Skip to content

Instantly share code, notes, and snippets.

@AWolf81

AWolf81/ Universe Of Thoughts Skill

Last active December 5, 2025 07:49
Show Gist options

  • Select an option

    Learn more about clone URLs
  • Save AWolf81/01fcaa59a30d6730bdf17506f010a451 to your computer and use it in GitHub Desktop.

Select an option

Learn more about clone URLs
Save AWolf81/01fcaa59a30d6730bdf17506f010a451 to your computer and use it in GitHub Desktop.
Download ZIP
Universe Of Thoughts Skill
Raw
README.md

Downloaded the PDF summary from https://drive.google.com/file/d/1omGpOCG7BFOkUjitlfe8aB9Ga00b2kQB/view created by https://tiktok.com/@officeoptout

See Universe Of Thoughts framework.pdf

It is based on

UNIVERSE OF THOUGHTS: ENABLING CREATIVE REASONING WITH LARGE LANGUAGE MODELS by Yuto Suzuki, Farnoush Banaei-Kashani https://arxiv.org/abs/2511.20471

Generated universe-of-thoughts.zip skill with Claude skill-creator skill based on the PDF summary.

Usage

  1. Download zip-file (just one SKILL.md, created by Claude with skill-creator skill) - extract if you want to review the skill content.
  2. Add to Claude.ai Chat:
  • Visit Claude.ai Settings → Skills
  • Upload the zip file
  • Skill will be imported and enabled
  1. Click three dots and select try in chat. This will open a chat with something like Hey Claude—ich habe gerade die „universe-of-thoughts“-Fähigkeit hinzugefügt. Kannst du etwas Großartiges damit machen?

Tests

Created an example chat with the skill to compare standard approach with UoT Framework.

The problem is about boosting a fictive coffee shop.

Overall standard approach scored 52% and UoT with 72.5% based on Claude's weights.

UoT wins at 12 of 20 different dimension it shines at unique new ideas (I haven't fully checked them but they seem good). Standard approach wins at 7 of 20 different dimension.

So standard approach wins at the following points:

  • Feasibility & Risk management --> more focused on best practices
  • Implementation complexity --> less complicated to implement
  • Time to first Value --> faster but with lower potential
  • Execution risk --> lower risk because of lower propability of ground breaking ideas
  • Market or staff education --> lower education req. as it follows best practices
  • Revenue predictability --> proven methods so better to predict.

You can find the full test here

Improvements

  • I've already tried to improve the Skill, so feasibility, risks and execution better into account but that wasn't working. So I think it's best to do both (see The Verdict from the Chat), so for tactical execution (standard approach) and strategic value use Universe of Thoughts. With this in the Coffee shop example, it's possible to test first ideas from (lower risk + quick wins) the standard approach and plan the strategic points from UoT with a longer time frame (higher risk + more revenue potential).
  • Let Claude review the skill with the original research paper from arxiv

Feedback or improvements

If you're improving the skill or found issues would be great to know. Also if you have an interesting conversation with Claude, would be awesome to see.

You can contact my via

License

MIT

Display the source blob
Display the rendered blob
Raw
Universe Of Thoughts Framework.pdf
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
@maosi100
Copy link

maosi100 commented Dec 5, 2025

Amazing!!

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment