
AI humanizer skill for Claude Code, Codex and Cursor. Removes AI slop and the signs of AI writing
AI humanizer skill for Claude Code, Codex and Cursor. Removes AI slop and the signs of AI writing, then measures the rewrite against human baselines.
·
English · Español
An agent skill for Claude Code, Codex and Cursor. It strips the AI slop that marks prose as machine-written,
then checks the result against measured human writing instead of a hunch.
Hand it a draft and ask it to humanize the text, or to make a README sound less like ChatGPT. It rewrites the prose, then measures the result. You get the rewrite and a measurement that says whether it now reads like a person wrote it.
With the skills CLI, for Claude Code and every other agent it supports, Gemini CLI and GitHub Copilot among them:
npx skills add ilien-dev/quironIt needs no API key. It runs on the model you already use, and the scripts need nothing beyond the Python 3 standard library.
Run these two commands inside Claude Code:
/plugin marketplace add ilien-dev/quiron
/plugin install quiron@quironThe plugin puts the skill under its own name, so you call it as /quiron:quiron.
The animation shows what the skill does in the background. You won't see this screen when you run it,
and it doesn't start a server or open a report: the model edits your text in the chat and gives you the meter's result there.
[!IMPORTANT] Use it responsibly. Quirón is for text you write for yourself or your own team: a how-to guide, internal docs, meeting notes, a draft nobody outside the company will read. The point is text that feels close and easy to read, not text that pretends a person wrote it.
Do not use it to pass AI writing off as human in public: social media, published articles, schoolwork, reviews, job applications, anything where the reader has a right to know who wrote it. Never use it to deceive or defraud anyone. It also does not beat AI detectors that read token probabilities, and it was not built to.
Ask a model for a blog post and you get a shape you learn to spot: lists of three, about twice the headings a person would use, a summary section at the end, "it's not just X, it's Y" and em dashes where a comma would do. Quirón gives the model a checklist of 33 of these signs of AI writing and a meter that says in numbers whether the fix landed or went too far.
Delve is not on the list anymore. On this repo's 2026 run it turned up in 1% of
assistant posts or fewer, roughly as often as in human ones. The words that give 2026
models away are ordinary ones you'd never flag by eye, used at many times the human rate
(the list is in references/word-choice.md). The
other half of the signal is what's missing: models rarely write very or able, and
people use both all the time.
Here is the meter on an assistant-written Stripe tutorial from eval/ai/blog/:
$ python3 scripts/aimeter.py eval/ai/blog/e2e-raw/aspittel-782713.md
feature this human band verdict
long words (7+) /1k 353.83 159.68 - 250.46 above band, AI side
nominalizations /1k 55.21 7.29 - 32.65 above band, AI side
mean word length 5.46 4.28 - 4.86 above band, AI side
lists of three /1k 11.29 0.00 - 5.51 above band, AI side
plain words /1k 33.88 43.19 - 95.24 below band, AI side
...
13/23 features inside the human band (p10-p90 of 167 human texts)
! triads: retries, cancellations, and preventing, refund, tax, and privacyThe rewrite of the same post, built from the author's own notes, scores 23 of 23.
The best-known humanizer skills, humanizer and stop-slop, give the model a list of AI writing patterns to remove, and they work. So does no-ai-slop. Stop-slop also has the model score its own draft from 1 to 10 on five questions.
Quirón has a pattern list too, but the model doesn't grade itself. A script measures 23 rates in the text and compares each one with the range found in human writing published before ChatGPT. That catches a failure a checklist can't see. Tell a model to write like a person and it usually overshoots: choppier and plainer than any person writes. The meter flags that as loudly as the AI side.
Every rule and number traces to a published study or to a run of the scripts in this repo. Nothing ships on "this reads better".
eval/ai/, from the plain prompt a user would type. They were
written in September 2026 and again in November with the models current then.eval/e2e/.The details of how each number was measured are in SKILL.md and
eval/README.md, along with the source of every rule.
The judges were not fooled by style edits alone. A rewrite that put every rate inside the human band was still judged AI 12 times out of 12. What moved them was the writer's own material. So:
Ask your agent in plain words, or call /quiron:
Humanize this post: [paste the text]
Make docs/launch.md sound less like AI. Here are my notes: [notes]
Check this email for AI tells, don't rewrite it yet.The scripts run on their own too, from a clone of this repository:
python3 scripts/aimeter.py FILE # 23 rates against the human bands
python3 scripts/audit.py --brief FILE # the pattern checklist
scripts/check.sh FILE # one pass of the full loopFor fiction or Spanish, set QUIRON_BANDS=scripts/bands-fiction.json or
scripts/bands-es.json. Texts under about 120 words get no measurement.
For the narration of a YouTube video script, set QUIRON_BANDS=scripts/bands-script.json,
or scripts/bands-script-es.json in Spanish. The meter reads only the spoken words and
leaves the stage directions alone. It measures a script and checks it for patterns that
assistant scripts share. It has not been shown to make a rewritten script read as
human-written. Rewritten from notes that were outlines of the finished human script of the
same video, the Claude judge's P(AI) fell on held-out titles from 71.0 to 24.7 in English and
to 20.3 in Spanish, while a GPT judge saw about 15 points and still rated them around 65.
Without notes a rewrite gained 4.5 to 10.5 points and about nine in ten were still rated AI,
and judges rated a script a person wrote as more AI after a rewrite. For your own script,
measure it and change what you choose to change.
Other languages get the same checklist as a best effort. There is no human baseline for them yet. The meter says so and shows only the numbers that don't depend on the words, such as paragraph length and headings.
Does it get text past AI detectors like GPTZero or Turnitin? No. Those tools read token probabilities, and Quirón doesn't touch them. It works only on what a human reader actually notices.
Which models does it work with? Any model behind an agent that loads skills. It was tested on text from ten Claude and GPT models, four from September 2026 and six from November.
Does it make things up to sound human? Its instructions forbid it. A rewrite may use only
facts from your text or your notes. scripts/factdiff.py lists the numbers and links in
the rewrite that the source doesn't have. When it needs detail it lacks, it asks.
Most centaurs in Greek myth were wild and violent. Chiron (Quirón in Spanish) was the wise one: he taught Achilles, Asclepius and Jason, and he was a healer. When a poisoned arrow wounded him, his immortality meant he could not die from it, so he gave it up, and Zeus set him among the stars. The logo shows him holding that star.
He fits the skill in two ways. He was a teacher of people, and this skill teaches a model how people write. And he was half man, half horse: the text Quirón helps produce is a hybrid too. The model does the drafting, and the human part has to come from you.
Free to use and change, under the GNU AGPL v3 with one added term
in NOTICE. Any work built on Quirón has to stay open under the same license,
including a modified version offered as a network service, and has to credit the
original: "Based on Quirón by ilien", with a link to this repository.
Paste this prompt into your agent. It reads this page and does the setup for you.
Read https://aiagentslisting.com/mcp/quiron to learn what the "Quiron" MCP server does and how to install it. Add it to my coding agent's MCP configuration as documented on that page, then confirm the server connects and list the tools it exposes.Agents can also browse this directory over MCP at https://aiagentslisting.com/api/mcp
npx skills add ilien-dev/quironThis server runs locally, so we can't read its tool list over the web yet.
We could not run this server: it ships no npx package for our sandbox and no public endpoint. The four checks that need a live server are left out, and the grade tops out at B until one exists.
Maintain this server? Claiming proves you own the listing and earns the last 4 points.
Claim this listingPaste this line near the top of your repository's README. The badge always renders the current score.
[](https://aiagentslisting.com/mcp/quiron)Nothing comparable is listed yet.
v1.5.0Quirón 1.5.0Release notesv1.4.0Quirón 1.4.0Release notesv1.3.0Quirón 1.3.0Release notesv1.2.0Quirón 1.2.0Release notesv1.1.0Quirón 1.1.0Release notesv1.0.0Quirón 1.0.0Release notesConnect to the AI Agents Listing MCP server at https://aiagentslisting.com/api/mcp using the HTTP transport and complete the sign-in when it asks. Then call the submit_review tool for the listing "quiron" with a rating from 1 to 5 and a short note on what worked and what did not.No reviews yet
Be the first to share your experience with this tool.
One email a week. New agents, MCP servers and skills, and what is actually getting traction.