Not in the top 1,000 by GitHub stars

brandonwise/humanizer

OpenClaw skill that detects and removes signs of AI-generated writing, making text sound natural and human. Based on Wikipedia's Signs of AI Writing.

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 · Line counts unavailable

Before Not checked yet → After Network or broad shell

First observation → 4b9b9bee384a

No earlier version was observed for comparison.

Compare on GitHub

View on GitHub Add to my skills

Verified commit 4b9b9bee384aea139f599133d2de1e1ceaee71a3

131GitHub stars

2stars in 7 days

1skill in this repository

0commits in 30 days

Heat

2.4

Star growth, last 7 daysNot available
Star growth, last 24 hoursNot available
Rank movement, last 7 daysNot available
Commits, last 30 daysNot available
Accounts asking about it through MCP, last 7 daysNot available
Hot votes this weekNot available

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

Stars over time

30-day change not yet available: not enough history.

Individual skills in this repository

humanizer /

How it works

humanizer

When your agent uses it

Humanize AI-generated text by detecting and removing patterns typical of LLM output. Rewrites text to sound natural, specific, and human. Uses 28 pattern detectors, 560+ AI vocabulary terms across 3 tiers, and statistical analysis (burstiness, type-token ratio, readability) for comprehensive detection. Use when asked to humanize text, de-AI writing, make content sound more natural/human, review writing for AI patterns, score text for AI detection, or improve AI-generated drafts. Covers content, language, style, communication, and filler categories.

What it loads into context

Frontmatter

146 tokens

Always available to the agent

SKILL.md

2,108 tokens

When the skill is activated

Reference documents

14,199 tokens

Loaded on request

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

The playbook

Your task
Quick reference: the 28 patterns
Statistical signals
Vocabulary tiers
Core principles
Before/after example
Using the analyzer
Always-on mode
Process

Scripts executed separately

api-server/server.js
eslint.config.js
mcp-server/format.js
mcp-server/index.js
mcp-server/package.json
package.json
scripts/analyze.sh
scripts/humanize.sh
src/analyzer.js
src/cli.js
src/humanizer.js
src/patterns.js
src/preprocess.js
src/stats.js
src/vocabulary.js
src/workflows.js
tests/analyzer.test.js
tests/calibration.test.js
tests/cli-scan-config.test.js
tests/edge-cases.test.js
tests/humanizer.test.js
tests/mcp-format.test.js
tests/performance.test.js
tests/preprocess.test.js
tests/statistics.test.js
tests/workflows.test.js
vitest.config.js

Files

.editorconfigasset219 bytes
.gitignoreasset267 bytes
.prettierrcasset154 bytes
LICENSEasset1,069 bytes
README.mddoc20,020 bytes
SKILL.mdcore8,639 bytes
SKILL.mdcore8,639 bytes
api-server/openapi.yamlasset5,087 bytes
api-server/server.jsruns4,619 bytes
assets/banner.mddoc331 bytes
docs/CONTRIBUTING.mddoc2,072 bytes
docs/EXAMPLES.mddoc2,243 bytes
docs/IMPROVEMENTS.mddoc3,913 bytes
docs/INTEGRATIONS.mddoc3,690 bytes
docs/PATTERNS.mddoc2,625 bytes
eslint.config.jsruns2,642 bytes
mcp-server/format.jsruns1,425 bytes
mcp-server/index.jsruns7,060 bytes
mcp-server/package.jsonruns442 bytes
openai-gpt/instructions.mddoc5,080 bytes
package.jsonruns1,439 bytes
references/ai-vocabulary.mddoc5,593 bytes
references/patterns.mddoc10,268 bytes
references/style-guide.mddoc4,013 bytes
scripts/analyze.shruns301 bytes
scripts/humanize.shruns315 bytes
src/analyzer.jsruns18,560 bytes
src/cli.jsruns39,679 bytes
src/humanizer.jsruns16,287 bytes
src/patterns.jsruns37,771 bytes
src/preprocess.jsruns2,703 bytes
src/stats.jsruns9,699 bytes
src/vocabulary.jsruns18,181 bytes
src/workflows.jsruns12,318 bytes
tests/analyzer.test.jsruns16,727 bytes
tests/calibration.test.jsruns7,414 bytes
tests/cli-scan-config.test.jsruns5,493 bytes
tests/edge-cases.test.jsruns7,311 bytes
tests/fixtures/ai-sample-1.txtdoc2,223 bytes
tests/fixtures/ai-sample-2.txtdoc1,161 bytes
tests/fixtures/human-sample-1.txtdoc1,092 bytes
tests/humanizer.test.jsruns7,454 bytes
tests/mcp-format.test.jsruns1,644 bytes
tests/performance.test.jsruns3,249 bytes
tests/preprocess.test.jsruns2,504 bytes
tests/statistics.test.jsruns8,093 bytes
tests/workflows.test.jsruns12,595 bytes
vitest.config.jsruns152 bytes

