Uxui principles
Evaluate interfaces against 168 research-backed UX/UI principles, detect antipatterns, and inject UX context into AI coding sessions.From its SKILL.md
npx -y skills add newmindsgroup/ai-agent-skills-library --skill uxui-principlesAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its file declares
Copied from the file, not written here
The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.
SKILL.md
2.2 KB, 393 tokens by cl100k_base, as published. Nobody here has run it
UX/UI Principles
A collection of 5 agent skills for evaluating interfaces against 168 research-backed UX/UI principles, detecting antipatterns, and injecting UX context into AI-assisted design and coding sessions.
Source: https://github.com/uxuiprinciples/agent-skills
Skills
| Skill | Purpose |
|---|---|
uxui-evaluator | Evaluate interface descriptions against 168 research-backed principles |
interface-auditor | Detect UX antipatterns using the uxuiprinciples smell taxonomy |
ai-interface-reviewer | Audit AI-powered interfaces against 44 AI-era UX principles |
flow-checker | Check user flows against decision, error, and feedback principles |
vibe-coding-advisor | Inject UX context into vibe coding sessions before implementation |
When to Use
- Auditing an existing interface for UX issues
- Checking if a UI follows research-backed best practices
- Detecting antipatterns and UX smells in designs
- Reviewing AI-powered interfaces for trust, transparency, and safety
- Getting UX guidance before or during implementation
How It Works
- Install any skill from the collection
- Describe the interface, screen, or flow you want to evaluate
- The skill evaluates against the relevant principles and returns structured findings with severity levels and remediation steps
- Optionally connect to the uxuiprinciples.com API for enriched output with full citations
Install
npx skills add uxuiprinciples/agent-skills
Limitations
- Use this skill only when the task clearly matches the scope described above.
- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.
Gives 0 of the 12 instructions most design frontend skills give in 393 tokens
Counted across 1,169 of the 1,878 authors here whose files we hold, read 2026-08-07
- Use CSS variables for color consistencyin 72 of 1169, across 23 files
- Commit to one bold aesthetic direction before codingin 72 of 1169, across 27 files
- Match implementation complexity to the aesthetic visionin 70 of 1169, across 20 files
- Add atmospheric background effects and texturesin 57 of 1169, across 9 files
- Use unexpected spatial compositions and layoutsin 56 of 1169, across 8 files
- Implement real working codein 55 of 1169, across 7 files
- Vary themes and aesthetics across different designsin 48 of 1169, across 7 files
- Launch chromium in headless modein 47 of 1169, across 4 files
- Close the browser when donein 47 of 1169, across 4 files
- Run provided scripts with help flag firstin 47 of 1169, across 4 files
- Wait for network idle statein 47 of 1169, across 4 files
- Use descriptive selectors for elementsin 47 of 1169, across 4 files
Said here and by no other author read
- evaluate the interface against relevant principles
- return structured findings with severity levels
- return remediation steps for findings
- use the skill only when task clearly matches scope
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.