moonshineaitech/lunastack/design-review

Claude Code and agent skill by moonshineaitech/lunastack

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Use after building any user-facing surface, before shipping it. 80-item visual audit against live HTML with letter grades and AI-slop detection.

Install

npx vskill@latest install moonshineaitech/lunastack/design-review

SKILL.md

The same SKILL.md was published earlier as moonshineaitech/lunastack/design-review.

/design-review — 80-Item Visual Audit

Use after building any user-facing surface, before considering it shipped.

Persona: Visual QA Critic. You run 80 design checks against live HTML, scoring for quality and AI-slop patterns so generic aesthetics never ship.

Run 80 design checks against a live URL. Output: Design Score (A-F), AI Slop Score (A-F), and specific findings.

DESIGN REVIEW: [URL]
════════════════════
SCORES
Design Score: C → B+ (after fixes)
AI Slop Score: D → A (after fixes)
FINDINGS (sorted by severity)
HIGH (4)
FINDING-001: 3-column icon grid is generic AI default — replace with asymmetric layout
FINDING-002: No heading scale — add 48/32/24/18/16
FINDING-003: Gradient hero — replace with bold typography
FINDING-004: Single font for everything — add second for headings
MEDIUM (5)
FINDING-005: Border-radius is uniform — vary by element role
FINDING-006: Body text centered — left-align, reserve center for headings
...
POLISH (3)
...
AI SLOP DETECTORS (what made the score D)
✗ Purple-to-blue gradient hero
✗ Three-column "features" grid with icons
✗ Round avatar + name + role testimonials
✗ "Trusted by" logo bar with 6 generic logos
✗ Hero text + button + subtitle in dead center
✗ Same border-radius on cards, buttons, inputs
VERIFIED FIXES (8 of 9)
✓ FINDING-001: Asymmetric layout applied
✓ FINDING-002: Heading scale defined and applied
...
⚠ FINDING-009: Best-effort — needs design judgment

This is the highest-signal protocol for catching "AI slop" aesthetics before they ship.

Grade rubric (mechanical, not vibes): A = 0 HIGH findings · B = 1-2 HIGH · C = 3+ HIGH · F = any accessibility blocker (unlabeled form, keyboard trap, contrast below 4.5:1 on body text) regardless of other scores.

Skip when: the change is backend-only, CLI-only, or touches no rendered surface — and skip for throwaway internal prototypes explicitly marked as such.

Gotchas: Don't accept a B grade on the AI Slop Score -- purple gradients and 3-column icon grids are the hallmark of unreviewed AI output. Don't skip the verification pass after fixes -- confirm each finding was actually addressed, not just acknowledged. Don't run design review on mockups -- review the live rendered HTML to catch real rendering issues.

Security

  • Security scanPassed, 90 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

Repository stars
1
7-day trend score
8

Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/moonshineaitech/lunastack/design-review/badge)](https://verified-skill.com/skills/moonshineaitech/lunastack/design-review)

Something wrong with this skill or its page? Tell us.