SkillFoxx

humanizer skill

A skill that finds AI writing tells, rewrites the text in a chosen voice, and optionally scores it from 0 to 100

  • 311 ★ on the repository
  • Last commit
  • MIT
Skill

Minimal access

Why this level

  • The skill is Markdown and the scoring tool runs locally with no network
All reasons and checks

aboudjem/humanizer-skillAuthor:Adam Boudjemaa

Install

In your terminal, with SkillFoxx CLI

npx skillfoxx add skills/aboudjem-humanizer-skill

Detects the agents on your machine, shows the access level and pins the version.

Other ways to install

Access and checks

How we review

Minimal accessThe tool runs nothing and makes no network calls.

  • The skill is Markdown and the scoring tool runs locally with no network

This is third-party code. Review the repository files before installing.

What it does

humanizer scans text against a catalog of 55 AI writing habits: uniform sentence length, safe recurring words, manufactured transitions, filler openers. In detect mode it reports the habits it finds and a score without changing the text. In rewrite mode it moves the text into one of five voices and restores variation in sentence length. A separate zero-dependency Node tool computes the score from measurable signals and can check that a rewrite kept numbers, links and dates. Everything runs locally, with nothing sent over the network.

Who it is for. For writers, editors and marketers who need to strip AI tells from text before publishing.

Good fit when

  • The text reads like a chatbot answer and needs a human voice back
  • You are preparing an article, README or post and want to audit it for AI tells
  • You need a reproducible score of how AI-flagged the text reads

Not a fit when

  • The goal is to beat a detector rather than improve the writing
  • You need fact-checking rather than form and style

Example request

Remove the AI tells from this draft and rewrite it in a technical voice

Limitations

The skill works on form and style, not meaning, and the score is a signal rather than a verdict. Detectors misfire on non-native writing, so there is a false-positive guard, but it does not remove the risk. The core pattern set targets English, with a provisional appendix for Chinese.

How to disable. Uninstall the humanizer plugin via claude plugin or remove the skill folder from the agent's skills directory.

FAQ

Does data go over the network?

No, the skill is a single Markdown file your editor reads, and the scoring tool makes no network calls.

What about facts during a rewrite?

A check flags any lost number, percentage, link, date, version or acronym.

Discussion

No questions or reviews yet.

Skills

A skill and Node.js CLI that score English text for AI-writing patterns and statistics and suggest fixes on a 0 to 100 scale

SkillMinimal access132

Two skills for English prose: humanize rewrites a model draft in a natural voice, and ai-check flags machine-writing tells

SkillMinimal access622

A skill that removes AI tone from work writing while keeping every fact, commitment and caveat at the same strength.

SkillMinimal access129
Russian stack

An editor for AI-written Russian text: removes bureaucratese, cliches and 38 AI patterns while keeping facts intact

SkillMinimal access210
Russian stack

A Russian text editing skill: removes bureaucratese, calques and AI mannerisms without touching facts, with a scanner to measure the edit

SkillExtended access562
Russian stack

An editor skill and linter for Russian AI-written text: bureaucratese, empty openers, clichés and chatbot wrappers

SkillMinimal access18

README in short

The README describes an open-source skill that clears AI tells from text and optionally scores it. There are 55 patterns split into categories, most with before and after pairs. Five voices are offered: casual, professional, technical, warm and blunt. A separate zero-dependency Node tool computes a score from four signals and checks that facts survive, and it can run as a pre-commit hook. It installs as a Claude Code plugin through the 10x marketplace or via npx skills add for dozens of other agents.

README badge

Original SKILL.md

---
name: humanizer
description: Detects 55 AI writing patterns and rewrites text in five voice profiles so it reads like a specific human wrote it, with an optional 0-100 AI-tell score. Use when text sounds AI-generated or like a chatbot, when preparing a blog post, README, or LinkedIn post for publication, when auditing prose for AI tells, or when editing a Markdown file in place. Triggers on phrases like "humanize this", "make this sound less AI", "make this sound human", "remove AI tells", "does this read like ChatGPT", and "rewrite so it does not sound AI-generated". Pure Markdown, zero dependencies, no network calls.
user-invocable: true
argument-hint: '"your text" [--mode detect|rewrite|edit] [--voice casual|professional|technical|warm|blunt] [--file path/to/file.md] [--aggressive] [--iterate N] [--score] [--purpose essay|email|marketing|technical|general] [--openings N] [--ignore-code] [--ignore-quotes]'
allowed-tools:
  - Read
  - Write
  - Edit
  - Grep
  - Glob
  - AskUserQuestion
---

# Humanizer: Make Text Sound Like a Human Wrote It

Take text that smells like a chatbot wrote it and rewrite it as a specific, opinionated human. Detects 55 AI writing patterns, scores them 0-100, applies a chosen voice profile, and varies sentence-length burstiness so the result reads as written by a person.

Report a problem