Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Claude Design System Prompt

github.com

Post reply on HN
Print view View original

11–20 of 35 posts

Re: Claude Design System Prompt

#11

Post by weird-eye-issue »

bossyTeacher wrote: post #3
jdormit wrote: post #2

This would be much more interesting if it detailed how the prompt/skills were reverse-engineered. As it is it seems like this could just be the output from “hey Claude write me a system prompt that works like Claude Design”.

> This would be much more interesting if it detailed how the prompt/skills were reverse-engineered That would enable Anthropic to block the technique.

They have never attempted to hide their system prompts in fact they explicitly publish them for Claude (https://platform.claude.com/docs/en/release-notes/system-pro...) and Claude Code they provide a proxy option which then makes it trivial to see the full requests and responses including the prompts and tool usage...

Re: Claude Design System Prompt

#12

Post by simonw »

simonw wrote: post #9

I can't even tell if this repository is based on prompts extracted from Claude Design or if the author had an LLM create all of these prompts in it from scratch. The fact that they encourage and accept PRs indicates that this isn't intended as a direct prompt extraction exposure project - plus the license, which should indicate they have the authorship necessary to license that content. Assuming this IS a complete gr…

If you ask Claude Design itself to list the names of the skills available to it you get:

  Animated video
  Interactive prototype
  Make a deck
  Make a doc
  Make tweakable
  Claude API in prototypes
  Frontend design
  Wireframe
  Export as PPTX (editable)
  Export as PPTX (screenshots)
  Create design system
  Save as PDF
  Save as standalone HTML
  Send to Canva
  Handoff to Claude Code
Which does not match the structure of this project at all.

Re: Claude Design System Prompt

#14

Post by krisknez »

simonw wrote: post #12
simonw wrote: post #9

I can't even tell if this repository is based on prompts extracted from Claude Design or if the author had an LLM create all of these prompts in it from scratch. The fact that they encourage and accept PRs indicates that this isn't intended as a direct prompt extraction exposure project - plus the license, which should indicate they have the authorship necessary to license that content. Assuming this IS a complete gr…

If you ask Claude Design itself to list the names of the skills available to it you get: Animated video Interactive prototype Make a deck Make a doc Make tweakable Claude API in prototypes Frontend design Wireframe Export as PPTX (editable) Export as PPTX (screenshots) Create design system Save as PDF Save as standalone HTML Send to Canva Handoff to Claude Code Which does not match the structure of this project at al…

There's this one which seems like it matched it: https://github.com/jimliu/baoyu-design

Re: Claude Design System Prompt

#15

Post by doginasuit »

I've been using Claude Design to make animated SVGs, and I've learned a thing or two about its limits and how to get around them for that narrow purpose.

One thing I've learned is that you have to ask it to first come up with a robust way to define the geometry and then apply that to an SVG. Without that first step, it just guesses at where everything should be that isn't directly connected with a node, and it is hilariously bad. But with that first step it is capable of creating some incredible geometry algorithmically from detailed instructions.

The other thing is that whatever tool prepares the svg for export will strip the animations as part of a sanitizing process, it won't even see that has occurred. You have to ask it to export to a different file type like my-animation.svg.txt, and then obviously you want to inspect it because svg can carry exploits not related to animation.

Its ability to generate these designs is part toddler with a crayon, part savant. It won't be able to create any quality organic figures without reference material, but its ability to create intricate and mathematically correct design and animate it is promising. I haven't used it extensively so I'd be very interested to hear other observations and advice.

Re: Claude Design System Prompt

#16

Post by simonw »

krisknez wrote: post #14
simonw wrote: post #12

Earlier quoted context omitted.

If you ask Claude Design itself to list the names of the skills available to it you get: Animated video Interactive prototype Make a deck Make a doc Make tweakable Claude API in prototypes Frontend design Wireframe Export as PPTX (editable) Export as PPTX (screenshots) Create design system Save as PDF Save as standalone HTML Send to Canva Handoff to Claude Code Which does not match the structure of this project at al…

There's this one which seems like it matched it: https://github.com/jimliu/baoyu-design

Yeah these skills match that list of names, looks like this one may have extracted all of the prompts: https://github.com/JimLiu/baoyu-design/tree/main/skills/baoy...

Re: Claude Design System Prompt

#17

Post by robotswantdata »

simonw wrote: post #9

I can't even tell if this repository is based on prompts extracted from Claude Design or if the author had an LLM create all of these prompts in it from scratch. The fact that they encourage and accept PRs indicates that this isn't intended as a direct prompt extraction exposure project - plus the license, which should indicate they have the authorship necessary to license that content. Assuming this IS a complete gr…

Agree, it’s vibe slopped rather than the actual Claude design system prompt

Re: Claude Design System Prompt

#19

Post by xyzzy_plugh »

smokel wrote: post #10
xyzzy_plugh wrote: post #8

Earlier quoted context omitted.

Isn't it, though? What's the copyright status of the output of these tools?

If this is regular output of the LLM, I'm not sure, but given that the author proclaims that this is reverse engineered, then they are not allowed to redistribute it under their own license terms. The terms of service are also pretty clear on this not being allowed, which makes it extra hard to defend (section 3.3): > You may not access or use, or help another person to access or use, our Services in the following wa…

How can you tell what regular output is? Is there a special output when you successfully jailbreak? Is there a meaningful distinction between jailbroken prompts and hallucinations? Are certain prompts against the terms of service? If so, is it easy to determine if they are? Who determines this? If you produce output that is against the terms of service, does that change the copyright status of the works?

I'd love to see this go to court.

Re: Claude Design System Prompt

#20

Post by throwaway7356 »

smokel wrote: post #10
xyzzy_plugh wrote: post #8

Earlier quoted context omitted.

Isn't it, though? What's the copyright status of the output of these tools?

If this is regular output of the LLM, I'm not sure, but given that the author proclaims that this is reverse engineered, then they are not allowed to redistribute it under their own license terms. The terms of service are also pretty clear on this not being allowed, which makes it extra hard to defend (section 3.3): > You may not access or use, or help another person to access or use, our Services in the following wa…

The terms of service are between Anthropic and one of their subscribers. So Anthropic can maybe cancel their contract.

This doesn't affect what copyright law allows or does not allow.

Also I think Anthropic very much suppports gathering data by whatever means possible. That should work both ways.

Post reply on HN