#29 by GitHub stars

blader/humanizer

Rewrite AI-sounding text so it reads like the writer without changing what it says. Use when editing or reviewing prose for AI tells: not-X-but-Y contrasts, one-line closers, staged openers, forced triads, dashes everywhere, inflated claims, sales language, stock AI words, bold labels, or filler. Ba

Claude Code Codex Engineering Writing

History

Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.

View weekly changes

`SKILL.md`

Week of Nov 2, 2026 · +0 / −0 lines

Before Local scripts → After Local scripts

8c307f367c91 → 0ef9fe5bc357

Compare on GitHub

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Local scripts

First observation → 8c307f367c91

No earlier version was observed for comparison.

Compare on GitHub

View on GitHub Add to my skills

Verified commit 0ef9fe5bc3572734fd3ae6c448fe00a30cd5dcf0

Version-pinned installation · Claude Code

git clone --filter=blob:none --no-checkout https://github.com/blader/humanizer.git .hotskills/blader-humanizer && git -C .hotskills/blader-humanizer checkout --detach 0ef9fe5bc3572734fd3ae6c448fe00a30cd5dcf0
# Copy each selected skill directory from .hotskills/blader-humanizer into .claude/skills/<skill-name>/

Version-pinned installation · Codex

git clone --filter=blob:none --no-checkout https://github.com/blader/humanizer.git .hotskills/blader-humanizer && git -C .hotskills/blader-humanizer checkout --detach 0ef9fe5bc3572734fd3ae6c448fe00a30cd5dcf0
# Copy each selected skill directory from .hotskills/blader-humanizer into .agents/skills/<skill-name>/

65.4kGitHub stars

2.7kstars in 7 days

1skill in this repository

5commits in 30 days

Heat

7.8

Star growth, last 7 daysAhead of 96% of tracked repositories
Star growth, last 24 hoursAhead of 95% of tracked repositories
Rank movement, last 7 daysAhead of 81% of tracked repositories
Commits, last 30 daysAhead of 70% of tracked repositories
Accounts asking about it through MCP, last 7 daysNot available
Hot votes this weekAhead of 0% of tracked repositories

Heat never changes the order by stars, and sponsorship never touches it. How heat works

Stars over time

Individual skills in this repository

humanizer /

How it works

humanizer

When your agent uses it

Rewrite AI-sounding text so it reads like the writer without changing what it says. Use when editing or reviewing prose for AI tells: not-X-but-Y contrasts, one-line closers, staged openers, forced triads, dashes everywhere, inflated claims, sales language, stock AI words, bold labels, or filler. Based on Wikipedia's "Signs of AI writing."

What it loads into context

Frontmatter

106 tokens

Always available to the agent

SKILL.md

7,056 tokens

When the skill is activated

Reference documents

5,313 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

Why AI text sounds the way it does
How to work
A. Staging instead of stating
B. Rhythm by rule
C. Inflation and borrowed authority
D. Formatting by rule
E. Leftovers from the chat and the draft
F. Writing for the wrong reader
When not to act
Source

Scripts executed separately

scripts/validate-package.py

Files

.claude-plugin/marketplace.jsonasset521 bytes
.claude-plugin/plugin.jsonasset448 bytes
.cursor-plugin/plugin.jsonasset388 bytes
.github/ISSUE_TEMPLATE/config.ymlasset393 bytes
.github/ISSUE_TEMPLATE/new-pattern.ymlasset681 bytes
.github/ISSUE_TEMPLATE/rewrite-problem.ymlasset1,286 bytes
.github/workflows/validate.ymlasset815 bytes
AGENTS.mddoc3,439 bytes
CHANGELOG.mddoc5,922 bytes
LICENSEasset1,066 bytes
README.mddoc12,926 bytes
SKILL.mdcore32,348 bytes
SKILL.mdcore32,348 bytes
SKILL.mdcore32,348 bytes
SKILL.mdcore32,348 bytes
SKILL.mdcore32,348 bytes
SKILL.mdcore32,348 bytes
SKILL.mdcore32,348 bytes
SKILL.mdcore32,348 bytes
SKILL.mdcore32,348 bytes
SKILL.mdcore32,348 bytes
SKILL.mdcore32,348 bytes
SKILL.mdcore32,348 bytes
agents/openai.yamlasset201 bytes
scripts/validate-package.pyruns5,418 bytes

Read SKILL.md


# Humanizer: remove AI writing patterns

Rewrite AI-sounding text so it reads like the writer, not a chatbot. Keep what it says. Do not make anything up.

## Why AI text sounds the way it does

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 human writer chooses for one reader and one subject, so their choices are uneven and specific. Every pattern below is one form of the default choice:

- **Staging.** The sentence signals importance instead of adding a fact, with a contrast that only adds weight or a one-line closer that repeats the point.
- **Rhythm by rule.** Triads and dashes applied everywhere, whether or not the meaning asks for them.
- **Inflation.** Ordinary facts dressed as pivotal or expert-backed.
- **Formatting by rule.** Bold and title case applied to every item.
- **Leftovers.** Chat wrappers and drafting moves that were never meant for the reader.
- **Wrong reader.** A reply re-explains background the other person already has, so the decision arrives last.

View the complete source on GitHub

Skills included

humanizer

Repository facts

License: MIT
Created: Jan 18, 2026
Last pushed: Oct 28, 2026
Forks: 5,162
Open issues: 5
Project activity: Active

Rank over the last 12 weeks

Now #29 · best #29 · up 2 in 30 days

#30 from Oct 15 to Oct 19
#31 from Oct 20 to Oct 21
#30 from Oct 22 to Oct 24
#32 on Oct 25
#30 from Oct 28 to Nov 5
#29 since Nov 6

17 earlier periods

#43 on Aug 2
#40 from Aug 7 to Aug 20
#39 from Aug 21 to Aug 26
#38 from Aug 27 to Aug 29
#39 on Aug 30
#40 on Aug 31
#39 from Sep 1 to Sep 2
#38 on Sep 3
#35 from Sep 4 to Sep 5
#34 on Sep 6
#35 from Sep 7 to Sep 9
#34 from Sep 10 to Sep 14
#33 from Sep 15 to Sep 20
#32 from Sep 21 to Sep 25
#31 from Sep 26 to Oct 2
#30 from Oct 3 to Oct 5
#31 from Oct 6 to Oct 14

Before you install

Local scripts

Automated signals, not a guarantee

Checked Nov 3, 2026

Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.

Show 11 notes

SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed

No broad tool permissions
No dangerous shell commands
30 network referencesin 6 files: README.md:3 .claude-plugin/plugin.json:5 .github/ISSUE_TEMPLATE/config.yml:2 and 3 more
No hidden or obfuscated text
No instruction overrides
1 executable scriptin 1 file: scripts/validate-package.py:1
No access to secrets
No requests to vote in Hot

Show all 31 signals by file

`.claude-plugin/marketplace.json`

Network accessline 1

{   "$schema": "https://json.schemastore.org/claude-code-marketplace.json",

Network accessline 2

"$schema": "https://json.schemastore.org/claude-code-marketplace.json",

Network accessline 4

"owner": {     "name": "blader",     "url": "https://github.com/blader"

Network accessline 5

"name": "blader",     "url": "https://github.com/blader"   },

Network accessline 6
```
"url": "https://github.com/blader"
```

`.claude-plugin/plugin.json`

Network accessline 5

"author": {     "name": "blader",     "url": "https://github.com/blader"

Network accessline 6

"name": "blader",     "url": "https://github.com/blader"   },

Network accessline 7
```
"url": "https://github.com/blader"
```

Network accessline 8

},   "homepage": "https://github.com/blader/humanizer",   "repository": "https://github.com/blader/humanizer",

Network accessline 9

"homepage": "https://github.com/blader/humanizer",

Network accessline 10

"repository": "https://github.com/blader/humanizer",

`.cursor-plugin/plugin.json`

Network accessline 6

"name": "blader"   },   "homepage": "https://github.com/blader/humanizer",

Network accessline 7

},   "homepage": "https://github.com/blader/humanizer",   "repository": "https://github.com/blader/humanizer",

Network accessline 8

"homepage": "https://github.com/blader/humanizer",

Network accessline 9

"repository": "https://github.com/blader/humanizer",

`.github/ISSUE_TEMPLATE/config.yml`

Network accessline 2

contact_links:   - name: Questions, ideas, and thanks     url: https://github.com/blader/humanizer/discussions

Network accessline 3

- name: Questions, ideas, and thanks     url: https://github.com/blader/humanizer/discussions     about: Ask how to use Humanizer, share results, or say thanks.

Network accessline 4

url: https://github.com/blader/humanizer/discussions

Network accessline 5

about: Ask how to use Humanizer, share results, or say thanks.   - name: AI detectors still flag the output     url: https://github.com/blader/humanizer#humanizer

Network accessline 6

- name: AI detectors still flag the output     url: https://github.com/blader/humanizer#humanizer     about: Getting past AI detectors is not a goal. Humanizer edits for human readers.

Network accessline 7

url: https://github.com/blader/humanizer#humanizer

`README.md`

Network accessline 3
```
sponsored by [cfo.ai](https://cfo.ai)
```

Network accessline 5

[![GitHub stars](https://img.shields.io/github/stars/blader/humanizer?style=flat)](https://github.com/blader/humanizer/stargazers) [![skills.sh installs](https://skills.sh/b/blader/humanizer)](https://skills.sh/blader/humanizer)

Network accessline 8

Humanizer makes AI-written text sound like a person wrote it, without changing what it says. It is built on Wikipedia's [Signs of AI writing](https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing), the guide Wikipedia editors use to c

Network accessline 16

In a blind test, judges preferred Humanizer's rewrite over the original AI text 16 times out of 16 ([#229](https://github.com/blader/humanizer/issues/229)).

Network accessline 105

> "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"](https://en.wikipedia.org/wiki

Network accessline 106

> Wikipedia, ["Signs of AI writing"](https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing)

Network accessline 198

- [Wikipedia: Signs of AI writing](https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing) is the source for the pattern list.

Network accessline 199

- [WikiProject AI Cleanup](https://en.wikipedia.org/wiki/Wikipedia:WikiProject_AI_Cleanup) maintains the page.

`SKILL.md`

Network accessline 397

The patterns come from Wikipedia's ["Signs of AI writing"](https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing), maintained by WikiProject AI Cleanup, and from reviews of AI-generated text on Wikipedia and elsewhere.

`scripts/validate-package.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

How the signals fit together

Facts from a static read of the files at the pinned commit. They describe what the code does, not why.

Some files could not be read; the facts below still hold.

Signal confidence: 10 facts

Network access in prose of documentationREADME.md:3Low confidence
Network access in prose of documentationREADME.md:5Low confidence
Network access in prose of documentationREADME.md:8Low confidence
Network access in prose of documentationREADME.md:16Low confidence
Network access in prose of documentationREADME.md:105Low confidence
Network access in prose of documentationREADME.md:106Low confidence
Network access in prose of documentationREADME.md:198Low confidence
Network access in prose of documentationREADME.md:199Low confidence
Network access in prose of the SKILL.mdSKILL.md:397Low confidence
Executable script in code of a file that runsscripts/validate-package.py:1High confidence

Works with

Agent compatibility, from the files in this repository
Agent	Status	Evidence	Install to
Claude Code	Native	Manifest .claude-plugin/marketplace.json	`.claude/skills/<skill-name>/`
Codex	Native	Manifest AGENTS.md	`.agents/skills/<skill-name>/`
Cursor	Compatible	Standard SKILL.md SKILL.md	`.cursor/skills/<skill-name>/`
Gemini CLI	Compatible	Standard SKILL.md SKILL.md	`.gemini/skills/<skill-name>/`
GitHub Copilot	Compatible	Standard SKILL.md SKILL.md	`.github/skills/<skill-name>/`
OpenCode	Compatible	Standard SKILL.md SKILL.md	`.opencode/skills/<skill-name>/`

Native The repository ships a manifest, folder or frontmatter field for this agent.
Compatible A standard SKILL.md that this agent can read.
Unknown No evidence either way.

Derived automatically from paths, manifests and frontmatter. Not tested on each agent.

Explore alternatives and comparisons

Add this badge to your README

It updates every night and links to this page.

[![blader/humanizer on hotskills](https://hotskills.dev/badge/blader-humanizer.svg)](https://hotskills.dev/skill/blader-humanizer/)

blader/humanizer

History

SKILL.md

Share this page

Heat

Stars over time

Individual skills in this repository

How it works

humanizer

Frontmatter

SKILL.md

Reference documents

The playbook

Scripts executed separately

Files

Skills included

Repository facts

Rank over the last 12 weeks

Before you install

.claude-plugin/marketplace.json

.claude-plugin/plugin.json

.cursor-plugin/plugin.json

.github/ISSUE_TEMPLATE/config.yml

README.md

SKILL.md

scripts/validate-package.py

How the signals fit together

Works with

You might also use

Raymondhou0917/speak-human-tw

meodai/skill.color-expert

Vladimir-Human/humanizer-ru

forjd/better-writing

Nanako0129/sepia

first-fluke/oh-my-agent

Explore alternatives and comparisons

Add this badge to your README

`SKILL.md`

`.claude-plugin/marketplace.json`

`.claude-plugin/plugin.json`

`.cursor-plugin/plugin.json`

`.github/ISSUE_TEMPLATE/config.yml`

`README.md`

`SKILL.md`

`scripts/validate-package.py`