MrBinnacle / skill-harnessView on GitHub
How do you KNOW if a 'skill' is any good - deterministically? This runs controlled skill-vs-no-skill experiments. It doesn't just ask, “Did the skill work?” It asks “Did we actually give the skill to the model, did the comparison remain fair, what changed, what did it cost, and do we have enough evidence to say that confidently?”
☆14Oct 19, 2026Updated this week

Alternatives and similar repositories for skill-harness

Users that are interested in skill-harness are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.

Sorting:

Are these results useful?