adversarial-ux-test
Roleplay the most difficult, tech-resistant user for your product. Browse the app as that persona, find every UX pain point, then filter complaints through a pragmatism layer to separate real problems from noise. Creates actionable tickets from genuine issues only.
Best for UX testing teamsWorks with GitHubLow risk
⌘source
- author
@NousResearch- language
- Python
★107kstars
15kforks
Apr 21, 2026
✦overview.md
Key Features
- ·Roleplays difficult, tech-resistant user personas
- ·Identifies UX friction points beyond technical bugs
- ·Filters complaints through pragmatism layer to separate real issues from noise
- ·Creates actionable tickets from genuine UX problems
- ·Catches confusing terminology, excessive steps, and accessibility issues
Use Cases
- →Identifying confusing terminology that developers understand but users don't
- →Finding too many steps required for basic tasks
- →Detecting missing onboarding or 'aha moments' for new users
- →Spotting accessibility issues like font size, contrast, or click target problems
- →Identifying cold-start problems with empty states or no demo content
- →Finding paywall or signup friction that reduces conversion
Best for
- ✓UX testing teams
- ✓Product managers
- ✓QA engineers focused on user experience
Not ideal for
- !Technical bug detection
- !Performance optimization
- !Security testing
FAQs
name
adversarial-ux-test
description
Roleplay the most difficult, tech-resistant user for your product. Browse the app as that persona, find every UX pain point, then filter complaints through a pragmatism layer to separate real problems from noise. Creates actionable tickets from genuine issues only.
license
MIT
version:1.0.0
author:Omni @ Comelse
metadata:{"hermes":{"tags":["qa","ux","testing","adversarial","dogfood","personas","user-testing"],"related_skills":["dogfood"]}}
Adversarial UX Test
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.
Why This Works
Most QA finds bugs. This finds friction. A technically correct app can still be unusable for real humans. The adversarial persona catches:
- Confusing terminology that makes sense to developers but not users
- Too many steps to accomplish basic tasks
- Missing onboarding or "aha moments"
- Accessibility issues (font size, contrast, click targets)
- Cold-start problems (empty states, no demo content)
- Paywall/signup friction that kills conversion
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.
How to Use
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"
$install
1-click copynpx skills add NousResearch/hermes-agent --skill adversarial-ux-testSafety assessment
★
Clarity score
How clear and easy to understand the SKILL.md instructions are, rated from 1 to 5.
4/ 5
very goodClear and well structured, with only minor parts that might need a second read.
◎
Actionability score
How directly an agent can act on the SKILL.md instructions, rated from 1 to 5.
3/ 5
mediumPartially actionable with several concrete steps, but still missing important details.