humanize
100 / 100 · Low risk
Fine to try.
Edit AI-sounding text so it reads like a careful person wrote it, without changing what it says. Two modes. Rewrite: edit the text you are given (posts, emails, docs, release notes, replies, landing pages). Interview: when a draft is AI-composed and thin, ask the writer 3-5 sharp questions and build the piece from their answers, in their words. Calibrated on measured differences between human and AI writing.
What this skill can do
We found nothing in the files we read that matches our rules. That does not prove the skill is safe: see the limits of static scanning.
Other copies in this repository
- evidence/skill-versions/v2
- evidence/skill-versions/v5
- evidence/skill-versions/v5i
- evidence/skill-versions/v5r1
- evidence/skill-versions/v5r2
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'humanize' ] || [ -L ~/.agents/skills/'humanize' ]; then echo 'A skill folder named humanize already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/phuryn/work-humanizer' "$d" && git -C "$d" checkout --quiet '0a9065791d021f3dda695f3887cb2ae4c0eacbcf' -- 'evidence/skill-versions/v1' && mkdir -p ~/.agents/skills && cp -R "$d"/'evidence/skill-versions/v1' ~/.agents/skills/'humanize' && rm -rf "$d"; fi
Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'humanize' ~/.claude/skills/'humanize' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.
Badge for your README
[](https://zalavijaysinh.github.io/skilltrust/repos/phuryn/work-humanizer/)
Score history
| Date | Version | Score |
|---|---|---|
| 2026-11-07 | 0a90657 | 100 |