← LeaderboardThe Skill Leaderboard

voice-baseline

Measure your own writing corpus for the words and sentence shapes you over-use, so an agent writing in your voice stops amplifying your tics into a style. Produces a counted baseline file and checks any new draft against it. Use when an agent's drafts start sounding like a caricature of you, before publishing anything written in your voice, or every ten new pieces to re-measure.

Description awaits a fresh source check.

Published by huytieu ↗huytieu/COG-second-brain

Try your first task

voice-baseline

Start a fresh conversation. Replace the highlighted placeholders.

Use voice-baseline to Measure my own finished writing in [corpus directory] with the documented census and compare [draft file] with the counted baseline. Check the required script is available, report per-file word and sentence-shape rates, distinguish a personal voice choice from padding, and do not fabricate measurements or publish anything. This starter task stops at the requested local result; wait for my explicit confirmation before any later external action.

Required inputs

  • [corpus directory]
  • [draft file]

User-approved starter prompt based on a pinned source version; check current skill requirements before running. Task evidence ↗

SKILL.md

name: voice-baselinedescription: Measure your own writing corpus for the words and sentence shapes you over-use, so an agent writing in your voice stops amplifying your tics into a style. Produces a counted baseline file and checks any new draft against it. Use when an agent's drafts start sounding like a caricature of you, before publishing anything written in your voice, or every ten new pieces to re-measure.

Read .claude/skills/voice-baseline/SKILL.md and execute it exactly as written; that file is the authoritative playbook. Then follow .agents/rules/cog.md.

Antigravity substitution: where the playbook delegates to a .claude/agents/<name> worker, invoke .agents/agents/<name>.md via invoke_subagent instead.