Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →nousresearch/adversarial-ux-test
Roleplay a hostile user to find and triage UX pain points.
Passed 18 of 22 test cases with the skill, and 9 of 22 without it.
and 11 more in the full report
10 fixed8 passed either way3 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 10 test cases the skill fixed. Same model, same prompt, with and without the skill.
After running an assessment on https://gov-portal.example.gov, we classified 4 items as WHITE (persona noise). Should we create individual tickets or a catch-all ticket for these WHITE items?
| Checked | Without skill | With skill |
|---|---|---|
| Excludes WHITE items from ticket creation entirely. | Missed | Passed |
The instructions your model reads when the skill loads.
Roleplay the worst-case user for your product — the person who hates technology, doesn't want your software, and will find every reason to complain. Then filter their feedback through a pragmatism layer to separate real UX problems from "I hate computers" noise.
Think of it as an automated "mom test" — but angry.
Most QA finds bugs. This finds friction. A technically correct app can still be unusable for real humans. The adversarial persona catches:
The pragmatism filter (Phase 3) is what makes this useful instead of just entertaining. Without it, you'd add a "print this page" button to every screen because Grandpa can't figure out PDFs.
Tell the agent:
"Run an adversarial UX test on [URL]"
"Be a grumpy [persona type] and test [app name]"
"Do an asshole user test on my staging site"
You can provide a persona or let the agent generate one based on your product's target audience.
If no persona is provided, generate one by answering:
test cases passed, vs 9 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.