Stats
Actions
Tags
From rz-ux-researcher
Heuristic evaluation of a specific UI surface or flow. Use when the ticket asks to audit an existing screen, page, or interaction against usability heuristics. Produces a structured critique with severity-ranked findings.
How this skill is triggered — by the user, by Claude, or both
Slash command
/rz-ux-researcher:usability-auditThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Invoke when the ticket:
Invoke when the ticket:
For journey-level analysis, use journey-map. For synthesis across many users, use interview-synthesis.
# Usability audit — {surface name}
**Target app:** {app_id}
**Date:** {YYYY-MM-DD}
**Triggering ticket:** [CAR-{n}]({URL})
**Confidence:** {low/medium/high}
**Evaluator:** User Researcher routine
**Method:** Nielsen's 10 heuristics + cognitive walkthrough
## Surface evaluated
Describe exactly what was audited. Link screenshots if possible. Note the date / version.
## Cognitive walkthrough
Pick the most important task on this surface. Walk through as a new user would.
- **Task:** {specific user goal}
- **Starting state:** {what the user is looking at}
### Step 1: {action}
- What the user sees
- What they probably think
- What they actually need to do
- Friction?
### Step 2: {action}
…
### Step 3: {action}
…
## Findings
Each finding maps to one or more of Nielsen's heuristics. Severity: Catastrophic, Major, Minor, Cosmetic.
### Finding 1 — {short label}
**Heuristic violated:** {#N — Name}
**Severity:** {Catastrophic / Major / Minor / Cosmetic}
**Location:** {specific UI element / screen region}
**Description:** What's wrong in user terms.
**Evidence:** Why this is a problem (cognitive load, error-proneness, violated convention, etc.)
**Suggested direction:** {not a prescribed solution — a direction for Designer to explore}
### Finding 2 — …
…
## Nielsen's heuristics reference
For the reader who needs the list:
1. Visibility of system status
2. Match between system and real world
3. User control and freedom
4. Consistency and standards
5. Error prevention
6. Recognition rather than recall
7. Flexibility and efficiency of use
8. Aesthetic and minimalist design
9. Help users recognize, diagnose, and recover from errors
10. Help and documentation
## Strengths
What this surface does well. 2–3 bullets. Audits that only critique are miscalibrated.
## Recommendations ranked by impact
1. **{Finding X}** — highest impact; fix first. Reason.
2. **{Finding Y}** — second priority. Reason.
3. **{Finding Z}** — …
## Hand-off
For Designer: Findings marked Major or Catastrophic should trigger design iteration. File `type:engineering` ticket with prototype scope if approved by Riché.
For PM-lite: If the audit reveals a bigger problem (e.g., the whole surface's purpose is unclear), flag a strategic ticket rather than iterating on current surface.
## Confidence: {low/medium/high}
Rationale: {e.g., "medium — expert heuristic eval only; no user testing to validate severity rankings"}
## Sources
- Nielsen Norman Group, 10 Usability Heuristics for User Interface Design
- Surface screenshots (linked)
- Related user research that informs this audit
npx claudepluginhub rczamor/rz-agent-team --plugin rz-ux-researcherCreates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.