run-benchmark
Facilitates MCP evaluations using mcpbr on SWE-bench datasets, ensuring valid and reproducible benchmarking for AI agents.
Install this skill
or
run-benchmark2 files
Comments
Sign in to leave a comment.
No comments yet. Be the first to comment!
GitHub Stars 2
Rate this skill
Categorydata analytics
UpdatedMay 21, 2026
majiayu000/claude-skill-registry-data