agentleFS
YehudaFrankelYehudaFrankel/clankbrain/.claude/skills/ux-heuristics/SKILL.md

ux-heuristics

Skill16 starsChanged 7 months agoMITView on GitHub

Evaluates interface usability using Nielsen's 10 heuristics + Krug's principles. Returns a severity-scored list of issues. Triggers on "audit this for usability", "heuristic review", "UX issues", "usability check", "ux heuristics".

13 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 12 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If any answer requires effort, the navigation is broken.

    line 35

“Common” is measured: kept by at least 6 in 10 of the 12 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

UX Heuristics

Evaluates interface usability using Nielsen's 10 heuristics + Krug's "Don't Make Me Think" principles. Returns a severity-scored list of what's broken and why.


Core Philosophy

Users scan, they don't read. They satisfice, they don't optimize. They muddle through, they don't figure out.

"Every page should be self-evident. If something requires thinking, it's a usability problem." — Steve Krug


Krug's Three Laws

  1. Don't make me think. Pages should be self-evident. Clear labels beat clever marketing copy.
  2. It doesn't matter how many times I click, as long as each click is mindless. Minimize cognitive effort per interaction.
  3. Get rid of half the words on each page, then get rid of half of what's left. Ruthlessly eliminate unnecessary text.

The Trunk Test

Drop a user on any random page. Can they immediately answer:

  • What site is this? What page am I on? What are the major sections?
  • What are my options at this level? Where am I in the hierarchy? How can I search?

If any answer requires effort, the navigation is broken.


Nielsen's 10 Heuristics

#HeuristicWhat to Check
1Visibility of System StatusLoading indicators? Form submission feedback? Current state visible?
2Match System and Real WorldJargon-free labels? Natural reading order? Icons match mental models?
3User Control and FreedomUndo available? Cancel on every modal? No dead ends?
4Consistency and StandardsSame action = same label? Button styles consistent?
5Error PreventionConfirmation for destructive actions? Inline validation? Disabled states?
6Recognition Rather Than RecallOptions visible? Recent items surfaced? Labels on icons?
7Flexibility and EfficiencyKeyboard shortcuts? Bulk actions? Search as navigation?
8Aesthetic and Minimalist DesignOnly essential info visible? Progressive disclosure? White space?
9Help Recover from ErrorsPlain language? Specific not generic? Suggest a fix?
10Help and DocumentationSearchable? Task-focused? Concrete steps?

Severity Scale

SeverityLabelPriority
0Not a problemSkip
1CosmeticFix if time permits
2MinorFix in next iteration
3MajorFix before shipping
4CatastrophicFix immediately

Audit Output Format

#Heuristic ViolatedIssueSeverityRecommendation
1H8: Minimalist DesignDashboard shows 12 metrics above fold2Progressive disclosure: show top 4, expand for rest
2H1: System StatusNo loading indicator on search3Add spinner or skeleton screen

Sort by severity (highest first). Summary: total issues, count by severity, top 3 fixes.


Quick Diagnostic Checklist (60 seconds)

  • Can I tell what page this is and what I can do here?
  • Is there a clear visual hierarchy?
  • Do all interactive elements look clickable?
  • Is there feedback when I take an action?
  • Can I undo or go back easily?
  • Are error messages helpful and specific?
  • Does it work on mobile without hover?
  • Are tap targets large enough (44x44px)?
  • Is the most important action obvious?
  • Would a first-time user know what to do?

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.