ux-heuristics
Evaluate and improve interface usability using heuristic analysis
Install / Use
npx skills add wondelai/skills --skill ux-heuristicsInstalls into whichever agent you are using.
SKILL.md
Installable skill definition
Quality Score
Category
Development & EngineeringSupported Platforms
Our assessment of ux-heuristics
ux-heuristics scores 84/100 on our quality scale, 2886th of 4,700 Development & Engineering skills we index.
Its SKILL.md is 16 KB long, well organised into 27 sections and no code examples: a thorough specification that gives an agent plenty to work with.
With 2,248 GitHub stars, it is one of the more widely adopted skills in the catalogue.
Maintenance, license and trust
- The repository was last updated about 2 months ago, so ux-heuristics is actively maintained.
- Our last check on 2026-11-05 found the source still online.
- It is released under the MIT license, a permissive license that allows use, modification and commercial use with attribution.
- Its trust signals score 100/100, with no cautions. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.
Safety scan
No issues foundOur scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.
AI review by kimi-k2.7-code on 2026-10-01. Automated pattern scan on 2026-10-01. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.
ux-heuristics compared with similar skills
All 4 of these similar skills score higher than ux-heuristics; compare them before choosing.
| Skill | Score | Stars | Updated | Format |
|---|---|---|---|---|
| ux-heuristics (this skill)by wondelai | 84 | 2.2k | 2mo ago | SKILL.md |
| taste-skillby Leonxlnx | 100 | 116.8k | 8d ago | CLAUDE.md |
| ai-job-searchby ai-job-search-dev | 100 | 72.1k | today | CLAUDE.md |
| claude-howtoby luongnv89 | 100 | 47.3k | 2d ago | CLAUDE.md |
| Claude-Code-Game-Studiosby Donchitos | 100 | 39.7k | 7d ago | CLAUDE.md |
Frequently asked questions
- How do I install ux-heuristics?
- Run
npx skills add wondelai/skills --skill ux-heuristics. The install tabs above show the steps for each supported agent. - Which AI agents does ux-heuristics work with?
- It is written for Universal, as a SKILL.md file. Other agents that read the same format can often use it too.
- Is ux-heuristics safe to use?
- Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It is MIT-licensed and scores 100/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
- Is ux-heuristics still maintained?
- The repository was last updated about 2 months ago, so ux-heuristics is actively maintained.
Skill content
View source on GitHubname: ux-heuristics description: 'Evaluate and improve interface usability using heuristic analysis. Use when the user mentions "usability audit", "users are confused", "form usability", "navigation problems", "Nielsen heuristics", "cognitive walkthrough", or "is this easy to use". Also trigger when reviewing a design for usability issues, improving form-completion rates, or evaluating information architecture and navigation. Covers Krug''s laws, Nielsen''s 10 heuristics, severity ratings, dark-pattern recognition, and accessibility. For visual design fixes, see refactoring-ui. For conversion-focused audits, see cro-methodology.' license: MIT metadata: author: wondelai version: "1.6.0"
UX Heuristics Framework
Practical usability principles for evaluating and improving user interfaces. Users don't read, they scan; they don't make optimal choices, they satisfice; they don't figure out how things work, they muddle through.
Core Principle
"Don't Make Me Think" — every page should be self-evident. If something requires thinking, it's a usability problem. Users have limited patience and cognitive bandwidth, so design for the scanning, satisficing, and muddling-through behavior described above.
Scoring
Goal: 10/10. Audit the interface, rate every issue on the severity scale below, then score the interface from its Quick Diagnostic results: start at 10 and subtract per failed diagnostic row, weighted by the worst severity it triggers (catastrophic/major rows cost ~2, minor/cosmetic ~1). Bands: 9-10 = no severity-3+ issues and ≤1 failed diagnostic row; 6-8 = some major issues or several failed rows; 3-5 = a catastrophic issue or many failed rows; ≤2 = core tasks blocked. Always state the current score, the highest-severity issues, and the specific fixes needed to reach 10/10.
Krug's Usability Principles
Laws 1-3 are Krug's Three Laws of Usability; #4, the Trunk Test, is his navigation orientation check.
1. Don't Make Me Think
Core concept: Every question mark that pops into a user's head adds cognitive load and distracts from the task.
Why it works: Users are on a mission — they don't want to puzzle over labels or decode clever marketing language. The less thinking required, the more likely they complete the task.
