human-writing

Human Writing Guidelines

Make AI-generated writing feel like a human wrote it.

How It Works

1. Fetch the latest guidelines from the source URL
2. Read the text or file provided
3. Apply guidelines to identify AI tells and suggest improvements
4. Output specific, actionable changes

Guidelines Source

Fetch fresh guidelines before each review:

https://guidelines.sh/api/guidelines?type=writing

Use WebFetch to retrieve the latest rules.

Quick Reference

Priority order for humanizing text:

1. Kill preamble - Remove "Certainly!", "Great question!", "I'd be happy to help"
2. Ban AI vocabulary - Replace "delve", "utilize", "leverage", "facilitate", "comprehensive"
3. Use contractions - "don't" not "do not", "it's" not "it is"
4. Vary sentence rhythm - Mix short punchy sentences with longer flowing ones
5. Get specific - Replace vague claims with concrete details
6. Cut filler - Remove "It's important to note that", "In order to"
7. Sound opinionated - Take stances instead of hedging everything

Usage

When text is provided:

1. Fetch guidelines from the source URL above
2. Analyze text against all rules
3. List specific violations found with examples
4. Provide rewritten version with all fixes applied

When reviewing a file:

1. Read the file content
2. Apply the same analysis
3. Output a diff or rewritten version