design-review
This skill contains shell command directives (!`command`) that may execute system commands. Review carefully before installing.
Design Review
World-class design review following standards of top Silicon Valley companies (Stripe, Airbnb, Linear).
Parse Arguments
Output Path Configuration:
- If
$ARGUMENTSis provided and non-empty: Use$ARGUMENTSas the output directory - Otherwise: Use default
./reviews/design/
Git Analysis
GIT STATUS:
!`git status`
FILES MODIFIED:
!`git diff --name-only origin/HEAD...`
COMMITS:
!`git log --no-decorate origin/HEAD...`
DIFF CONTENT:
!`git diff --merge-base origin/HEAD`
Review the complete diff above to understand the scope of UI/UX changes.
Core Methodology
"Live Environment First" — Always assess the interactive experience before diving into static analysis or code. Prioritize the actual user experience over theoretical perfection.
Prerequisites
- A live preview environment (local dev server or staging URL)
- Playwright CLI for automated browser testing (refer to the
playwright:playwright-cliskill for full command reference)
Review Phases
Execute each phase systematically. See WORKFLOW.md for detailed checklists.
| Phase | Focus | Key Actions |
|---|---|---|
| 0 | Preparation | Analyze PR/description, review code diff, set up preview, configure viewport (1440x900) |
| 1 | Interaction | Execute user flows, test interactive states (hover/active/disabled), verify confirmations |
| 2 | Responsiveness | 7 viewport tiers (375–1920px), between-breakpoint sweeps, zoom reflow (400%), container queries |
| 3 | Visual Polish | Layout alignment, typography hierarchy, color consistency, image quality |
| 4 | Accessibility | Automated axe-core scan + manual keyboard sequence (Tab order, focus traps, Enter/Space) |
| 5 | Robustness | Form validation, content overflow, loading/empty/error states, edge cases |
| 6 | Code Health | Component reuse, design tokens (no magic numbers), pattern adherence |
| 7 | Content & Console | Grammar, text clarity, browser console errors/warnings |
Confidence & Signal Quality
Before reporting any finding, score confidence 1-10:
| Confidence | Action | Requirement |
|---|---|---|
| 9-10 | Report | Measurable failure with concrete evidence (screenshot, axe output, contrast ratio) |
| 7-8 | Report | Design system violation with specific token/rule reference |
| 5-6 | Suppress | Plausible but speculative — no system rule to cite |
| Below 5 | Discard | Aesthetic preference or subjective opinion |
Finding caps: Max 8 meaningful findings (Blocker + High-Priority + Medium-Priority) and max 2 Nits per review. If more exist, keep the highest-confidence items and note "additional observations available on request."
Self-reflection: After generating all candidate findings, re-evaluate each in context of the full set. Remove redundant, low-signal, or opinion-only items. Apply false positive filtering from WORKFLOW.md.
Triage Matrix
Categorize every finding using confidence thresholds:
- [Blocker]: Measurable failure requiring immediate fix — broken layout, keyboard trap, contrast <4.5:1, element inaccessible, content overflow (confidence >=8)
- [High-Priority]: Documented system violation — wrong design token, WCAG AA violation, responsive breakage (confidence >=7)
- [Medium-Priority]: Inconsistency with evidence — spacing/alignment with comparison screenshot (confidence >=6)
- [Nit]: Minor aesthetic detail, optional — max 2 per review
- [Praise]: Acknowledge a good design decision — max 1 per review
Communication Principles
- Problems Over Prescriptions: Describe problems and their impact, not technical solutions. Example: Instead of "Change margin to 16px", say "The spacing feels inconsistent with adjacent elements."
- Evidence-Based: Provide screenshots for visual issues. Reference specific design tokens or WCAG criteria.
- Start Positive: Begin with acknowledgment of what works well.
Output Instructions
- Create output directory using Bash:
mkdir -p {output-directory} - Save the report to:
{output-directory}/{YYYY-MM-DD}_{HH-MM-SS}_design-review.md
Include this header:
# Design Review Report
**Date**: {ISO 8601 date}
**Branch**: {current branch name}
**Commit**: {short commit hash}
**Reviewer**: Claude Code (design-review)
---
- Display the full report to the user in the chat
- Confirm the save: Report saved to: {output-directory}/{filename}
Resources
- WORKFLOW.md - Detailed phase-by-phase checklists, false positive filtering, confidence scoring guide, and report template
- EXAMPLES.md - Sample design review reports
- TROUBLESHOOTING.md - Common issues with environment, viewports, accessibility, and output
More from joaquimscosta/arkhe-claude-plugins
generating-stitch-screens
>
19deep-research
>
18listing-stale-branches
Lists local and remote git branches that are candidates for cleanup — merged but not deleted, and inactive branches with no commits in a configurable period (default 3 months). Use when user mentions "stale branches", "old branches", "branch cleanup", "prune branches", "dead branches", "unused branches", "inactive branches", "branch hygiene", or asks to "list branches to delete", "find stale branches", or runs /stale-branches command.
17sops-decrypt
>-
1releasing
Automate semantic versioning releases with CHANGELOG validation, comparison link management, GitHub Actions workflow triggering, and monitoring. Scaffold release infrastructure for new projects. Use when user runs /release command, mentions "release version", "cut a release", "create release", "publish release", "tag release", "release setup", or "scaffold release pipeline".
1taskfile-setup
>-
1