Key insights:
- Clever names lose to clear names every time
- Marketing-speak creates friction; plain language removes it
- Unfamiliar categories force users to stop and interpret
- Ambiguous links and buttons cause hesitation
Product applications:
| Context | Application | Example | |---------|-------------|---------| | Navigation labels | Self-evident names | "Get directions" not "Calculate route to destination" | | CTAs | Action verbs users understand | "Sign in" not "Access your account portal" | | Error states | Tell users what to do next | "Check your email format" not "Validation error" |
Copy patterns:
- Action-oriented buttons: verb + noun ("Create account", "Download report")
- Avoid jargon: "Save" not "Persist", "Remove" not "Disassociate"
- If a label needs explanation, simplify the label
Ethical boundary: Clarity should serve users — never use plain language as a veneer to hide unfavorable terms.
See: references/krug-principles.md when you need the full Krug method — scanning/satisficing/muddling psychology, the goodwill reservoir, homepage and tagline guidance, and the $0 usability-testing protocol (how many users, the test script).
2. It Doesn't Matter How Many Clicks
Core concept: The myth says "users leave after 3 clicks." In reality users don't mind clicks if each one is painless, obvious, and confidence-building.
Why it works: Cognitive effort per click matters more than click count. Users abandon when they lose confidence, not when they run out of patience for clicking.
Key insights:
- Each click should be painless, obvious, and confidence-building
- Three mindless clicks beat one click that requires deliberation
- Shallow nav with clear labels beats deep nav with vague ones
Product applications:
| Context | Application | Example | |---------|-------------|---------| | Checkout flows | Make each step obvious | Clear step indicators with descriptive labels | | Settings | Clear categories over flat lists | "Account > Security > Change password" (3 confident clicks) | | Onboarding | Small, clear steps | Wizard with one clear action per step |
Copy patterns:
- Progress indicators: "Step 2 of 4: Shipping details"
- Confirmations at each step: "Great, your email is verified. Now let's set up your profile."
- Clear link text: "View all running shoes" not "Click here"
Ethical boundary: Never use extra steps to bury cancellation flows — every click should move users toward their goal, not away from it.
3. Get Rid of Half the Words
Core concept: Remove half the words on each page, then half of what's left. Brevity makes useful content prominent and respects the user's time.
Key insights:
- Happy-talk ("Welcome to our website!") wastes space
- Instructions nobody reads should be removed
- "Please" and "Kindly" and polite fluff add noise
- Shorter pages mean less scrolling and faster scanning
Product applications:
| Context | Application | Example | |---------|-------------|---------| | Landing pages | Cut welcome copy, lead with value | Remove "Welcome to..." paragraphs | | Error messages | State problem and fix, nothing more | "Password too short (min 8 chars)" | | Empty states | Action-oriented, minimal | "No results. Try a different search." |
Copy patterns:
- Before: "Please kindly note that you will need to enter your password in order to proceed to the next step." → After: "Enter your password to continue."
- Before: "We've received your message and will get back to you as soon as possible." → After: "Message sent. We'll reply within 24 hours."
Ethical boundary: Brevity must not omit critical information — concise disclosures for pricing, terms, and data usage are a user right.
4. The Trunk Test
Core concept: Drop a user on any random page (like being released from a car trunk at a random spot) — they should instantly answer six orientation questions: What site is this? What page? What are the major sections? What are my options here? Where am I in the hierarchy? Where's search?
Why it works: Good navigation gives constant orientation. Users who can't tell where they are feel lost and leave.
Apply it as the navigation check: page titles must match the link the user clicked, a "you are here" indicator (highlighted nav item, bold breadcrumb) must be present, and section headings must orient ("Your Account > Billing" not just "Settings").
Ethical boundary: Navigation labels must honestly represent site structure — never use misleading labels to funnel users into marketing pages.
See: references/krug-principles.md when running the Trunk Test or designing navigation — it maps each of the six questions to the page element that answers it, plus breadcrumb and permanent-navigation rules.
Nielsen's 10 Usability Heuristics
1. Visibility of System Status
Keep users informed through timely feedback. Every action needs acknowledgment — progress bars for uploads, confirmations for submissions, skeleton screens for loading. Silent failures destroy trust. Copy pattern: "Saving..." → "Saved".
2. Match Between System and Real World
Speak users' language: "Sign in" not "Authenticate", "Search" not "Query." Follow real-world metaphors (trash bin, shopping cart) and natural ordering (street → city → state → zip).
