
Heuristic Evaluation
Run Nielsen-based heuristic walks on screens and flows, log severities, and prioritize fixes before user testing.
Overview
Heuristic Evaluation is an agent skill most often used in Ship (also Build frontend polish) that audits interfaces against Nielsen’s 10 heuristics with a 0–4 severity scale and prioritized recommendations.
Install
npx skills add https://github.com/owl-listener/designer-skills --skill heuristic-evaluationWhat is this skill?
- Full Nielsen 10 usability heuristics as evaluation lens
- Seven-step process from scope definition through prioritized findings
- Severity scale 0–4 per documented issue template
- Three walkthrough modes: new user, experienced user, and per task flow
- Per-issue record: heuristic violated, location, screenshot reference, recommendation
- Severity scale 0–4 per issue
- Seven-step evaluation process in SKILL.md
Adoption & trust: 580 installs on skills.sh; 1.5k GitHub stars; 3/3 security scanners passed (skills.sh audits).
What problem does it solve?
You are about to ship or test UI but lack a consistent expert pass that catches usability breaks early.
Who is it for?
Indie builders with working screens who want a cheap pre-test usability gate.
Skip if: Replacing moderated user research when you need behavioral evidence from real customers.
When should I use this skill?
Interfaces are ready for expert review and you want heuristic violations documented with severity before user testing.
What do I get? / Deliverables
You produce a scoped, severity-rated issue list tied to specific heuristics so fixes can be scheduled before user testing or launch.
- Prioritized usability issue list with heuristic mapping
- Per-issue severity (0–4) and recommendations
- Compiled findings across novice, expert, and task-flow passes
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Ship/review is the canonical shelf for expert usability passes on built UI prior to release or formal QA. Review subphase covers structured quality gates that do not require live users yet.
Where it fits
Audit checkout and settings flows while iterating components to catch consistency breaks early.
Run new-user and task-flow walks to produce a prioritized fix list before release candidate.
Feed severity 3–4 findings into manual test scripts before automated regression.
How it compares
Expert heuristic audit checklist, not a design critique facilitation session for live team feedback.
Common Questions / FAQ
Who is heuristic-evaluation for?
Solo founders and small teams doing UX on their own product who need Nielsen-style rigor without hiring a full usability lab.
When should I use heuristic-evaluation?
During build while hardening frontend flows, and during ship review before QA sign-off or first user tests.
Is heuristic-evaluation safe to install?
It is documentation-driven review guidance; review the Security Audits panel on this page for the package before enabling it in your agent.
SKILL.md
READMESKILL.md - Heuristic Evaluation
# 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