Humanizer for Openclaw

A specialized editing agent for Openclaw Skills that identifies and eliminates 24 distinct AI-generated writing patterns to create natural, soulful text.

runesleo
v1.0.0
Mar 7, 2026
0
857
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install runesleo-humanizer

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install runesleo-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?

Humanizer is a professional writing editor designed for Openclaw Skills that focuses on removing the clinical, predictable signatures of large language models. Based on Wikipedia's comprehensive guide to AI writing signs, this tool scans for patterns like inflated symbolism, promotional fluff, and repetitive sentence structures.

Beyond simple editing, these Openclaw Skills empower users to inject personality and 'soul' into their text. It addresses the sterile nature of algorithmic writing by encouraging opinionated perspectives, varied rhythms, and the acknowledgment of complexity, ensuring the final output resonates with human readers rather than sounding like a processed press release.

Humanizer Use Cases

  • Reviewing AI-generated blog posts to remove overused vocabulary like 'delve' or 'tapestry'.
  • Refining technical documentation to eliminate 'copula avoidance' and improve clarity.
  • Humanizing marketing copy by stripping away promotional 'AI-isms' and vague attributions.
  • Converting outline-like 'Challenges' sections into natural, narrative-driven paragraphs.
  • Performing a final anti-AI pass on project reports using Openclaw Skills to ensure authenticity.

How Humanizer Works

  1. The skill performs an initial scan of the provided text to identify 24 specific AI indicators, such as superficial analyses and undue emphasis on significance.
  2. Problematic sections are rewritten to replace robotic constructions with simple, direct language (e.g., using 'is' or 'are' instead of 'serves as').
  3. The agent applies a 'personality' layer, varying sentence lengths and adding first-person perspectives where appropriate to break the algorithmic rhythm.
  4. A self-critique phase is triggered where the agent asks what makes the draft still look like AI.
  5. A final revision pass is executed to eliminate any remaining tells, resulting in a version that sounds genuinely human-written.

Humanizer Setup

To integrate Humanizer into your environment, ensure you have the latest version of Openclaw Skills installed and the humanizer skill file in your directory.

# Register the skill within your local Openclaw Skills repository
openclaw skills add humanizer

# Ensure the agent has read/write permissions for text files
openclaw config set permissions.read write

Humanizer Data Schema & Taxonomy

The Humanizer skill processes text and metadata using the following structure:

Data Element Type Description
Input Content Markdown/String The original AI-generated text to be humanized.
Pattern Registry Array A set of 24 markers (e.g., negative parallelisms, rule of three).
Audit Log List A brief summary of remaining AI tells identified during the final pass.
Soul Injection Logic Heuristics for varying sentence structure and injecting opinions.
Final Output Markdown/String The cleaned, natural-sounding final text.

Humanizer Advanced Features

  • Multi-pass revision workflow that iteratively strips away algorithmic signatures.
  • Soul-injection algorithms that automatically vary prose rhythm and add human-like tangents.
  • Context-aware tone preservation to maintain formal, technical, or casual voices while using Openclaw Skills.
  • Specific detection for 'elegant variation' and 'false ranges' often missed by basic spellcheckers.
  • Direct integration with Wikipedia's WikiProject AI Cleanup standards for up-to-date pattern recognition.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*