Humanizer is a Python skill that rewrites text to remove signs of AI writing, packaged as a portable agent skill with multiple installation modes and usage options. It provides voice calibration and several rewrite modes, with recent releases focused on distribution, no-fabrication rules, and new invocation modes.
Collecting history — the radar snapshots this repo daily. The trend line appears after 3 days of data (1 so far).
What it is
A portable agent skill that removes signs of AI-generated writing from text, making it sound more natural and human. It is plain Markdown, so it can run in any harness that supports skill-style instructions.
How it works
The README describes usage via installed skills across harnesses, with direct prompts or slash commands. It includes a final audit pass for obviously AI-generated text and a second rewrite to reduce lingering AI-isms. Rewrites follow a no-fabrication rule: they never add facts, names, dates, or citations that aren't in the source text.
Getting started
Skills CLI
Install globally with the cross-agent skills CLI so Humanizer is available in every project:
npx skills add blader/humanizer --global
Update an existing install:
npx skills update humanizer --global
To install globally into every supported agent harness:
npx skills add blader/humanizer --global --agent '*'
To target one configured harness, pass its agent name:
npx skills add blader/humanizer --global --agent <agent-name>
Omit --global for a project-local install that can be committed and shared with collaborators. Start a new agent session or reload skills after installation.
Claude Code plugin
Claude Code users can also install Humanizer as a plugin:
/plugin marketplace add blader/humanizer
/plugin install humanizer@humanizer
The skill is then invoked as /humanizer:humanizer.
Manual
Any agent harness can use the skill directly because the runtime artifact is SKILL.md.
For example:
git clone https://github.com/blader/humanizer.git /path/to/your/skills/humanizer
Or, if you already have this repo cloned:
mkdir -p /path/to/your/skills/humanizer
cp SKILL.md /path/to/your/skills/humanizer/
Usage
Invoke the skill through your harness-exposed interface:
/humanizer
[paste your text here]
Please humanize this text: [your text]
Point it at a file and the skill rewrites it in place:
Humanize the prose in docs/launch-post.md
Voice Calibration
To match your personal writing style, provide a sample of your own writing:
/humanizer
Here's a sample of my writing for voice matching:
[paste 2-3 paragraphs of your own writing]
Now humanize this text:
[paste AI text to humanize]
The skill will analyze your sentence rhythm, word choices, and quirks, then apply them to the rewrite instead of producing generic "clean" output.
Overview
Based on Wikipedia's Signs of AI writing guide, maintained by WikiProject AI Cleanup. Includes a final audit pass and second rewrite.
Rewrites follow a no-fabrication rule: they never add facts, names, dates, or citations that aren't in the source text. Specificity has to come from the source or the author, not from the rewrite.
Key Insight from Wikipedia
"LLMs use statistical algorithms to guess what should come next. The result tends toward the most statistically likely result that applies to the widest variety of cases."
33 Patterns Detected (with Before/After Examples)
(Details are in the README; not reproduced here to avoid duplicating content.)
Version History
- 2.9.1 (2026-07-22): Improved distribution and portability: removed nonportable frontmatter and tool preapprovals, made global installation the documented default, added package validation, and removed the duplicated long-form example from the runtime prompt. No change to the 33 patterns.
- 2.9.0 (2026-07-22): Adds a hard no-fabrication rule, repairs examples that modeled invented facts, and introduces pasted-text, file, and embedded invocation modes. Also preserves information over paragraph shape and lets
License
MIT






