LaunchKit · 2026
Back to Skills

ai-writing-humanizer

AI & LLMsv0.1.0

Automatically strip AI writing patterns and stock phrases from user-facing prose before sending.

0
363 downloads
by @hosthobbit

Setup & Installation

openclaw skills install @hosthobbit/ai-writing-humanizer

Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:

npx clawhub install ai-writing-humanizer

What This Skill Does

Strips common AI writing patterns from prose before it reaches readers. Covers hedging phrases, stock transitions, em dashes, rule-of-three constructs, passive voice markers, and performed authenticity cues. Operates via a Python script or importable function.

Catches specific linguistic fingerprints that general proofreaders miss, rather than relying on the author to self-edit for AI patterns.

When to use it

  • Cleaning up AI-drafted blog posts before publishing
  • Preparing client-facing emails written with AI assistance
  • Humanizing AI-generated product copy
  • Reviewing longer AI responses before sending to customers
  • Stripping AI tells from grant or proposal drafts

Example Workflow

Here's how your AI assistant might use this skill in practice.

INPUT

User asks: Humanize this 300-word AI-written support email before I send it.

AGENT
  1. 1Load the input text from the user
  2. 2Run scripts/humanize.py --input text.txt --output cleaned.txt
  3. 3Scan for hedging phrases, serial lists, em dashes, and passive voice constructs
  4. 4Rewrite or remove flagged patterns
  5. 5Return the cleaned text to the user
OUTPUT

A revised version of the email with AI-characteristic phrasing removed or rewritten in a more natural voice.