Assess Construct Validity

Assess whether a benchmark measures its claimed capability using content, convergent, discriminant, and confound analysis.

yogsoth-ai Updated 512 repo stars
No DARE runtime: 271 SKILL.md files executed by any capable agent, instead of a seven-layer framework stack

File contents

yogsoth-ai/de-anthropocentric-research-engine commit f14d405fa0

Frequently asked questions

npx get-skill add yogsoth-ai/assess-construct-validity