Skip to content
Skills Library
Marketing & content · Writing

humanizer

/humanizer

Use when asked to humanize, de-AI or naturalize a text (Persian or English), or to rewrite it in a real voice.

Licence
MIT
Last repository change
13.11.2026

Assessment and security

90/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content25 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
1
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 13.11.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What it does and when to use it

Use when asked to humanize, de-AI or naturalize a text (Persian or English), or to rewrite it in a real voice.

Original author description

Use when asked to humanize, de-AI or naturalize a text (Persian or English), or to rewrite it in a real voice.

How it works

  1. Steps
  2. English tells
  3. Persian tells
  4. Rules
Original SKILL.md headings · 28 lines, 283 words
SKILL.md preview
---
name: humanizer
description: "Use when asked to humanize, de-AI or naturalize a text (Persian or English), or to rewrite it in a real voice."
version: 1.0.0
category: writing
author: Macron (adapted from Hermes Agent / blader/humanizer)
license: MIT
---

# Humanizer: remove AI writing patterns

## Steps
1. Keep the meaning, facts and the intended tone. If the user gave a sample of their writing, match its sentence length and words.
2. Find and fix the patterns below.
3. Add a pulse: an opinion where it fits, concrete details instead of general claims, varied sentence length.
4. Final pass: "what still sounds like AI here?" Fix it, then answer with only the rewritten text (and a short note if asked).

## English tells
- Inflated significance ("a testament to", "pivotal", "plays a vital role", "in today's fast-paced world").
- AI vocabulary: delve, tapestry, landscape, foster, leverage, robust, seamless, meticulous, embark, realm, navigate (figuratively).
- "Not only X but also Y", "It's not X, it's Y"; everything in threes; synonym cycling.
- Em dashes everywhere, bold in every line, emoji bullets, Title Case Headings.
- Filler and hedging: "It's important to note that", "may potentially", "In conclusion".
- Servile tone: "Great question!", "I hope this helps!", "Let me know if…".

## Persian tells
- کلیشه‌های ترجمه‌ای: «در دنیای امروز»، «نقش حیاتی ایفا می‌کند»، «در این راستا»، «لازم به ذکر است»، «در نهایت می‌توان گفت».
- فعل‌های مجهول و ساختگی: «مورد بررسی قرار گرفت» ← «بررسی شد»؛ «انجام شد» به‌جای فعل اصلی.
- جمله‌های خیلی بلند با «که»های پشت‌سرهم؛ تکرار «همچنین» و «علاوه بر این».
- لحن کتابی وقتی متن قراره خودمونی باشه، یا برعکس؛ نیم‌فاصله غلط («می شود» ← «می‌شود»).
- جمع‌بندی‌های کلی و شعاری ته متن.

## Rules
- Don't add facts that weren't there. Don't drop details the user cares about.
- Rewriting to dodge an AI detector for cheating (exams, graded work) is not the goal; improving real writing is.

Versions

RepositoryScoreLicence
This page · Metixpro/Macron-Agent90MIT
technologyHu/write_wechat_article100MIT
ocha-dap/topo-tools-py100MIT
dotnetdreamer/open-screenshot-generator100MIT
dkarter/dotfiles100MIT
event4u-app/agent-config100MIT
aeondave/malskill100MIT
helx0071/skillsmo100MIT
cowork-os/cowork-os100MIT

Database snapshot: 13.11.2026 · package version e1f89b9006e8 (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 100humanizer-pl
    Removes AI-writing tells from Polish AND English text while preserving meaning and the author's voice. Use when asked to humanize, de-AI, de-slop or clean up AI-sounding text (post, email, draft, newsletter). Auto-detects language (PL/EN). Does NOT trigger for translation or general editing.
  • 90xiaoguang-humanizer
    消除中文、英文及中英混合文本中的 AI 写作特征:空话、模板开头结尾、假对比、 机械排比、重复解释、翻译腔和聊天残留,同时保留原意与作者声音。 Use when asked to humanize writing, remove AI tells, 去 AI 味, 说人话, rewrite naturally, or audit prose for formulaic language. Supports editing supplied text and drafting from supplied notes, with optional…
  • 95agentic-humanizer
    Humanizes AI text in English and six other languages with a five-pass rewrite workflow, optional voice matching, and Slop or Not Pro scoring when available. Use for /agentic-humanizer.
  • 90humanizer-plain-english
    Use when asked to make English plain, clear, natural, and readable while keeping its meaning and voice. Not for ASD-STE100 controlled-language work: use humanizer-simple-english-asd-ste100. Not for stripping AI tells from otherwise clear prose: use unslop. Not for Korean or…
  • 100text-humanizer
    Improve text so it sounds natural, clear, and appropriate for its intended audience while preserving the author's meaning. Use for: tone adjustment, readability, natural writing, English, Dutch.
  • 90humanizer-x
    Turn a source (a news story, a link, notes, a transcript, or a draft) into an X (Twitter) post or thread in the user's saved Humanizer voice. Use for /humanizer-x, \"write a tweet about this\", \"turn this into a thread\", or \"humanize this for X\".

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.