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…
Drafts, rewrites, or reviews the user's personal messages, emails, posts, and tickets from a private per-platform profile plus a shared soul.md, strips the machine tells that make prose read as AI, and applies a communication-strategy layer to high-stakes messages. Use when asked to "write this in my voice", "draft a…
Trains private, platform-specific tone profiles from local writing samples with deterministic held-out splits, clean Codex or Claude Code sessions, previews, backups, and atomic writes. Use when asked to "learn my tone", "build my voice profile", "train a writing style", import writing samples, refresh a tone profile…