Skip to content

Humanizer AI Prompt #50

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 2 commits into
base: main
Choose a base branch
from

Conversation

TabOne2507
Copy link

🚀 Summary

This PR introduces a new “Humanizer AI” prompt template designed to help LLMs rewrite raw content drafts into more natural, engaging, and professional messages while preserving key technical content and author style.


✨ Changes

  • New file Humanizer AI Prompt/convert_or_generate_with_human_touch.txt containing:
    • Prompt instructions for transforming an input content.
    • Parameter definitions (Writing Style, Content Type, Creativity Level, Length Ratio, Word Preservation, Semantic Preservation, Style Mimicking).
    • Usage examples with input and desired output sections.

🛠️ Motivation

Many AI-driven assistants produce overly generic or robotic text. This template ensures:

  • 40% word preservation to keep original language intact.
  • 75% semantic preservation so no crucial points are lost.
  • 60% creativity for natural transitions and warmth.
  • 1× length ratio to match input length.
  • 70% style mimicry to maintain the author’s voice.

By standardizing these parameters, teams can quickly fine-tune or zero-shot generate polished, human-touch content in a consistent way.


✅ Testing

Manual verification:

  • Copy an existing prompt draft into the Input block.
  • Run the prompt in your preferred LLM playground.
  • Confirm the output meets the parameter constraints (length, word overlap, tone).

📖 Documentation

  • See Humanizer AI Prompt/convert_or_generate_with_human_touch.txt for full instructions and examples.
  • Feel free to tweak parameter defaults or extend with additional options (e.g., “Tone Warmth,” “Formality Level,” “Humor”).

🤝 Review

  • Focus areas: clarity of instructions, completeness of parameter definitions, formatting consistency.
  • Optional: suggestions for new test cases or example drafts to validate edge cases (very short/long emails, highly technical content, etc.).

@TabOne2507 TabOne2507 changed the title TabOne2507 - Humanizer AI Prompt Humanizer AI Prompt Apr 23, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

1 participant