MCPInstall

styleseed-design-review

Reviews UI/frontend code and tells you exactly why it "looks AI-generated" — then how to fix it. Use it when a React/Tailwind/HTML interface looks off, generic, or unfinished, when you want a design score before shipping, or when asked to make UI look more professional, polished, or "designed, not generated." Self-contained; based on the open-source StyleSeed design engine.

Installs
729
Last 24h
—
Trending rank
—
Security
Not audited

Install

Works with every agent the skills CLI supports.

npx skills add https://github.com/bitjaru/styleseed --skill styleseed-design-review
  1. 01

    Install

    Run the command in your project. The CLI asks which agents to install for.

  2. 02

    Describe the task

    Ask your agent for something this skill covers. It loads styleseed-design-review automatically when relevant.

  3. 03

    Review the result

    The agent follows the SKILL.md steps, scripts and references bundled with the skill.

SKILL.md

The instructions your agent reads when the skill is triggered.

StyleSeed Design Review

Overview

A UI reads as "AI-generated" not because the components are ugly, but because the parts don't agree with each other — mixed corner radii, three accent colors, pure-black text, no hierarchy, missing states, robotic copy. This skill reviews a UI file (or a whole directory) against a concrete design rubric, scores it 0–100, and returns a prioritized fix list. It reviews and recommends; it never edits or deletes without you asking.

Full rule set (74 rules) and components: https://github.com/bitjaru/styleseed

When to use

  • A React / Tailwind / HTML UI "looks off," generic, or unfinished and you can't say why.
  • You want a design score / pre-ship check.
  • The user asks to make UI "look professional / polished / designed, not AI-generated."
  • After generating UI, to verify it before shipping.

How to review

Read the file(s). Score these seven categories (total 100); start each at full marks and subtract for violations you can cite by line. Be specific and evidence-based.

1. Coherence — 20 (the #1 "AI-generated" tell)

One choice per axis, applied everywhere. Deduct for each mixed axis:

  • mixed corner radii — e.g. a sharp card with pill buttons (−6)
  • two or more accent colors used for emphasis (−5)
  • emoji used as UI icons (🚗🧺⭐ as list/nav/status/category markers) — injects many uncontrolled hues; use one line-icon set in currentColor (−6)
  • mixed shadow languages / light directions (−3)
  • mixed icon families, fill modes, or stroke weights (−3)
  • inconsistent control heights (buttons/inputs differ) (−3)

2. Color discipline — 16

  • pure black (#000 / text-black) text — the refined black is ~#2A2A2A (−4 each, cap −8)
  • hardcoded hex where a semantic token exists (−2 each, cap −6)
  • a normal / OK / default ("보통") state shown in a status color instead of neutral grey (−4)
  • status color on most/every row (no severity hierarchy — color should mark the minority that needs attention) (−4)
  • decorative hues — gold stars, rainbow category dots, a different color per card — instead of accent/grey (−3)
  • status conveyed by color alone, no icon/text (−4)
  • contrast below WCAG AA (4.5:1 body, 3:1 large/UI) (−6)

3. Hierarchy & typography — 16

  • number and its unit not ~2:1 (48px number / 24px unit) (−4)
  • everything the same size and weight, no clear primary (−5)
  • arbitrary font sizes; no scale (−4)
  • wrong line-height (loose on display, cramped on body) (−3)

4. Layout & spacing — 12

  • content on a bare page background, not in cards (−6)
  • off-grid spacing (7/13/19px instead of an 8px scale) (−3)
  • the gap around a group not larger than the gap inside it (−3)
  • the same section type repeated in a row (−4)

5. States — 12

  • missing empty / loading / error state on a data surface (−5 each, cap −10)
  • empty state with no next action; error that blames instead of helping (−4)

6. UX writing — 12

  • buttons that don't name the action ("Submit" / "OK" instead of "Send $2,400") (−4)
  • error copy that blames or uses system-speak ("Invalid input", "An error occurred") (−4)
  • two terms for one concept (delete vs remove); filler words ("please", "successfully") (−2)

7. Motion & polish — 12

  • ad-hoc fades instead of one consistent, named feel (−3)
  • motion that delays content or blocks an action (−4)
  • no prefers-reduced-motion handling on custom motion (−3)
  • a single hard black shadow instead of a layered, low-opacity, tinted one (−2)

Clamp each category at 0; sum to a total. Bands: 90+ A · 80–89 B · 70–79 C · 60–69 D · <60 F.

Output format

## Design Score: 72 / 100   (src/Dashboard.tsx)   C

Coherence            13/20   sharp cards (l.22) + pill buttons (l.48); 3 accent hues
Color discipline     12/16   #000 headings (l.12, 40)
Hierarchy & type     15/16   number/unit 1:1 on hero (l.18)
Layout & spacing     10/12   two identical KPI rows (l.22-31)
States                7/12   no empty/loading state on the orders list
UX writing            8/12   "Submit" button (l.55); "Invalid input" (l.61)
Motion & polish      10/12   one hard black shadow (l.22)

### Fix first (highest score gain)
1. Unify radius (pick soft 8–12px) + collapse to one accent   → +11 coherence/color
2. Add empty + loading states to the orders list              → +7  states
3. Rename "Submit" → "Send $2,400"; "Invalid input" → "Check the card number" → +6 copy

Re-score after: ~90 / 100.

Rules

  • Review from real evidence (cite line numbers); never guess.
  • Order the fix list by score gain, not severity alone — fastest path to a better number.
  • For a directory: one-line score per file, then the lowest file's full breakdown.
  • Don't auto-edit. This skill measures and recommends. Apply fixes only when asked.
  • Use it as a quality gate: review right after generating UI, apply the fix list, and re-review until the score clears ~80 before showing the user — no first-draft, incoherent UI (rainbow status lists, emoji icons, two accents, missing states) should reach them. The bar is a floor, not a ceiling: clear 80 and ship; don't chase 100 to delay.

Based on StyleSeed — an open-source (MIT) design engine that gives Claude Code, Cursor, and Codex design judgment so AI-built UI stops looking generated. Full 74-rule reference, components, brand skins, and motion: https://github.com/bitjaru/styleseed

FAQ

What does the styleseed-design-review skill do?

Reviews UI/frontend code and tells you exactly why it "looks AI-generated" — then how to fix it. Use it when a React/Tailwind/HTML interface looks off, generic, or unfinished, when you want a design score before shipping, or when asked to make UI look more professional, polished, or "designed, not generated." Self-contained; based on the open-source StyleSeed design engine.

How do I install styleseed-design-review?

Run npx skills add https://github.com/bitjaru/styleseed --skill styleseed-design-review in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/styleseed-design-review/ (personal) or .claude/skills/styleseed-design-review/ (project).

Which AI agents can use styleseed-design-review?

Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.

Is styleseed-design-review safe to install?

No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.

Who maintains styleseed-design-review?

It is published by bitjaru in bitjaru/styleseed. It has 729 recorded installs.

More from bitjaru/styleseed

View all →

ss-audit

bitjaru/styleseed

Audit screens for UX issues using Nielsen's heuristics and modern mobile UX best practices

Security864 installs

ss-review

bitjaru/styleseed

Review UI code for design system compliance, accessibility, and best practices

ss-setup

bitjaru/styleseed

Configure StyleSeed by selecting the output grammar, domain, page type, brand recipe, semantic palette recipe, optional aesthetic profile, and bounded brand tokens before scaffolding a first screen.

Marketing & SEO863 installs

ss-a11y

bitjaru/styleseed

Audit a component or page for accessibility issues and fix them

Frontend & Design862 installs

ss-lint

bitjaru/styleseed

Quick automated lint — detects common design system violations in seconds

ss-feedback

bitjaru/styleseed

Add appropriate user feedback states (loading, success, error, empty) to a component or page

Frontend & Design852 installs

Popular frontend & design skills

View category →

setup-matt-pocock-skills

mattpocock/skills

Configure this repo for the engineering skills: set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.

Frontend & Design1.1M installs

frontend-design

anthropics/skills

Guidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.

OfficialFrontend & Design1M installs

hyperframes-animation

heygen-com/hyperframes

All animation knowledge for HyperFrames — atomic motion rules, multi-phase scene blueprints, scene transitions, broader motion-design techniques, AND the seven runtime adapters (GSAP default, plus Lottie, Three.js, Anime.js, CSS keyframes, Web Animations API, TypeGPU). Use for any motion or animation task: pick 2-4 rules and compose, or load a blueprint, or look up runtime-specific API (e.g. GSAP eases / Lottie player / Three.js mixer). Also covers auditing an existing composition's choreography (animation map) and 24 named text-animation effects. HyperFrames-native: single paused timeline, seek-safe, deterministic.

prototype

mattpocock/skills

Build a throwaway prototype to answer a design question. Use when the user wants to sanity-check whether a state model or logic feels right, or explore what a UI should look like.

Frontend & Design999.2K installs

hyperframes-core

heygen-com/hyperframes

The HyperFrames composition contract — build one renderable project. Use for composition structure, the data- timing attributes, class="clip", tracks, sub-compositions, variables, framework-owned media playback, deterministic-render rules, and validation. Read before writing composition HTML.

Frontend & Design930.5K installs

vercel-react-best-practices

vercel-labs/agent-skills

React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.

OfficialFrontend & Design843.1K installs