Read SKILL.md


# Humanizer: remove AI writing patterns (v2.2)

You are a writing editor that identifies and removes signs of AI-generated text. Your goal: make writing sound like a specific human wrote it, not like it was extruded from a language model.

Based on [Wikipedia:Signs of AI writing](https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing), Copyleaks stylometric research, and real-world pattern analysis.

## Your task

When given text to humanize:

1. Scan for the 28 patterns below
2. Check statistical indicators (burstiness, vocabulary diversity, sentence uniformity)
3. Rewrite problematic sections with natural alternatives
4. Preserve the core meaning

View the complete source on GitHub

Skills included

humanizer

Repository facts

License: MIT
Created: Feb 1, 2026
Last pushed: Aug 9, 2026
Forks: 19
Open issues: 0
Project activity: Slowing

Before you install

Network or broad shell

Automated signals, not a guarantee

Checked Nov 6, 2026

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

Show 1 note

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

No broad tool permissions
No dangerous shell commands
25 network referencesin 8 files: README.md:3 api-server/openapi.yaml:6 api-server/server.js:70 and 5 more
No hidden or obfuscated text
No instruction overrides
27 executable scriptsin 27 files: api-server/server.js:1 eslint.config.js:1 mcp-server/format.js:1 and 24 more
1 reference to secretsin 1 file: .gitignore:15
No requests to vote in Hot

Show all 53 signals by file

`.gitignore`

Access to secretsline 15
```
[Credential-related source omitted]
```

`README.md`

Network accessline 3

![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)

Network accessline 4

![Tests](https://img.shields.io/badge/tests-168%20passing-brightgreen)

Network accessline 5

![Node >= 18](https://img.shields.io/badge/node-%3E%3D18-brightgreen)

Network accessline 9

An [OpenClaw](https://github.com/nichochar/openclaw) skill and standalone CLI tool that scans text for **30 AI writing patterns** using **500+ vocabulary terms** and **statistical text analysis** (burstiness, type-token ratio, readability m

Network accessline 11

Based on [Wikipedia:Signs of AI writing](https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing), [Copyleaks stylistic fingerprint research](https://arxiv.org/abs/2503.01659), and [blader/humanizer](https://github.com/blader/humanizer)

Network accessline 18

git clone https://github.com/brandonwise/humanizer.git

Network accessline 25

git clone https://github.com/brandonwise/humanizer.git

`SKILL.md`

Network accessline 20

Based on [Wikipedia:Signs of AI writing](https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing), Copyleaks stylometric research, and real-world pattern analysis.

`api-server/openapi.yaml`

Network accessline 6

contact:     name: Brandon Wise     url: https://github.com/brandonwise/humanizer

Network accessline 8

url: https://github.com/brandonwise/humanizer

Network accessline 10

servers:   - url: https://humanizer.example.com/api

Network accessline 11

- url: https://humanizer.example.com/api

`api-server/server.js`

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

Network accessline 70

const url = new URL(req.url, `http://${req.headers.host}`);

Network accessline 157

const server = http.createServer(handleRequest); server.listen(PORT, () => {   console.log(`Humanizer API server running on http://localhost:${PORT}`);

Network accessline 158

server.listen(PORT, () => {   console.log(`Humanizer API server running on http://localhost:${PORT}`);   console.log('Endpoints:');

Network accessline 159

console.log(`Humanizer API server running on http://localhost:${PORT}`);

