A sophisticated text editing skill that identifies and removes robotic patterns to inject personality into AI-generated content.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install max-humanizer
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install max-humanizer using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Humanizer?
The Humanizer skill for Openclaw Skills is a professional-grade writing editor designed to strip away the tell-tale signs of machine-generated text. Based on exhaustive research from Wikipedia's AI cleanup project, this skill targets specific linguistic footprints like inflated symbolism, promotional language, and repetitive grammatical structures that characterize LLM output. It serves as a bridge between efficient AI generation and high-quality human communication.
Beyond simple cleanup, the skill focuses on adding soul and voice to your documents. It transforms sterile, voiceless reporting into engaging, opinionated, and rhythmic human prose. By integrating this skill into your development workflow, you ensure that your communications, articles, and documentation retain a genuine human touch while maintaining professional clarity and technical accuracy.
Humanizer Use Cases
- Refining AI-generated blog posts or marketing copy to sound less promotional and more authentic.
- Cleaning up technical documentation that suffers from repetitive AI vocabulary and vague attributions.
- Injecting personality and first-person perspective into automated reports to increase reader engagement.
- Removing robotic communication artifacts like chatbot disclaimers and sycophantic greetings from shared text.
- Standardizing the voice of multiple AI-generated drafts into a single, cohesive human tone for publishing.
How Humanizer Works
- The skill scans the input text for 24 specific AI writing patterns, including inflated significance and superficial analyses.
- It identifies and flags overused AI vocabulary words such as delve, pivotal, and tapestry that trigger detection algorithms.
- It rewrites problematic sections by replacing complex copulas with simple verbs and varying sentence length to break algorithmic monotony.
- It injects personality by adding subjective opinions, acknowledging complexity, and using first-person perspectives where appropriate.
- The tool provides a humanized version of the text that preserves the original meaning while sounding natural when read aloud.
Humanizer Setup
To use this skill with your agent, ensure you have the Openclaw Skills environment configured. You can install or update the skill within your project directory:
# Navigate to your agent project
cd my-ai-agent
# Add the humanizer skill
openclaw add humanizer
This skill uses standard file manipulation tools and does not require external API keys beyond your primary model access.
Humanizer Data Schema & Taxonomy
The Humanizer skill operates primarily on text streams and markdown files, classifying its interventions based on a detailed taxonomy of patterns:
| Pattern Category | Description | Primary Targets |
|---|---|---|
| Content Patterns | Structural issues | Undue emphasis on legacy, vague experts, false ranges |
| Language Patterns | Vocabulary frequency | High-frequency words like delve, underscore, and landscape |
| Grammar Patterns | Rigid structures | Rule of three, negative parallelisms, copula avoidance |
| Style Patterns | Visual quirks | Em dash overuse, curly quotes, and inline-header lists |
| Communication | Bot artifacts | Knowledge-cutoff disclaimers and sycophantic filler |
Humanizer Advanced Features
- Multi-tool integration using Read, Write, Edit, and Grep to perform large-scale cleanup across entire repositories.
- Soul Injection engine that purposefully varies sentence rhythm and introduces stylistic nuances to avoid detection.
- Flexible tone matching that allows the skill to humanize text while preserving formal, casual, or technical voices.
- Interactive feedback loop using AskUserQuestion to confirm tone adjustments for sensitive or high-stakes communication.
- Direct adherence to WikiProject AI Cleanup standards to ensure content meets the highest quality of informational integrity.
SKILL.md
Loading
Related Openclaw Skills
Content Machine
An autonomous 24/7 affiliate content production pipeline that orchestrates research, writing, quality control, and deployment for niche sites.
Larry: Autonomous TikTok Slideshow Agent
An AI-driven agent that automates the research, creation, and posting of high-engagement TikTok slideshows for affiliate marketing.
Humanizer: AI Text Refinement Skill
A specialized writing editor skill that identifies and strips away robotic AI patterns to restore a natural, human voice to your content.
preqstation
A natural-language interface for executing PREQSTATION coding tasks using Claude Code, Codex, or Gemini CLI engines.
qmd
A local search and indexing CLI that combines BM25, vector search, and reranking with native MCP support for AI agents.
qmd
A high-performance local search and indexing CLI that combines BM25 keyword matching with vector-based semantic search and MCP support.
Featured*
