PluginBench
Skill
Pass
Audit score 90

heuristic-evaluation

owl-listener/designer-skills

Systematic expert review of interfaces against Nielsen's 10 usability heuristics with severity ratings.

What is heuristic-evaluation?

Conduct a structured heuristic evaluation of digital interfaces to identify usability problems without recruiting participants. Use this when you need expert findings quickly, or pair it with user testing for a complete picture.

  • Evaluate interfaces against Nielsen's 10 established usability heuristics
  • Walk through interfaces as both new and experienced users to surface different issues
  • Document each issue with location, heuristic violated, severity rating (0–4), and recommendations
  • Rate severity from cosmetic (1) to catastrophic/must-fix (4)
  • Compile and prioritize findings for actionable next steps
  • Support multiple independent evaluators to find more issues

How to install heuristic-evaluation

npx skills add https://github.com/owl-listener/designer-skills --skill heuristic-evaluation
Claude Code
Cursor
Windsurf
Cline

How to use heuristic-evaluation

  1. 1.Define the scope: identify which screens, flows, or features to evaluate
  2. 2.Walk through the interface as a new user unfamiliar with the product
  3. 3.Walk through again as an experienced user to identify efficiency issues
  4. 4.Execute each key task flow and note where friction occurs
  5. 5.For each issue found, document: which heuristic it violates, description, exact location, severity (0–4), and a recommendation
  6. 6.Compile all findings and sort by severity to prioritize fixes
  7. 7.If evaluating as a team, have each person evaluate independently first, then compare results to find issues others missed

Use cases

Good for
  • Quick expert review of a new feature before user testing to catch obvious problems early
  • Systematic audit of an existing product against usability standards
  • Evaluation of competitor interfaces to identify best practices and gaps
  • Assessment of accessibility and clarity in task flows before launch
  • Team-based heuristic evaluation where 3–5 evaluators review independently then compare findings
Who it's for
  • UX/product designers conducting interface reviews
  • Product managers prioritizing fixes before user research
  • Design teams seeking structured feedback without participant recruitment
  • Accessibility and usability specialists auditing digital products

heuristic-evaluation FAQ

How many evaluators should I use?

3–5 independent evaluators is ideal. Multiple evaluators find significantly more issues than one person alone; evaluate independently before comparing results.

What's the difference between severity levels?

0 = not a problem; 1 = cosmetic only; 2 = minor problem; 3 = major problem (important to fix); 4 = catastrophe (must fix before release).

Should I focus on edge cases or real user tasks?

Focus on real user tasks and common workflows, not edge cases. The goal is to find problems that actual users will encounter.

Can heuristic evaluation replace user testing?

No. Heuristic evaluation finds expert-identified issues quickly, but combine it with real user testing for a complete picture of how actual users interact with your product.

What if I find many issues?

Prioritize by severity (fix all 4s and 3s first) and by heuristic category. For each issue, always suggest a concrete recommendation, not just the problem.

Full instructions (SKILL.md)

Source of truth, from owl-listener/designer-skills.


name: heuristic-evaluation description: Run an expert review against Nielsen's heuristics and domain criteria, with severity ratings. Use when you need findings without recruiting participants. For a facilitated team feedback session, use design-critique (design-ops).

Heuristic Evaluation

You are an expert in conducting systematic heuristic evaluations of digital interfaces.

What You Do

You evaluate interfaces against established usability heuristics to identify problems before user testing.

Nielsen's 10 Usability Heuristics

  1. Visibility of system status — Users know what is happening
  2. Match real world — System speaks users' language
  3. User control and freedom — Easy undo and exit
  4. Consistency and standards — Follow conventions
  5. Error prevention — Prevent problems before they occur
  6. Recognition over recall — Make options visible
  7. Flexibility and efficiency — Shortcuts for experts
  8. Aesthetic and minimalist design — No irrelevant information
  9. Error recovery — Help users recognize and recover from errors
  10. Help and documentation — Provide assistance when needed

Evaluation Process

  1. Define scope (which screens/flows to evaluate)
  2. Walk through as a new user
  3. Walk through as an experienced user
  4. Walk through each task flow
  5. Document each issue found
  6. Rate severity
  7. Compile and prioritize findings

Issue Documentation

For each issue: heuristic violated, description, location, severity (0-4), screenshot/reference, recommendation.

Severity Scale

  • 0: Not a usability problem
  • 1: Cosmetic only
  • 2: Minor problem
  • 3: Major problem (important to fix)
  • 4: Catastrophe (must fix before release)

Best Practices

  • Multiple evaluators find more issues (3-5 ideal)
  • Evaluate independently before comparing
  • Focus on real user tasks, not edge cases
  • Don't just find problems — suggest solutions
  • Combine with real user testing for complete picture