humanizer is a free, open source ai development platforms project written in Python and released under MIT. It has 49,532 GitHub stars, 4,011 forks and 13 open issues, and was last pushed 11 days ago. On this registry it ranks #16 of 61 tracked projects in AI Development Platforms, with 5 head-to-head comparisons available. It gained 1,026 stars over the last 3 tracked days.

What is humanizer?

Humanizer is an MIT-licensed agent skill that rewrites AI-sounding text so it reads like a person wrote it without changing what it says, and it is aimed at writers, developers, and documentation teams working inside Claude Code, Codex, Cursor, or any other agent that supports skills.

What it is

Humanizer is a Markdown skill file, SKILL.md, that lives inside an AI coding or writing agent and rewrites prose on request. Because it is plain Markdown rather than a compiled tool or a hosted service, it installs into any agent that implements the skills convention, and the same file serves Claude Code, Codex, and Cursor. The registry lists the project under AI & Machine Learning / AI Development Platforms, with a homepage at skills.sh/blader/humanizer.

The concrete problem it solves is the cleanup pass that follows AI drafting. A language model picks whatever is most likely to come next, so it defaults to phrasing that fits the widest range of readers and subjects, while a person writing for one reader and one subject does not. Humanizer names the resulting tells — staged run-ups, one-line closers, sayings that sound deep, "not X but Y" constructions — and rewrites them. It replaces the manual rewriting an editor would otherwise do line by line, and it does so under a hard constraint: a name, number, date, quote, or citation must come from the source text or from the writer, never from the model.

Key capabilities

  • Applies a catalogue of 25 numbered patterns ordered by strength and frequency, where the first five justify an edit on a single sighting and patterns marked weak alone count only when several tells appear in one passage.
  • Ships as the /humanizer slash command, or /humanizer:humanizer when installed as a Claude Code plugin.
  • Shows its work on pasted text: the first rewrite, a short critique of anything that still sounds artificial, and the final version.
  • Preserves factual detail and asks the writer when a missing detail is required, rather than inventing one.
  • Edits files in place while leaving code, data, frontmatter, and link targets untouched, so Humanize the prose in docs/launch-post.md changes only the running prose.
  • Supports voice matching from a two-to-three paragraph writing sample, following the sample's rhythm, word choice, punctuation, and deliberate quirks including dashes.
  • Adjusts register by material: personal writing keeps the writer's opinions, technical and reference prose stays neutral and plain.

Who uses it and how

  • Claude Code users on version 2.1.142 or newer who install it through the plugin marketplace and invoke it as /humanizer:humanizer.
  • Teams running several agents at once, using --agent or --agent '*' to choose which agents receive the skill before reloading their skill sets.
  • Documentation and launch-writing workflows that point the skill at a Markdown file by path and expect the code blocks and link targets to survive unchanged.
  • Writers with an established voice who paste a sample of their own prose so rewrites track their punctuation and rhythm.
  • Claude Desktop users who download the repository as a ZIP and upload it as a skill, and users who copy SKILL.md into an agent's skill folder by hand.

Getting started

Install through the Skills CLI with npx skills add blader/humanizer --global, dropping --global for a project-only install. Claude Code can instead add the plugin with /plugin marketplace add blader/humanizer followed by /plugin install humanizer@humanizer.

How it compares

No paid products are listed as things this project replaces, and no sibling skill doing the same work is named in the facts. Within this registry it stands alone: it is the only entry covered here that addresses AI-generated prose as an agent skill rather than as a service or an application.

When to use it — and when not to

Nothing needs operating: the project ships as Markdown, so there is no database, object storage, or mail server to run, and no cost beyond the host agent. It does require an agent that supports skills, and rewrite quality tracks whatever model that agent runs, so anyone without a skills-capable host should not pick it. The project is also a prose rewriter rather than a linter or a formatter, so teams seeking deterministic, rule-checked style enforcement will not get that from it.

project readme (upstream, from github) — read inline

Humanizer

skills.sh installs

Humanizer rewrites AI-sounding text so it reads like a person wrote it, without changing what it says. Because it is just Markdown, it works with any agent that supports skills.

Installation

Install Humanizer with the Skills CLI:

npx skills add blader/humanizer --global

Leave off --global to install Humanizer only in the current project. Add --agent or --agent '*' to choose which agents receive it, then reload their skills. The skill answers to /humanizer.

Claude Code 2.1.142 or newer can install the plugin instead:

/plugin marketplace add blader/humanizer
/plugin install humanizer@humanizer

The plugin answers to /humanizer:humanizer.

In Claude Desktop, download this repository as a ZIP and upload it as a skill. For a manual install, copy SKILL.md into the agent's skill folder.

Usage

Call the skill directly:

/humanizer

[paste your text here]

Or ask in plain language:

Please humanize this text: [your text]

To rewrite a file, give Humanizer its path:

Humanize the prose in docs/launch-post.md

Match your voice

If you want the rewrite to sound more like you, include a sample:

/humanizer

Here's a sample of my writing for voice matching:
[paste 2-3 paragraphs of your own writing]

Now humanize this text:
[paste AI text to humanize]

Humanizer follows the sample's rhythm, word choice, punctuation, and deliberate quirks, including dashes if you use them.

How it works

A language model writes whatever is most likely to come next, so by default it makes the choice that fits the widest range of readers and subjects. A person chooses for one reader and one subject. Every tell Humanizer looks for is a form of that default choice: a sentence that signals importance instead of adding a fact, rhythm or formatting applied by rule, an ordinary fact dressed as a pivotal one, or text left over from the chat.

