content / skill

Humanizer

Rewrite AI-written text to remove common signs of AI writing, such as one-line closers and overused AI words.

At a glance

Purpose
Rewrite AI-written text to remove common signs of AI writing, such as one-line closers and overused AI words.
Runs in
Chat app with skills, Local agent with shell
Operating systems
Not stated
Needs
Runtime: Not stated; Needs internet: Not stated; Needs accounts or API keys beyond your agent: Not stated
Files and data
Reads files: Yes; Writes files: Yes; Sends data to other services: Not stated
Tool type
Skill
Delivery
From GitHub
Version
Latest on the main branch
Access
Code on GitHub
Compatibility
According to the README, it works in Claude Code, Codex and any other agent that supports skills. It gives install routes for Claude Code, Codex, the Claude web app and Claude Desktop, and says the Skills CLI also covers Gemini CLI, GitHub Copilot and Windsurf. For an agent the Skills CLI does not know, it says to copy SKILL.md into the agent's skill folder.
External costs
The repository is MIT-licensed and states no pricing. Your coding agent or model provider may charge for usage.
Permissions
The skills act through your coding agent with the access you give it. According to the README, you can paste text or give a file path. When it works on a file, it changes only the prose and leaves code, data, frontmatter and link targets alone. The README says leaving off --global installs it only in the current project.
Usage terms
MIT License, as stated in the repository. See its LICENSE file for the exact terms.

Code on GitHub

blader/humanizer

MIT

Python56,222 stars4,445 forksLast pushed 28 Sept 2026 UTC

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

Topics: agent-skills ai-humanizer ai-writing chatgpt claude claude-code codex cursor

Public GitHub data fetched · 0 days old

View on GitHub ↗

What it does

Humanizer is a skill that rewrites AI-written text to remove common signs of AI writing. According to the README, it keeps what the text says and builds on Wikipedia's guide called Signs of AI writing. The README says it checks text against 26 patterns, such as "not X but Y" phrasing, one-line closers, sayings that sound deep, overused AI words, decorative headings and chatbot residue.

The README says that when you paste text, Humanizer shows a first rewrite, a short critique of anything that still sounds artificial, and a final version. For a file, the README says it changes only the prose and leaves code, data, frontmatter and link targets alone. The README says names, numbers, dates, quotes and citations must come from the source or the writer, and that Humanizer asks when a detail is missing.

You call it with /humanizer or ask in plain language. You can add a writing sample so the rewrite follows your rhythm, word choice and punctuation.

Who it is for

People who want to edit AI-drafted text so it reads less like AI writing, using an agent that supports skills.

Example tasks

Rewrite pasted text to remove signs of AI writing.
Humanize the prose in a document file and leave its code and link targets alone.
Match your own voice by supplying a writing sample.
Read a short critique of what still sounds artificial before the final version.

Getting started

In Claude Code, the README gives /plugin marketplace add blader/humanizer and /plugin install humanizer@humanizer. For Codex it gives npx skills add blader/humanizer --global --agent codex. For other agents it gives npx skills add blader/humanizer --global --agent '*'. For the Claude web app and Claude Desktop, it says to download the repository as a ZIP and upload it as a skill in Settings. Once installed, the skill answers to /humanizer; the README says the Claude Code plugin answers to /humanizer:humanizer. The README has the exact commands.

Limitations

It depends on a coding agent that supports skills. According to the README, the Claude Code plugin needs Claude Code 2.1.142 or newer, and older versions use a different command. The README says Humanizer edits for human readers, that getting past AI detectors is not a goal, and that detectors still flag most of its output. The repository can change at any time; check its README before you install.

Data practices

The README does not describe data handling. What is sent where depends on your coding agent and model provider.

Community experience

Not rated yet

Sign in to share your experience.

Comments 0

No comments yet.

Sign in to comment

Report a listing concern