Agent skill that removes signs of AI-generated writing from text

★ 67,291⑂ 5,290👁 284⑃ 195● 122▤ 6◈ 4
PythonMITCreated 2026-01-18skills.sh/blader/humanizer
67,291
stars
+484+3,344+13,129
5,290
forks
284
watchers
195
prs
122
issues
6
releases
4
discussions

README

Humanizer 

sponsored by cfo.ai

  


Humanizer makes AI-written text sound like a person wrote it, without changing what it says. It is built on Wikipedia's Signs of AI writing, the guide Wikipedia editors use to catch AI-generated text, and it works in Claude Code, Codex, and any other agent that supports skills.

Before:
 I'm thrilled to announce that shared drafts are finally here! 🚀 For months, our own team was drowning in files named final_v7.docx — and we knew there had to be a better way. Now two people can edit the same doc at once, with every change appearing live for both of them. It's not just a feature; it's a whole new way to collaborate. Comments stay anchored to the exact sentence they reference, even as the text around them evolves. And the best part? It's available today on every plan, completely free. Let that sink in.

After:
 Shared drafts are out today. For months our own team passed around files named final_v7.docx, so we built a way for two people to edit the same doc at once, with each person's changes showing up live for the other. Comments stay pinned to the sentence they're about, even when the text around them changes. It's free on every plan.

In a blind test, judges preferred Humanizer's rewrite over the original AI text 16 times out of 16 (229).

Humanizer edits for human readers. Getting past AI detectors is not a goal, and detectors still flag most of its output.

 The five strongest tells

These are the most common signs of AI writing, and Humanizer rewrites any of them on sight:

1. Not X but Y: "It's not just a feature, it's a shift."
2. One-line closers: "Let that sink in."
3. Sayings that sound deep: "At its core, what really matters is..."
4. A staged run-up: "Here's the thing." "Honestly?"
5. Arguing with no one: "I'm not saying X, but..."

Humanizer checks for 26 patterns in all.

 Installation

Once installed, the skill answers to /humanizer.

 Claude Code

text
/plugin marketplace add blader/humanizer
/plugin install humanizer@humanizer


The plugin answers to /humanizer:humanizer. It needs Claude Code 2.1.142 or newer; on older versions, use npx skills add blader/humanizer --global --agent claude-code.

 Codex

bash
npx skills add blader/humanizer --global --agent codex


 Claude.ai and Claude Desktop

Download this repository as a ZIP (Code → Download ZIP) and upload it as a skill in Settings.

 Other agents

bash
npx skills add blader/humanizer --global --agent ''


This installs Humanizer for every agent the Skills CLI supports, including Gemini CLI, GitHub Copilot, and Windsurf. Leave off --global in any command above to install it only in the current project. For an agent the Skills CLI does not know, copy SKILL.md into its skill folder.

 Usage

Call the skill directly:


/humanizer

[paste your text here]


Or ask in plain language:


Please humanize this text: [your text]


To rewrite a file, give Humanizer its path:


Humanize the prose in docs/launch-post.md


 Match your voice

If you want t

Top issues

Discussions

Latest release

Humanizer v3.1.0 v3.1.0 2026-09-28
Humanizer 3.1.0 adds a pattern for replies that re-explain what the reader already knows, and it tightens the skill so each rule is stated once.

 What changed

- Added pattern 26 and section F for replies that re-explain context the reader already has (269). It acts on replies, not standalone writing. 26 patterns total.
- Extended the core rule so "something the reader did not already have" counts the surrounding conversation, not only earlier text.
- Widened 25 to text that describes its own sourcing, assembly, or layout (290), and added headings written for effect to 20.
- Extended 2 to "Th

Snapshot: 2026-11-10T09:35:25Z · Data license Apache-2.0 · JSON