The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Back to feedPost
I built an open-source skill that stops AI from making every design look the same
Every AI-generated website looks the same. Centered hero. Purple gradient. Three feature cards.
The reason isn't bad taste. AI agents fill gaps in a brief with the average of their training data. If you don't define what "not average" means for your project, you get the mean.
So I built Intent Interrogator, a free skill that works across Claude Code, Codex, Cursor, Copilot, and any agent that reads the Agent Skills standard.
It does three things:
Interrogates - asks 4 questions before writing any code:
→ What should someone feel in the first 3 seconds?
→ Who specifically is this for?
→ What's the one constraint I must respect?
→ What should this definitely not look like?
Persists - saves the brief to a .intent/ file inside your project. New chat, new week, new agent, the intent is still there.
Verifies - before declaring the work done, it compares what it built against what you asked for, and produces an Intent Receipt showing where it matched and where it drifted.
That last part is the piece I haven't seen anywhere else.
You don't need to code to use it. You just answer four questions.
Free forever. Feedback welcome.
#design #ai #opensource #productdesign
github.com
GitHub - yutivora/intent-interrogator
Contribute to yutivora/intent-interrogator development by creating an account on GitHub.
The point about agents filling gaps with the average is spot on. Forcing the brief to say what not to do probably helps more than any style prompt.
The brief gap point is the real one. Give an agent three reference sites and a hard rule like no centered hero, and the output changes more than any prompt tweak.
The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Related posts
The fix for an agent that keeps getting your design system wrong isn't a better prompt.
It's putting the rules where the agent reads them.
In the repo. In skills. In checks it can run itself.
Writing a course about exactly this.
What sells it for me is the refusal telling the agent exactly where the token should go. A bare "no hex" error usually just sends it looping. Does guard.mjs run only as an agent hook, or in pre-commit too so it catches humans as well?
I'd pick Light for an analysis tool, the charts and sources read better on a pale surface and the violet bars still pop. Dark works as the night option. Is the sources panel on the right open by default?
Really liked how these designs turned out!
Explored a concept for AI SaaS product, focusing on a clean interface and a simple, intuitive chat experience.
Tried two different layout variation for the hero section.
Which would you like?
13 voted
57%
10 voted
43%
23 votes
Closed
Really clean concept! 👏
I like the second layout more — the headline "Your ideas deserve an intelligent partner" + the chat preview below makes the AI feel real and easy to use immediately. The first one is also clean, but this one sells the product faster.
I also design SaaS...