Skip to content
Automation
Skill

/ui-review

Review UI code for StyleSeed design-system compliance, accessibility, mobile ergonomics, spacing discipline, and implementation quality.

From plugin
lihongwei-cn
5200 skills1 agent
Install
$ npx -y skills add LiHongwei-cn/lihongwei-cn --skill ui-review --agent claude-code

How it fires

How this skill gets triggered: by you, by Claude, or both.

  • Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
  • You can call itInvoke it directly when you want it.
  • Slash command/ui-review

Context preview

The summary Claude sees to decide when to auto-load this skill.

Review UI code for StyleSeed design-system compliance, accessibility, mobile ergonomics, spacing discipline, and implementation quality.

SKILL.md

ui-review.SKILL.md
name: ui-review
description: "Review UI code for StyleSeed design-system compliance, accessibility, mobile ergonomics, spacing discipline, and implementation quality."
category: design
risk: safe
source: community
source_repo: bitjaru/styleseed
source_type: community
date_added: "2026-04-08"
author: bitjaru
tags: [ui, review, design-system, accessibility, styleseed]
tools: [claude, cursor, codex, gemini]

UI Review

Overview

Part of [StyleSeed](https://github.com/bitjaru/styleseed), this skill audits UI code against the Toss seed's conventions instead of reviewing it as generic frontend work. It focuses on design-token discipline, component ergonomics, accessibility, mobile readiness, typography, and spacing consistency.

When to Use

  • Use when a component or page should follow the StyleSeed Toss design language
  • Use when reviewing a UI-heavy PR for consistency and design-system violations
  • Use when the output looks "mostly fine" but feels off in subtle ways
  • Use when you need a structured review with concrete fixes

Review Checklist

Design Tokens

  • no hardcoded hex colors when semantic tokens exist
  • no improvised shadow values when tokenized shadows exist
  • no arbitrary radius choices outside the system scale
  • no random spacing values that break the seed rhythm

Component Conventions

  • uses the project's class merge helper
  • supports `className` extension when appropriate
  • uses the agreed typing pattern
  • avoids wrapper components that only forward one class string
  • reuses existing primitives before inventing new ones

Accessibility

  • touch targets large enough for mobile
  • visible keyboard focus states
  • labels and `aria-*` attributes where needed
  • adequate color contrast
  • reduced-motion respect for animation

Mobile UX

  • no horizontal overflow
  • safe-area handling where relevant
  • readable text sizes
  • thumb-friendly interaction spacing
  • bottom nav or sticky actions do not obscure content

Typography and Spacing

  • uses the system type hierarchy
  • display and headings are not overly loose
  • body text remains readable
  • spacing follows the seed grid instead of arbitrary values

Output Format

Return: 1. A verdict: Pass, Needs Improvement, or Fail 2. A prioritized list of issues with file and line references when available 3. Concrete fixes for each issue 4. Any open questions where the design intent is ambiguous

Best Practices

  • Review against the seed, not against personal taste
  • Separate stylistic drift from real usability or accessibility bugs
  • Prefer actionable diffs over abstract criticism
  • Call out duplication when an existing component already solves the problem

Additional Resources

  • [StyleSeed repository](https://github.com/bitjaru/styleseed)
  • [Source skill](https://github.com/bitjaru/styleseed/blob/main/seeds/toss/.claude/skills/ui-review/SKILL.md)

Limitations

  • Use this skill only when the task clearly matches the scope described above.
  • Do not treat the output as a substitute for environment-specific validation, testing, or expert review.
  • Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.
Read more
Ships withlihongwei-cn

MUNDO - THE EMPEROR. Complete AI orchestration system with 1208 skills, 25 capability modules, self-evolving, collective consciousness. GitHub Actions 24/7 automation.

Get the whole plugin
Stats
5
Stars
1
Forks
Maintained
Maintenance
Python
Language
MIT
License
1mo ago
Last commit
4mo ago
Created

Repo: LiHongwei-cn/lihongwei-cn

Other skills on lihongwei-cn.

cheat-on-content
Skill

cheat-on-content

给所有想把"感觉"变成可校准预测的内容创作者。**方法论通用**——打分 → 盲预测 → T+3d 复盘 → 进化 rubric 的循环适用任何能被量化(播放 / 阅读 / 收听 / 点击)的内容。**rubric 是循环的内容,不是循环本身**——当前内置一份观点视频 rubric(参考博主 25+…

cheat-bump
Skill

cheat-bump

提议并执行 rubric 或 bucket 升级。两种模式:**完整 rubric bump**(最高风险动作,5 步强制 + 跨模型审核)和 **--bucket-only 轻量重校**(只换 bucket 边界,不动 rubric 公式)。**Phase 2 强制走 cheat-score-blind…

cheat-init
Skill

cheat-init

cheat-on-content 的首次 onboarding 与脚手架创建器。统一流程——所有用户都走相同 5 阶段闭环,唯一区别是"发过视频的人"会在 init 时多一步:抓取已有视频建立历史 context(用于后续 cheat-seed 给更贴合的选题、更准的…

cheat-migrate
Skill

cheat-migrate

把老用户的 .cheat-state.json 升级到当前 schema_version。读 migrations/registry.md 算迁移链,按顺序应用每一步迁移文件。幂等:跑两次结果一样。失败停在中间版本不前进。触发词:"迁移"/"升级 state"/"migrate"/"我的 state…

cheat-persona
Skill

cheat-persona

从复盘评论数据派生 / 刷新账号的受众画像,写入 audience.md。这是和 rubric 平行的第二个派生物——rubric 答"怎么打分",persona 答"谁在看"。cheat-seed 选题 / 写稿时读它。**audience.md 含实绩信号,cheat-score-blind…