

// Claude skill & agent registry

Find the right skill for the job.

Browse, search and score 2,100+ Claude skills and 155+ agents — or connect the MCP and let Claude pull the right one on demand.

Library  ·  Active

    No skills match those filters.

    Add a skill from GitHub