Illustrative cover generated by us — see the source repo for real examples.
How to use
- 1
Copy the install prompt
Sign in, then click the black button. One click, done.
- 2
Paste it to your agent
Send it in Claude Code, Codex, Cursor or similar. It installs itself.
- 3
Ask in one sentence
Say what you want, like below, and the agent follows this skill.
/humanizer make me: English blog posts, launch notes, emailsExample message showing how to invoke it, not a real output.
What you get
- Catches not-X-but-Y contrasts, forced triads, stock AI words and filler
- Keeps facts and meaning intact
- Works as an editing or review pass
Good fit
- English blog posts, launch notes, emails
Not for
- Chinese text (use Humanizer-zh)
- License
- MIT
- Author
- @blader
- Source
- blader/humanizer · ★ 54,311
Upstream description
Rewrite AI-sounding text so it reads like the writer without changing what it says. Use when editing or reviewing prose for AI tells: not-X-but-Y contrasts, one-line closers, staged openers, forced triads, dashes everywhere, inflated claims, sales language, stock AI words, bold labels, or filler. Based on Wikipedia's "Signs of AI writing."
Other ways to install
Prefer doing it yourself? These commands do the same as the button.
Read https://skilloop.dev/skills/humanizer/install.md and follow the instructions to install the skill.
npx skills add https://github.com/blader/humanizer -g -a claude-code
npx skills add https://github.com/blader/humanizer -g -a codex
git clone --depth 1 https://github.com/blader/humanizer.git /tmp/humanizer mkdir -p ~/.claude/skills && cp -r /tmp/humanizer ~/.claude/skills/humanizer
Original work by its authors, redistributed under its license. We only link and describe it.
Related skills
Data Report Page
Turn a CSV, Excel or JSON file into a polished visual report page with charts and key takeaways.
Skill Creator
Create, edit and benchmark your own Agent Skills — including evals and description tuning for better triggering.
Brainstorming Before Building
Makes your coding agent clarify intent, requirements and design with you before it writes any code.
Systematic Debugging
A four-phase debugging discipline: find the root cause before proposing fixes, for any bug or failing test.