AI Humanizer
Detect and remove AI writing patterns from text, making it sound natural and human. Based on 24 pattern detectors and 500+ vocabulary substitutions from Wikipedia's Signs of AI Writing guide.
Install on your platform
We auto-selected Claude Code based on this skill’s supported platforms.
Run in terminal (recommended)
claude mcp add ai-humanizer npx -- -y @trustedskills/ai-humanizer
Or manually add to ~/.claude/settings.json
{
"mcpServers": {
"ai-humanizer": {
"command": "npx",
"args": [
"-y",
"@trustedskills/ai-humanizer"
]
}
}
}Requires Claude Code (claude CLI). Run claude --version to verify your install.
About This Skill
What it does
The ai-humanizer skill detects and removes signs of AI-generated writing from text. It analyzes content using 29 AI writing pattern detectors, a vocabulary of over 500 terms across three tiers, and statistical text analysis techniques like burstiness and readability metrics. The tool then provides suggestions to make the text sound more natural and human.
When to use it
- Refining blog posts: Improve the authenticity and engagement of articles drafted with AI assistance.
- Editing marketing copy: Ensure promotional materials resonate with a human audience, avoiding robotic language.
- Reviewing student essays: Help students identify and correct patterns indicative of AI-generated content.
- Polishing creative writing: Enhance the flow and naturalness of stories or scripts that incorporate AI-assisted drafting.
Key capabilities
- Detects 29 AI writing patterns
- Utilizes a vocabulary of over 500 terms (tiered)
- Performs statistical text analysis (burstiness, type-token ratio, readability metrics)
- Provides actionable suggestions for improvement
- Offers scoring (0-100) to quantify "AI-ness"
Example prompts
- "Analyze this paragraph and suggest improvements to make it sound more human."
- "Score the AI-readability of this article draft."
- "Humanize this text with automatic fixes."
Tips & gotchas
The skill’s scoring engine weighs pattern detection (70%) higher than uniformity analysis (30%). For best results, review suggested changes carefully as automated fixes may not always be appropriate for all writing styles.
TrustedSkills Verification
Unlike other registries that point to live repositories, TrustedSkills pins every skill to a verified commit hash. This protects you from malicious updates — what you install today is exactly what was reviewed and verified.
Installing this skill downloads the exact code at commit 42b871f2, not the current state of the repository. This prevents supply-chain attacks from unauthorized updates.
Security Audits
| Gen Agent Trust Hub | Pass |
| Socket | Pass |
| Snyk | Pass |
Details
- Version
- v1.0.0
- License
- MIT
- Author
- brandonwise
- Installs
- 0
- Updated
- Feb 27, 2026
- Published
- Feb 1, 2026
🌐 Community
Passed automated security scans.
Install command fetches the verified snapshot, not the live repository.