I A/B-tested 9 popular AI agent skills. 4 of them did nothing.

Automated excerpt

Some skill repos have hundreds of thousands of stars. Harder eval cases are the most useful thing credential access, the skill spec, and how many tokens a skill pack adds to every session. That's how the next skill gets written, with its eval first.

Selected automatically from source text; not independently written or fact-checked. Read the original for full context.