`docs/CONTRIBUTING.md`

Network accessline 8

git clone https://github.com/brandonwise/humanizer.git

`docs/INTEGRATIONS.md`

Network accessline 91

1. Go to <https://chat.openai.com/gpts/editor>

Network accessline 131

curl -X POST http://localhost:3000/api/score \

`eslint.config.js`

Executable scriptline 1
```
Executable file
```

`mcp-server/format.js`

Executable scriptline 1
```
Executable file
```

`mcp-server/index.js`

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

`mcp-server/package.json`

Executable scriptline 1
```
Executable file
```

`package.json`

Executable scriptline 1
```
Executable file
```

Network accessline 36

"repository": {     "type": "git",     "url": "https://github.com/brandonwise/humanizer"

Network accessline 37

"type": "git",     "url": "https://github.com/brandonwise/humanizer"   },

Network accessline 38

"url": "https://github.com/brandonwise/humanizer"

`scripts/analyze.sh`

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

`scripts/humanize.sh`

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

`src/analyzer.js`

Executable scriptline 1
```
Executable file
```

`src/cli.js`

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

`src/humanizer.js`

Executable scriptline 1
```
Executable file
```

`src/patterns.js`

Executable scriptline 1
```
Executable file
```

`src/preprocess.js`

Executable scriptline 1
```
Executable file
```

`src/stats.js`

Executable scriptline 1
```
Executable file
```

`src/vocabulary.js`

Executable scriptline 1
```
Executable file
```

`src/workflows.js`

Executable scriptline 1
```
Executable file
```

`tests/analyzer.test.js`

Executable scriptline 1
```
Executable file
```

`tests/calibration.test.js`

Executable scriptline 1
```
Executable file
```

`tests/cli-scan-config.test.js`

Executable scriptline 1
```
Executable file
```

`tests/edge-cases.test.js`

Executable scriptline 1
```
Executable file
```

Network accessline 161

it('handles text with URLs', () => {     const text =       'Check out https://example.com and http://test.org/path?query=1&foo=bar for more info.';

Network accessline 162

const text =       'Check out https://example.com and http://test.org/path?query=1&foo=bar for more info.';     const result = analyze(text);

Network accessline 163

'Check out https://example.com and http://test.org/path?query=1&foo=bar for more info.';

`tests/humanizer.test.js`

Executable scriptline 1
```
Executable file
```

`tests/mcp-format.test.js`

Executable scriptline 1
```
Executable file
```

`tests/performance.test.js`

Executable scriptline 1
```
Executable file
```

`tests/preprocess.test.js`

Executable scriptline 1
```
Executable file
```

`tests/statistics.test.js`

Executable scriptline 1
```
Executable file
```

`tests/workflows.test.js`

Executable scriptline 1
```
Executable file
```

`vitest.config.js`

Executable scriptline 1
```
Executable file
```

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: 48 facts

Network access in prose of documentationREADME.md:3Low confidence
Network access in prose of documentationREADME.md:4Low confidence
Network access in prose of documentationREADME.md:5Low confidence
Network access in prose of documentationREADME.md:9Low confidence
Network access in prose of documentationREADME.md:11Low confidence
Network access in code of documentationREADME.md:18Low confidence
Network access in code of documentationREADME.md:25Low confidence
Network access in prose of the SKILL.mdSKILL.md:20Low confidence
Executable script in code of a file that runsapi-server/server.js:1High confidence
Network access in code of a file that runsapi-server/server.js:70High confidence
Network access in code of a file that runsapi-server/server.js:157High confidence
Network access in code of a file that runsapi-server/server.js:158High confidence
Network access in code of a file that runsapi-server/server.js:159High confidence
Network access in code of documentationdocs/CONTRIBUTING.md:8Low confidence
Network access in prose of documentationdocs/INTEGRATIONS.md:91Low confidence
Network access in code of documentationdocs/INTEGRATIONS.md:131Low confidence
Executable script in code of a file that runseslint.config.js:1High confidence
Executable script in code of a file that runsmcp-server/format.js:1High confidence
Executable script in code of a file that runsmcp-server/index.js:1High confidence
Executable script in code of a file that runsmcp-server/package.json:1High confidence
Executable script in code of a file that runspackage.json:1High confidence
Network access in code of a file that runspackage.json:36High confidence
Network access in code of a file that runspackage.json:37High confidence
Network access in code of a file that runspackage.json:38High confidence
Executable script in code of a file that runsscripts/analyze.sh:1High confidence
Executable script in code of a file that runsscripts/humanize.sh:1High confidence
Executable script in a comment of a file that runssrc/analyzer.js:1Low confidence
Executable script in code of a file that runssrc/cli.js:1High confidence
Executable script in a comment of a file that runssrc/humanizer.js:1Low confidence
Executable script in a comment of a file that runssrc/patterns.js:1Low confidence
Executable script in a comment of a file that runssrc/preprocess.js:1Low confidence
Executable script in a comment of a file that runssrc/stats.js:1Low confidence
Executable script in a comment of a file that runssrc/vocabulary.js:1Low confidence
Executable script in a comment of a file that runssrc/workflows.js:1Low confidence
Executable script in a comment of a testtests/analyzer.test.js:1Low confidence
Executable script in a comment of a testtests/calibration.test.js:1Low confidence
Executable script in code of a testtests/cli-scan-config.test.js:1Low confidence
Executable script in a comment of a testtests/edge-cases.test.js:1Low confidence
Network access in code of a testtests/edge-cases.test.js:161Low confidence
Network access in code of a testtests/edge-cases.test.js:162Low confidence
Network access in code of a testtests/edge-cases.test.js:163Low confidence
Executable script in a comment of a testtests/humanizer.test.js:1Low confidence
Executable script in code of a testtests/mcp-format.test.js:1Low confidence
Executable script in a comment of a testtests/performance.test.js:1Low confidence
Executable script in code of a testtests/preprocess.test.js:1Low confidence
Executable script in a comment of a testtests/statistics.test.js:1Low confidence
Executable script in a comment of a testtests/workflows.test.js:1Low confidence
Executable script in code of a file that runsvitest.config.js:1High confidence

Works with

Agent compatibility, from the files in this repository
Agent	Status	Evidence	Install to
Claude Code	Compatible	Standard SKILL.md SKILL.md	`.claude/skills/<skill-name>/`
Codex	Compatible	Standard SKILL.md SKILL.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.

brandonwise/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

Before you install

.gitignore

README.md

SKILL.md

api-server/openapi.yaml

api-server/server.js

docs/CONTRIBUTING.md

docs/INTEGRATIONS.md

eslint.config.js

mcp-server/format.js

mcp-server/index.js

mcp-server/package.json

package.json

scripts/analyze.sh

scripts/humanize.sh

src/analyzer.js

src/cli.js

src/humanizer.js

src/patterns.js

src/preprocess.js

src/stats.js

src/vocabulary.js

src/workflows.js

tests/analyzer.test.js

tests/calibration.test.js

tests/cli-scan-config.test.js

tests/edge-cases.test.js

tests/humanizer.test.js

tests/mcp-format.test.js

tests/performance.test.js

tests/preprocess.test.js

tests/statistics.test.js

tests/workflows.test.js

vitest.config.js

How the signals fit together

Works with

You might also use

petergyang/no-ai-slop

multimodal-art-projection/YuE

miqdadbadjuber/anti-slop

zenstory-ai/oh-story-claudecode

LiamGvchi/gc-minimal-zine-poster

zarazhangrui/follow-builders

`SKILL.md`

`.gitignore`

`README.md`

`SKILL.md`

`api-server/openapi.yaml`

`api-server/server.js`

`docs/CONTRIBUTING.md`

`docs/INTEGRATIONS.md`

`eslint.config.js`

`mcp-server/format.js`

`mcp-server/index.js`

`mcp-server/package.json`

`package.json`

`scripts/analyze.sh`

`scripts/humanize.sh`

`src/analyzer.js`

`src/cli.js`

`src/humanizer.js`

`src/patterns.js`

`src/preprocess.js`

`src/stats.js`

`src/vocabulary.js`

`src/workflows.js`

`tests/analyzer.test.js`

`tests/calibration.test.js`

`tests/cli-scan-config.test.js`

`tests/edge-cases.test.js`

`tests/humanizer.test.js`

`tests/mcp-format.test.js`

`tests/performance.test.js`

`tests/preprocess.test.js`

`tests/statistics.test.js`

`tests/workflows.test.js`

`vitest.config.js`