A CLI-driven utility for identifying and eliminating common AI writing patterns to make text sound more natural.
The fastest way to install a skill directly from the registry.
npx clawhub@latest install humanize-ai
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
Copy this prompt to OpenClaw to install it automatically.
Help me install humanize-ai using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Get the raw skill files in a ZIP archive.
The Humanize AI skill provides a robust framework for developers and content creators to sanitize text generated by large language models. By integrating these Openclaw Skills into your workflow, you can programmatically identify and rectify linguistic patterns that signal AI authorship, such as predictable vocabulary, excessive puffery, and repetitive sentence structures.
This toolset goes beyond simple detection; it offers an automated pathway to transform robotic prose into more authentic, human-like content. It is particularly valuable for users who need to maintain a consistent brand voice or ensure that their automated content pipelines produce high-quality, undetectable output.
To get started with these Openclaw Skills, ensure you have a Python environment ready. Navigate to the skill directory and use the following commands:
# Check the analysis capabilities
python scripts/analyze.py --help
# Test the humanization script on a sample file
python scripts/humanize.py input.txt -o output.txt
The skill manages its detection logic and replacement rules through a structured JSON configuration. This allows for high degrees of customization when using Openclaw Skills for different niches.
| Component | Description |
|---|---|
scripts/patterns.json |
The core configuration file containing all detection strings and replacement mappings. |
ai_words |
A list of high-probability AI terms that trigger flags but not auto-replacements. |
replacements |
A dictionary of key-value pairs where the key is the AI phrase and the value is the human alternative. |
chatbot_artifacts |
A list of common conversational phrases used by LLMs that are slated for total removal. |
puffery |
Adjectives and promotional terms that often indicate non-human authorship. |
patterns.json, enabling users to define their own industry-specific AI detection rules.Loading
A professional AI-driven content creator for XiaoHongShu that generates viral titles, body copy, hashtags, and image prompts in seconds.

An advanced OSINT tool for monitoring Persian-language social media signals to detect geopolitical escalation and trending narratives in real-time.

A specialized monitoring tool that scans global news to identify and analyze layoffs specifically caused by AI adoption and automation.

A professional analytical framework designed for AI startups to classify market signals and deliver actionable strategic intelligence.

An advanced writing editor that identifies and removes AI-generated patterns to make text sound authentic and human.

A TypeScript CLI toolkit designed to analyze and transform AI-generated text to bypass detection and appear human-written.








































