humanize — Claude Code skill: what it does, how to install
This skill sends text to the HumanizerAI API for rewriting and displays before-and-after scores. Use it to change the style of AI-generated text.
npx skills add humanizerai/agent-skills --skill humanize -a claude-codeWhat humanize does
The skill accepts text and a rewrite intensity: light, medium, or aggressive. It uses medium by default. After the API request, the agent returns the revised text, scores from before and after processing, the word count, and your remaining credits.
You need an API key set in the HUMANIZERAI_API_KEY environment variable. Processing costs one credit per word, while detection checks are free. Longer text therefore uses more credits; if your balance is too low, the skill reports the required and available amounts.
What it helps with
- rewrite AI-generated text at a chosen intensity
- keep a text’s style with a light rewrite
- compare scores before and after processing
- check credit use and remaining balance
Example prompts for the agent
- Rewrite this text while keeping my style: [text]
- Make a stronger rewrite of this text: [text]
- Process this text and show the before-and-after scores: [text]
How to install humanize
1Skills CLI (Vercel)
npx skills add humanizerai/agent-skills --skill humanize -a claude-code2Manually: put the files in place
~/.claude/skills/humanize/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/humanize/
1Skills CLI (Vercel)
npx skills add humanizerai/agent-skills --skill humanize -a codex2Manually: put the files in place
.agents/skills/humanize/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add humanizerai/agent-skills --skill humanize -a cursor2Manually: put the files in place
.cursor/skills/humanize/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install humanizerai/agent-skills humanize2Manually: put the files in place
.github/skills/humanize/SKILL.md1Skills CLI (Vercel)
npx skills add humanizerai/agent-skills --skill humanize -a gemini-cli2Platform CLI
gemini skills install https://github.com/humanizerai/agent-skills --path skills/humanizeManually: put the files in place
.devin/skills/humanize/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add humanizerai/agent-skills --skill humanize -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about humanize
How do I install humanize in Claude Code?
Run npx skills add humanizerai/agent-skills --skill humanize -a claude-code. The skill file will be available at ~/.claude/skills/humanize/SKILL.md.
What does humanize do?
It sends text to the HumanizerAI API and returns a rewritten version with before-and-after scores, word count, and remaining credits.
What does humanize need to run?
Set the HUMANIZERAI_API_KEY environment variable. Rewriting costs one credit per word; detection checks are free.
Source text
SKILL.md · MIT
---
name: humanize
description: Transform AI-generated text into natural, human-like content that bypasses AI detectors like GPTZero, Turnitin, and Originality.ai. Uses credits based on word count.
user-invocable: true
argument-hint: "[text to humanize] [--intensity light|medium|aggressive]"
allowed-tools: WebFetch
---
# Humanize AI Text
Transform AI-generated content into natural, human-like writing using the HumanizerAI API.
## How It Works
When the user invokes `/humanize`, you should:
1. Parse $ARGUMENTS for text and optional --intensity flag
2. Call the HumanizerAI API to humanize the text
3. Present the humanized text with before/after scores
4. Show remaining credits
## Parsing Arguments
The user may provide:
- Just text: `/humanize [their text]`
- With intensity: `/humanize --intensity aggressive [their text]`
Default intensity is `medium`.
## Intensity Levels
| Value | Name | Description | Best For |
|-------|------|-------------|----------|
| `light` | Light | Subtle changes, preserves style | Already-edited text, low AI scores |
| `medium` | Medium | Balanced rewrites (default) | Most use cases |
| `aggressive` | Bypass | Maximum bypass mode | High AI scores, strict detectors |
## API Call
Make a POST request to `https://humanizerai.com/api/v1/humanize`:
```
Authorization: Bearer $HUMANIZERAI_API_KEY
Content-Type: application/json
{
"text": "<user's text>",
"intensity": "medium"
}
```
## Response Format
Present results like this:
```
## Humanization Complete
**Score:** X → Y (improvement)
**Words Processed:** N
**Credits Remaining:** X
---
### Humanized Text
[The humanized text]
---
[Recommendation based on final score]
```
## Credit Usage
- 1 word = 1 credit
- Detection is free
- Check credits at https://humanizerai.com/dashboard
## Error Handling
### Insufficient Credits
If the user doesn't have enough credits:
1. Show how many credits are needed vs available
2. Direct them to https://humanizerai.com/dashboard to top up
### Invalid API Key
1. Check HUMANIZERAI_API_KEY environment variable
2. Direct to https://humanizerai.com to get a key
### Rate Limit
If rate limited, suggest waiting or upgrading to Business plan.
© humanizerai · MIT · humanizerai/agent-skills
