About design-review
A skill for structured reviews of screens and flows. It scores six weighted dimensions, applies accessibility checks and Nielsen’s heuristics, and produces prioritized findings with concrete fixes.
Key features
- 01Score six dimensions with weighted criteria
- 02Check accessibility and color contrast
- 03Apply Nielsen’s ten usability heuristics
- 04Prioritize findings by severity
- 05Recommend fixes tied to design tokens
Use cases
- 01Review an individual screen or user flow
- 02Assess accessibility and usability of a design
- 03Create a prioritized remediation list for UI issues
Install
Copy the command and run it in a terminal.
$
npx skills add https:/ / github.com/ plugin87/ ux-ui-agent-skills --skill design-reviewAfter installing, type/design-reviewin Claude Code to confirm it loaded.
Details
From the project READMESkill: Design Review
Step 0: is the kit here? This skill reads files from the kit. Check once:
ls ${CLAUDE_SKILL_DIR}/../../../tokens >/dev/null 2>&1 && echo KIT_OK || echo KIT_MISSINGOnKIT_MISSINGonly the skill folders were installed, which is whatnpx skills adddoes. Say so plainly, point the user atnpx ux-ui-agent-skills initor the plugin install, and stop. Do not guess the contents of a file you could not open.
Run a structured, scored review.
Steps
- Read
${CLAUDE_SKILL_DIR}/../../../workflows/design-review.md(rubric, scoring guide, Nielsen heuristics, process). - Gather context: the screen(s)/flow, target users, platform, constraints.
- Score the 6 dimensions (Visual Hierarchy 20%, Consistency 20%, Accessibility 20%, Usability 20%, Responsiveness 10%, Performance 10%); compute the weighted overall.
- Run the accessibility lens with
${CLAUDE_SKILL_DIR}/../../../accessibility/wcag-checklist.md; use${CLAUDE_SKILL_DIR}/../../../scripts/contrast.pyfor any color-pair doubts. - Check against the anti-slop tells in
${CLAUDE_SKILL_DIR}/../../../taste/design-taste.md(Banned Defaults checklist). - Apply Nielsen's 10 heuristics; flag violations by number.
Output
- The 6-dimension scored table + overall score.
- A prioritized findings table: # · Severity (Critical → Major → Minor → Enhancement) · Finding · Recommendation.
- Concrete, token-referenced fixes.
Comments
Markdown supported