Humanize
Author: Harold Mansfield
Version: 1.0.0
Platform: Claude Cowork
License: MIT
Humanize is a Claude Cowork skill that rewrites AI-generated copy to remove the most common AI writing tells — overused words, hollow phrasing, em dashes, inflated language — without changing the meaning, length, or intent of the original text. It fixes the style, not the substance.’
What it removes:
- Overused AI vocabulary (“pivotal,” “underscore,” “tapestry,” “delve,” “vibrant,” and 30+ others)
- Em dashes, replaced entirely with commas, colons, or sentence breaks
- Puffery and fake significance (“a pivotal moment in the evolving landscape of…”)
“Not just X, but Y” constructions, collapsed into plain statements - Excessive bold formatting
Chatbot sign-offs like “I hope this helps” and “Let me know if you need anything”
After each pass, the skill tells you exactly what was changed and asks whether you want further edits or to download the result as a Word doc, plain text, or Markdown file.
Installation
- To install: Unzip humanize.zip,
- Then go to Cowork → Settings → Capabilities → Skills → Upload Skill, and select the unzipped humanize folder.
- That’s it.
How to use it:
There are no slash commands. Once the skill is installed and toggled on in your Cowork settings, it activates automatically when you paste text and use natural language like:
- “Humanize this”
- “Make this sound human”
- “Remove the AI tells”
- “This sounds like ChatGPT, fix it”
- “Clean up the AI writing”
No special syntax required.
Humanize
Send download link to:
About Me
Harold Mansfield
AI Support Strategist
Sec+ CySA+ NIST 800-37
I help small business owners and teams turn AI confusion into AI solutions.
My background spans 15 years in IT support, infrastructure, cybersecurity, and systems administration for SMBs and corporate teams. That foundation shapes everything I do, from security-aware design to a practical understanding of what actually works in the real world versus what just sounds good in a demo.
I also build things. Most recently I conceived, built, and shipped Samaritan, a 12-agent autonomous OSINT investigation platform built on OpenClaw, running on ParrotOS. It includes automated case management, a curated library of nearly 2,000 intelligence sources, structured evidence pipelines, and upgrade safety automation.
When I show you how agentic AI works, I am showing you something I built myself.
That is the difference. Everything I teach comes from something I have actually built, broken, fixed, and shipped. If you are ready to stop guessing and start getting real results from AI, let’s talk.