Skip to main content
skill CX Codex

heuristic-evaluation — Claude Code skill: review and install

This skill reviews interfaces against Nielsen’s heuristics and domain criteria, then rates finding severity. Use it before user testing when you need an expert audit.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add Owl-Listener/designer-skills --skill heuristic-evaluation -a claude-code
Open on GitHub

What heuristic-evaluation does

The skill runs a structured expert review of a digital interface. It helps define the scope, inspect screens and task flows as a new and experienced user, record each issue, and compile a prioritized set of findings.

Each finding includes the violated heuristic, its location, a recommendation, and a severity rating from 0 to 4. The review covers Nielsen’s 10 usability heuristics, including system status, real-world language, user control, error prevention, recovery, and help.

This is a fit for review without recruiting participants. It does not replace a facilitated team feedback session; the description points to design-critique for that use case. The guidance also recommends independent evaluation before comparing results and keeping attention on real user tasks rather than edge cases.

What it helps with

  • review an interface before user testing
  • identify Nielsen heuristic violations across screens and flows
  • rate usability findings from 0 to 4
  • add recommendations to documented issues
  • compare reviews from independent evaluators

Example prompts for the agent

  • Run a heuristic evaluation of the login screens and rate every finding from 0 to 4.
  • Review this checkout flow against Nielsen’s heuristics, note each issue’s location, and suggest a fix.
  • Compare the independent interface reviews and prioritize the findings.

How to install heuristic-evaluation

1Skills CLI (Vercel)

npx skills add Owl-Listener/designer-skills --skill heuristic-evaluation -a claude-code

2Manually: put the files in place

~/.claude/skills/heuristic-evaluation/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/heuristic-evaluation/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about heuristic-evaluation

How do I install heuristic-evaluation in Claude Code?

Run npx skills add Owl-Listener/designer-skills --skill heuristic-evaluation -a claude-code, then run the same command again: npx skills add Owl-Listener/designer-skills --skill heuristic-evaluation -a claude-code. After that, check ~/.claude/skills/heuristic-evaluation/SKILL.md.

What does heuristic-evaluation do?

It performs an expert interface review using Nielsen’s heuristics and domain criteria. The skill documents issues, suggests fixes, and assigns each finding a severity rating from 0 to 4.

How is heuristic-evaluation different from design-critique?

heuristic-evaluation is for an expert review without recruiting participants. The description points to design-critique for a facilitated team feedback session.

Source text

SKILL.md · MIT
---
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

© Owl-Listener · MIT · Owl-Listener/designer-skills

Similar skills

Everything for Design →

From the same set111

user-flow-diagram Draws screen-level flow diagrams with entry points, decision branches and error paths. Useful when a feature needs step-by-step specs. CX Codex +1 2,400installs dark-mode-design This skill turns an existing light palette into a dark theme: surface elevation, contrast, desaturated accents. Use it when the light tokens already exist. CX Codex +1 2,400installs responsive-design A skill that steers your coding agent toward layouts and interactions that hold up across screen sizes and input methods. CX Codex +1 2,300installs spacing-system Builds a systematic spacing scale from a 4px or 8px base unit with rules for padding and margins. Useful when cleaning up inconsistent layout values. CX Codex +1 2,300installs usability-test-plan Builds a usability test plan: research questions, methodology, participant criteria, metrics and a facilitation script. Useful when the study is still being planned. CX Codex +1 2,200installs case-study Structures design portfolio case studies around process evidence, personal contribution, and business metrics. Built for presenting projects to external audiences. CX Codex +1 2,200installs design-token Defines and organises colour, spacing, type and elevation tokens with naming and usage rules. Useful when you are laying down the token layer. CX Codex +1 2,200installs error-handling-ux A skill that guides the agent through preventing, surfacing and recovering from errors in a product. Useful when failures cross several flows at once. CX Codex +1 2,200installs

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor