A sophisticated editing skill that systematically removes AI writing signatures to produce text with authentic human soul and personality.
The fastest way to install a skill directly from the registry.
npx clawhub@latest install wikipedia-humanizer
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 wikipedia-humanizer using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Get the raw skill files in a ZIP archive.
The Humanizer skill for Openclaw Skills is a specialized writing editor designed to purge the distinct signatures of machine-generated text. Based on the comprehensive research from Wikipedia's AI Cleanup project, this tool identifies twenty-four distinct patterns—from inflated symbolism and promotional fluff to repetitive grammatical structures like the rule of three and em dash overuse. Unlike simple paraphrasers, this skill focuses on injecting rhythm, opinion, and complexity back into the prose to ensure it resonates as truly human-written.
By implementing this skill within your agent workflow, you can ensure that your content avoids the sterile, voiceless quality typical of modern LLMs. Using Openclaw Skills allows your agent to not only clean up technical 'tells' but also to take a stance, vary sentence length, and acknowledge nuance in a way that algorithmic generation often misses. It is an essential tool for anyone needing to maintain a high-quality, authentic digital presence.
To integrate the Humanizer into your agent, ensure you have the necessary file permissions for reading and editing. Use the following command to initialize the skill within your environment:
# Install the skill to your project
openclaw add humanizer
# Run a scan on specific files
openclaw run humanizer --path ./drafts/article.md
The Humanizer skill processes text through a multi-stage pipeline, tracking modifications via the following schema:
| Attribute | Description |
|---|---|
source_text |
The original markdown or plain text input. |
patterns_detected |
An internal list of identified AI signatures (e.g., 'rule of three', 'em dash overuse'). |
draft_rewrite |
The initial humanized version after the first pass. |
audit_report |
Brief bullet points identifying remaining AI tells after the draft pass. |
final_output |
The polished, high-quality humanized text string. |
Loading
An automated workflow for researching trending topics and generating platform-optimized social media content from fresh news.

An automated macOS utility that captures periodic snapshots to provide AI-powered encouragement and daily activity summaries.

A developer-centric skill for managing interactive mobile dashboard widgets through a GitHub-backed JSON workflow.

An automated bridge that synchronizes Notion content to local Obsidian vaults with full metadata and scheduled updates.

A headless-ready integration for the Box CLI to manage cloud content and leverage Box AI directly from your agent.

A powerful tool for minting and managing permanent, on-chain identities and behavioral traits for AI agents on the Base network.








































