undetectable-ai
Make AI text undetectable. TypeScript CLI that scans ChatGPT, Claude, OpenClaw output for patterns flagged by GPTZero, Turnitin, Originality.ai, then auto-fixes them to pass as human-written. Use to bypass AI detection, evade checkers, or humanize text before submission.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/artur-zhdan/undetectable-aiWhat This Skill Does
The undetectable-ai skill is a powerful TypeScript-based CLI toolkit designed to analyze and neutralize common AI-generated writing artifacts. It functions by identifying specific vocabulary choices, sentence structures, and chatbot-typical phrasing that platforms like GPTZero, Turnitin, and Originality.ai flag as non-human. By performing automated replacements of repetitive filler phrases and correcting structural patterns, this skill helps users humanize AI-generated text before publication or submission, effectively mitigating the common 'AI-written' signature.
Installation
To integrate this tool into your OpenClaw environment, execute the following command in your terminal:
clawhub install openclaw/skills/skills/artur-zhdan/undetectable-ai
Once installed, navigate to the skill directory and ensure your environment is prepared by running npm install within the scripts folder. This ensures all dependencies required for the analyzer and transformer scripts are correctly resolved.
Use Cases
This skill is ideal for content creators, students, and professionals who utilize AI assistants to generate initial drafts but require a more natural, human-like output. It is particularly useful for:
- Cleaning up blog posts or articles generated by ChatGPT or Claude to improve readability and bypass automated detection.
- Iteratively refining academic drafts to ensure they reflect a personal writing voice rather than synthetic patterns.
- Batch-processing documentation files to remove repetitive corporate-sounding filler phrases.
Example Prompts
- "OpenClaw, please analyze my essay 'draft.txt' for detectable AI patterns and show me the report."
- "Run the transformation script on 'article.md' to rewrite the text and save the result to 'humanized_article.md'."
- "Scan all files in my current folder for AI-detection risks and output the results in JSON format."
Tips & Limitations
While the undetectable-ai skill is highly effective at removing mechanical patterns, it is not a silver bullet. The software excels at removing 'AI-isms' like 'furthermore' or 'in order to,' but it cannot replicate the complex nuance of deep human thought. Use the provided patterns.json file to customize the flagging logic based on your specific writing style. Always perform a final manual review to ensure your content retains its original meaning and creative flair after automated transformations.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-artur-zhdan-undetectable-ai": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: file-read, file-write, code-execution
Related Skills
humanize-ai
Humanize AI content by detecting and auto-fixing AI generated content. Humanize AI text using Python scripts. Scans for AI vocabulary, puffery, chatbot artifacts, and auto-replaces filler phrases. Use when you want to analyze text in AI detector and bypass it in future, batch-process files, run automated cleanup, or get a report before manual humanizing.
humanize-ai
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.
humanizer
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.
study
Help users study and learn effectively. Use when the user wants to learn new material, review concepts, prepare for exams, or memorize information. Supports active recall, spaced repetition, flashcard generation, quizzing, concept explanation, and study planning.
humanizer
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.