3. User Control and Freedom
Provide clear "emergency exits." Undo beats "Are you sure?" dialogs — users click through confirmations without reading. Every flow needs cancel/exit, and back buttons must never break.
4. Consistency and Standards
Same words, styles, and behaviors mean the same thing throughout. Internal consistency (your app) plus external consistency (platform conventions: logo top-left, search top-right). One term per concept — "Projects" everywhere, never mixed with "Workspaces."
5. Error Prevention
Prevent problems before they occur: constrained inputs (date pickers over text fields), autocomplete, sensible defaults, "unsaved changes" warnings. Slips (accidental wrong action) and mistakes (wrong intention) need different prevention.
6. Recognition Rather Than Recall
Minimize memory load — show options, don't require memorization. Breadcrumbs, recent searches, pre-filled fields, dropdowns with decoded values. Working memory holds ~7 items; recognition is far easier than recall.
7. Flexibility and Efficiency of Use
Serve both novices and experts: keyboard shortcuts, bulk actions, saved searches, command palettes (Cmd+K). Progressive disclosure keeps it simple for beginners while experts access full power.
8. Aesthetic and Minimalist Design
Every element must earn its place — when everything screams for attention, nothing stands out. Show what matters now, hide what doesn't. One primary CTA per page.
9. Help Users Recognize, Diagnose, and Recover from Errors
Error messages need three parts: what happened, why, and how to fix it. Plain language ("Connection failed" not "ECONNREFUSED"), specific ("Password must be 8+ characters" not "Invalid"), never blame the user, preserve their input.
10. Help and Documentation
Help should be searchable, task-focused ("How to..." not technical reference), and contextual (tooltips, inline hints, guided tours).
See: references/nielsen-heuristics.md when auditing against a specific heuristic — it expands each of the 10 into good-implementation / common-violation / severity tables with copy patterns and ethical boundaries.
Severity Rating Scale
Rate each issue found in an audit:
| Severity | Rating | Description | Priority | |----------|--------|-------------|----------| | 0 | Not a problem | Disagreement, not usability issue | Ignore | | 1 | Cosmetic | Minor annoyance, low impact | Fix if time | | 2 | Minor | Causes delay or frustration | Schedule fix | | 3 | Major | Significant task failure | Fix soon | | 4 | Catastrophic | Prevents task completion | Fix immediately |
Weigh three factors: frequency (how often it occurs), impact (how severe when it occurs), persistence (one-time or ongoing).
See: references/audit-template.md when running a full heuristic evaluation — a structured per-screen template that captures issues, severity, and recommended fixes in a consistent format.
Common Mistakes
| Mistake | Why It Fails | Fix | |---------|-------------|------| | Mystery meat navigation | Icons without labels force guessing | Add text labels alongside icons | | Too many choices | Decision paralysis slows users | Reduce to 7 plus/minus 2 items | | No "you are here" indicator | Users feel lost in the hierarchy | Highlight current section in nav and breadcrumbs | | No inline validation | Submit, error, scroll cycle frustrates | Validate on blur with specific messages | | Unclear required fields | Users confused about what's mandatory | Mark optional fields, not required | | Wall of text | Nobody reads dense paragraphs | Break up with headings, bullets, whitespace | | Jargon in labels | Users don't speak your internal language | User-test all labels, use plain language | | No loading indicators | Users think the system is broken | Show spinner, progress bar, or skeleton screen | | Tiny tap targets | Mobile users misclick constantly | Minimum 44x44 px touch targets | | Hover-only information | Mobile and keyboard users miss it | Don't hide critical info behind hover | | No undo | Users afraid to take any action | Provide undo for all non-destruc
Truncated for display — read the full file on GitHub.
Related Skills
taste-skill
116.8kAgent skills that give coding agents taste: art direction, reference images and a browser check instead of generic AI pages
ai-job-search
72.1kThe job search that runs on your machine. AI job application framework built on Claude Code: evaluate postings, tailor CVs, write cover letters, prep interviews. Fork it and own it.
claude-howto
47.3kA visual, example-driven guide to Claude Code — from basic concepts to advanced agents, with copy-paste templates that bring immediate value.
Claude-Code-Game-Studios
39.7kTurn Claude Code into a full game dev studio — 49 AI agents, 72 workflow skills, and a complete coordination system mirroring real studio hierarchy.
Languages
Trust signals
From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.
