suyoumo/clawprobench

ClawProBench is a live-first benchmark harness for evaluating LLM agents in the OpenClaw runtime with deterministic grading and repeated-trial reliability.

5.0 / 10
Established • Skills Mode

Solid, but check the details before adopting.

Dimensions

Alive
5.6
Legit
4.0
Solid
5.4
Usable
5.0

Repository Stats

Stars
453
Forks
38
License
Apache-2.0
Mode
Skills

Embed this badge

Add the MCP Skills trust badge to your README to show current status.

MCP Skills trust badge
[![MCP Skills](https://mcpskills.io/.netlify/functions/badge?repo=suyoumo%2Fclawprobench)](https://mcpskills.io/score/suyoumo/clawprobench)
Want the full 14-signal breakdown?
Unlock safety scan findings, signal-level scores, and actionable recommendations.
Get the full report →