"LLMs use statistical algorithms to guess what should come next. The result tends toward the most statistically likely result that applies to the widest variety of cases." Wikipedia, "Signs of AI writing"

Humanizer marks every tell it finds, strongest first. It drafts a rewrite without treating the original structure as fixed, checks the draft against the patterns and the original claims, and then writes the final version. It does not make things up. A name, number, date, quote, citation, or other factual detail must come from the source or the writer, and if a sentence needs a detail that is missing, Humanizer asks instead of inventing one.

When you paste text, Humanizer shows its work: the first rewrite, a short critique of anything that still sounds artificial, and the final version. Point it at a file and it changes only the prose, leaving code, data, frontmatter, and link targets alone. Personal writing keeps the writer's opinions and quirks. Technical and reference prose stays neutral and plain.

The 25 patterns

The patterns are numbered by strength and frequency. The first five justify an edit on a single sighting. Patterns marked weak alone count only when several tells share a passage, because a careful writer may use any one of them on purpose.

A. Staging instead of stating

# Pattern Before After
1 Not X but Y "It's not just X, it's Y", "This doesn't mean X. It means Y." State the point directly
2 One-line closers and dramatic fragments "That is the real win." after every section; "No prior. No nostalgia." Cut the closer that repeats; merge fragments into a specific claim
3 Sayings that sound deep "At its core, what matters is...", "Symmetry is the language of trust" Replace the saying with the specific claim
4 Staged run-up before the point "Let's dive in", "Honestly? It depends..." Remove the run-up and state the point
5 Arguing with no one "This isn't mainly about...", "A tempting approach would be..." Remove the unraised objection or fake option; keep any real claim

B. Rhythm by rule

# Pattern Before After
6 Forced triads "innovation, inspiration, and insights"; three examples plus a lesson Use the number of items the meaning needs
7 Repeated sentence openings "She noted... She noted... She filed..." Merge the sentences or change the subject
8 Dashes as the universal connector (weak alone) "institutions—not the people—yet this continues—" Use periods, commas, colons, or parentheses; match a sample that uses dashes
9 Stacked qualifiers (weak alone) "could potentially possibly be argued" Keep only qualifiers the source supports
10 Hyphenated pairs everywhere (weak alone) "the team is cross-functional" Keep only the hyphens grammar needs
11 Passive voice and missing subjects (weak alone) "No configuration file needed" Name the actor when that helps

C. Inflation and borrowed authority

# Pattern Before After
12 Overused AI words "delve... testament... landscape... showcasing" Use plain words; the list in SKILL.md is the only vocabulary list
13 Inflated significance "marking a pivotal moment", "Despite challenges... continues to thrive", "The future looks bright" Keep the fact and drop the significance; end on the last concrete fact
14 Vague connection or association "associated with the leadership of", "in connection with" State the relationship the source gives
15 Shallow -ing riders "symbolizing... reflecting... showcasing..." Keep only what the source supports
16 Sales language "nestled within the breathtaking region" State what the thing is
17 Borrowed authority "Experts believe...", "cited in NYT, BBC, FT, and The Hindu" Name a real source and what it said, or remove the claim or list
18 Avoiding is, are, and has "serves as... features... boasts" "is... has"

D. Formatting by rule

# Pattern Before After
19 Bold as decoration "OKRs, KPIs"; "Performance: Performance improved" Remove the bold; turn a labeled list into prose
20 Decorative headings "Strategic Negotiations And Partnerships", "🚀 Launch Phase:" Sentence case; remove emojis and arrows
21 Curly quotation marks (weak alone) said “the project” said "the project"

E. Leftovers from the chat and the draft

# Pattern Before After
22 Chatbot residue "Great question! ... I hope this helps!" Remove the wrapper and keep the content
23 Knowledge-limit disclaimers and guesses "While details are limited in available sources, it appears..." State what the source shows, or remove the sentence
24 A heading repeated in the first sentence "## Performance" + "Speed matters." Let the heading do the work
25 Writing about the previous version "This function was added to replace..." Describe what it does now

Full example

The writer supplied these notes with the draft, so the rewrite can use them: the trip was last October, the hotel was in Alfama, the custard tart was at a small place in Graça, the tram ride took about forty minutes. Without notes like these, Humanizer asks instead of inventing.

Before (AI-sounding):

I recently spent five unforgettable days in Lisbon, and let me tell you — this city completely stole my heart. From the moment I arrived, I knew I was somewhere truly special.

Nestled along the banks of the Tagus River, Lisbon stands as a vibrant testament to Portugal's enduring spirit, where rich history and modern energy intertwine at every turn. Yes, the famous hills are challenging — my legs certainly felt it! — but every climb rewards you with breathtaking, panoramic views that make it all worthwhile.

No trip would be complete without riding the iconic Tram 28, winding through the city's most historic neighborhoods. And the food? Simply divine. The original pastéis de nata at Pastéis de Belém are a beloved national treasure, and savoring one still warm was a moment I will never forget.

But what truly makes Lisbon special isn't just the sights — it's the feeling. Wander a few steps off the main squares and you'll discover a quieter, more authentic side: sun-drenched alleys, charming tiled facades, and friendly locals going about their daily lives, inviting you to slow down and savor every moment.

Of course, the must-see São Jorge Castle offers stunning views over the rooftops below. The queues can be long, but the experience is absolutely worth it for an

readme truncated — read the full docs on github

Frequently asked questions

Is humanizer free to use?

humanizer is open source under the MIT licence. There is no licence fee and no seat count — you can self-host it or, where the project offers one, pay a vendor for a managed version instead.

What does humanizer do?

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

What is humanizer written in?

humanizer is primarily written in Python. Its source is publicly available at https://github.com/blader/humanizer, and it has 49,532 GitHub stars.