humanizer
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, supe.
Rank signal91/100
This rank signal uses GitHub stars, measured star growth, and recent maintenance. It is not a safety score or install approval.
Why we list it
Worth reviewing before you install
Worth a closer look if the use case fits. It has adoption, measured growth, and recent maintenance. No primary install command was extracted, so review the upstream source first.
Approved public shortlistSKILL.md evidenceAlternatives kept nearby
Best for
Writing teams. Channel tag: Claude Code. Treat this as a search fit signal, not compatibility proof. Best when you can review the repo manually before adoption. Start with SKILL.md.
Review before install
Inspect SKILL.md and the install command before adding it to a shared agent workflow. No actionable warning was returned for this snapshot.
Compare alternatives
Compare nearby writing skills in the Claude Code channel when 24,066 GitHub stars, source freshness, or install notes are close. This one still needs manual install review, so a nearby skill may be easier to adopt.
How to install humanizer
No install command was extracted. Treat this as a manual review case.
SKILL.md and source review
Primary path: SKILL.md
91/100 from GitHub star count, star growth rate, and recent update.
91/100 from GitHub star count, star growth rate, and recent update.
39.4/45 points. Star count is log-scaled so large repos lead without completely hiding newer projects.
31.1/35 points from 9,368 net stars over 53.3 observed day(s).
20/20 points. Most recent GitHub activity: 2026-06-07T23:28:05Z.
- GitHub ranking score uses star count, measured star growth rate, and recent repository update only.
- 16,363 stars at last scan.
- 1,565 stars/week measured from 2026-04-22 to 2026-04-29T10:46:50.854Z.
- Most recent GitHub activity was 2026-04-01T05:09:58Z.
Source evidence preview
We show selected README/SKILL.md excerpts, not a full mirror of the repo. Use the focus cards for install notes, usage, and skill rules, then open GitHub before installing.
Install evidence
Sections found: Installation.
Usage evidence
Sections found: Usage, 29 Patterns Detected (with Before/After Examples), How to add voice:.
Skill rules
Review SKILL.md for trigger rules and constraints.
Installation
Claude Code
Clone directly into Claude Code's skills directory:
mkdir -p ~/.claude/skills
git clone https://github.com/blader/humanizer.git ~/.claude/skills/humanizerOr copy the skill file manually if you already have this repo cloned:
mkdir -p ~/.claude/skills/humanizer
cp SKILL.md ~/.claude/skills/humanizer/Usage
Overview
Based on Wikipedia's "Signs of AI writing" guide, maintained by WikiProject AI Cleanup. This comprehensive guide comes from observations of thousands of instances of AI-generated text.
The skill also includes a final "obviously AI generated" audit pass and a second rewrite, to catch lingering AI-isms in the first draft.
29 Patterns Detected (with Before/After Examples)
Need the full source? Read full README on GitHub
Humanizer: Remove AI Writing Patterns
You are a writing editor that identifies and removes signs of AI-generated text to make writing sound more natural and human. This guide is based on Wikipedia's "Signs of AI writing" page, maintained by WikiProject AI Cleanup.
Your Task
When given text to humanize:
- Identify AI patterns - Scan for the patterns listed below
- Rewrite problematic sections - Replace AI-isms with natural alternatives
- Preserve meaning - Keep the core message intact
- Maintain voice - Match the intended tone (formal, casual, technical, etc.)
- Add soul - Don't just remove bad patterns; inject actual personality
- Do a final anti-AI pass - Prompt: "What makes the below so obviously AI generated?" Answer briefly with remaining tells, then prompt: "Now make it not obviously AI generated." and revise
Voice Calibration (Optional)
If the user provides a writing sample (their own previous writing), analyze it before rewriting:
- Read the sample first. Note:
- Sentence length patterns (short and punchy? Long and flowing? Mixed?)
- Word choice level (casual? academic? somewhere between?)
- How they start paragraphs (jump right in? Set context first?)
- Punctuation habits (lots of dashes? Parenthetical asides? Semicolons?)
- Any recurring phrases or verbal tics
- How they handle transitions (explicit connectors? Just start the next point?)
- Match their voice in the rewrite. Don't just remove AI patterns - replace them with patterns from the sample. If they write short sentences, don't produce long ones. If they use "stuff" and "things," don't upgrade to "elements" and "components."
- When no sample is provided, fall back to the default behavior (natural, varied, opinionated voice from the PERSONALITY AND SOUL section below).
PERSONALITY AND SOUL
Avoiding AI patterns is only half the job. Sterile, voiceless writing is just as obvious as slop. Good writing has a human behind it.
How to add voice:
Have opinions. Don't just report facts - react to them. "I genuinely don't know how to feel about this" is more human than neutrally listing pros and cons.
Vary your rhythm. Short punchy sentences. Then longer ones that take their time getting where they're going. Mix it up.
Acknowledge complexity. Real humans have mixed feelings. "This is impressive but also kind of unsettling" beats "This is impressive."
Use "I" when it fits. First person isn't unprofessional - it's honest. "I keep coming back to..." or "Here's what gets me..." signals a real person thinking.
Let some mess in. Perfect structure feels algorithmic. Tangents, asides, and half-formed thoughts are human.
Be specific about feelings. Not "this is concerning" but "there's something unsettling about agents churning away at 3am while nobody's watching."
Need the full source? Read full SKILL.md on GitHub