Skill Claude Code
Optimize an AI agent's harness for MCP-Atlas benchmark. Use when analyzing execution traces, diagnosing failures, and proposing improved prompts, skills, or harness code.
not rated 817
+7 1mo ago A 37 tokens
eval
02Skill Claude CodeCodex
Use when evaluating a model on the current benchmark(s).
not rated 22 2mo ago A 13 tokens
original MIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: