Evaluate Ghostwriter

Runs blind, human-labeled baseline-versus-profile evaluations through a locally authenticated Codex or Claude Code CLI. Measures whether the exact ghostwriter skill and private platform profiles improve resemblance to held-out writing. Use when asked to "evaluate my voice", "test my voice profile", compare writing with and without the ghostwriter skill, review blind A/B candidates, or report voice evaluation results. Use train-ghostwriter to create the profiles and held-out cases this measures.

mblode Updated 202 repo stars

File contents

mblode/ghostwriter commit 57b047864d

Frequently asked questions

npx get-skill add mblode/evaluate-ghostwriter