git404hub

what is michelin fr?

voidful/michelin — explained in plain English

Analysis updated 2026-05-18

3PythonAudience · writerComplexity · 2/5LicenseSetup · easy

tl;dr

A bilingual skill for AI assistants that identifies AI-sounding text or design and rewrites it, then verifies the result with a blind human comparison test.

vibe map

mindmap
  root((Michelin))
    What it does
      Detects AI sounding text
      Rewrites templated design
      Blind validation
    Languages
      Traditional Chinese
      English
    Process
      Lock facts
      Find issues
      Targeted fix
      Blind test
    Use cases
      Marketing copy audit
      Design review
      Voice profile building

Code map

Detail Auto

An interactive map of this repo's files and how they connect — its source is parsed live in your browser. Click Visualize to build it.

filefunction / class

what do people make with this?

VIBE 1

Audit and rewrite AI-generated marketing copy in Chinese or English to sound more natural

VIBE 2

Review website or product interface designs for templated, AI-typical patterns

VIBE 3

Build a reusable voice or design profile from real writing or design samples

VIBE 4

Run a blind A/B comparison to test whether rewritten text is distinguishable from human writing

what's the stack?

Python

how it stacks up fr

voidful/michelin0marildo/imago0xdfi/glm-5.2-1m-4x-dgx-spark
Stars333
LanguagePythonPythonPython
Setup difficultyeasyeasyhard
Complexity2/52/55/5
Audiencewritergeneralresearcher

Figures from each repo's GitHub metadata at analysis time.

how do i run it?

Difficulty · easy time til it works · 5min

Copy the skill folder into an agent's skills directory, such as ~/.claude/skills/.

Use freely for any purpose, including commercial use, as long as you keep the copyright notice.

in plain english

Michelin is a skill made for AI coding assistants that tries to make text and visual design written or reviewed by AI feel less like an AI wrote it, in both Traditional Chinese used in Taiwan and English. Rather than just swapping out a few overused words, it works in four steps: first identifying facts and constraints in the text that must not change, then figuring out what specifically feels templated, whether that is structure, tone, visual layout, or wording that does not match how people in Taiwan actually speak, then only fixing the specific issues found, and finally checking the result through a blind side-by-side comparison against real human writing. It can be used to review website copy, product interfaces, documents, presentations, and marketing materials, either checking existing drafts or helping build a sense of a person's or brand's voice and design style from real examples they provide. The project is explicit that outside AI-detection tools are not treated as a reliable judge of success, instead, success means the AI-written version becomes hard to tell apart from human writing in a matched blind comparison, without the quality getting worse just to pass the test. The repository includes a Python-based checker that scans text or web pages for common AI writing patterns and Taiwan-specific language signals, plus a set of scripts for running the anonymous comparison process: preparing test cases, collecting judgments from independent reviewers, and generating a report. It also includes a packaging script that bundles the skill into a distributable file with a checksum. The author notes clear limits: there is no single fixed definition of what sounds human, blind tests can only show something is hard to distinguish under that specific test setup rather than proving anything about its origin, and image or video content still needs human judgment. The project is unrelated to the Michelin Group or Michelin Guide and carries no official rating meaning. It is released under the MIT license.

prompts (copy fr)

prompt 1
Use michelin to audit this landing page copy and point out where it sounds AI-generated.
prompt 2
Help me install the michelin skill into my Claude Code skills directory and run its validation script.
prompt 3
Walk me through running michelin_lint.py on a draft document to check for AI writing patterns.
prompt 4
Explain how michelin's blind evaluation process compares candidate text against human references.

Frequently asked questions

what is michelin fr?

A bilingual skill for AI assistants that identifies AI-sounding text or design and rewrites it, then verifies the result with a blind human comparison test.

What language is michelin written in?

Mainly Python. The stack also includes Python.

What license does michelin use?

Use freely for any purpose, including commercial use, as long as you keep the copyright notice.

How hard is michelin to set up?

Setup difficulty is rated easy, with roughly 5min to a first successful run.

Who is michelin for?

Mainly writer.

peek the repo → explain another one

This repo across BitVibe Labs

double-check against the repo, no cap.