ui-design-to-code-qa

ui-design-to-code-qa is a skill for Claude Code from volomydyr/design-engineer-plugin. It costs 51 tokens per session (1,877 once invoked), scanned A, original, MIT.

A review guide for comparing a built user interface with its intended design and finding common implementation mistakes. It covers issues such as incorrect text casing, spacing, hardcoded styles, and unnecessary duplicate components.

In plain words
What is it for?
Use it after implementation or when someone reports that an interface looks wrong. It is for checking design fidelity and reuse, rather than judging overall visual taste.
Why use it?
It catches visual differences and repeated patterns that can accumulate when interfaces are produced quickly, especially by coding agents.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: model in frontmatter; names the AskUserQuestion tool.

Part of the design-engineer plugin — 57 skills, 11 commands, 10 agents, 6 hooks shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/volomydyr/design-engineer-plugin/ui-design-to-code-qa
Any agent
npx skills add volomydyr/design-engineer-plugin --skill ui-design-to-code-qa
Clone the repo
git clone --depth 1 https://github.com/volomydyr/design-engineer-plugin

Made for: Claude Code.

Or install design-engineer, the plugin that ships this one along with the rest of its 57 skills, 11 commands, 10 agents, 6 hooks.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for ui-design-to-code-qa

README.md
[![agentmods](https://agentmods.dev/badge/skills/volomydyr/design-engineer-plugin/ui-design-to-code-qa.svg)](https://agentmods.dev/skills/volomydyr/design-engineer-plugin/ui-design-to-code-qa)
Your own site
<a href="https://agentmods.dev/skills/volomydyr/design-engineer-plugin/ui-design-to-code-qa"><img src="https://agentmods.dev/badge/skills/volomydyr/design-engineer-plugin/ui-design-to-code-qa.svg" alt="Measured on agentmods" height="20"></a>
Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,877 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00051 $0.01877
Opus 5 $0.00026 $0.00938
Sonnet 5 $0.00010 $0.00375
Haiku 4.5 $0.00005 $0.00188

Measured 6d ago against content hash aaecab0fed05, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

ui-design-to-code-qa scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/ui-design-to-code-qa/SKILL.md · 179 lines

How it starts

The opening of the file, as written. The whole thing — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Visual Review

Why This Matters

AI-generated UI frequently contains specific, predictable issues: title case where sentence case was intended, incorrect spacing, hardcoded values instead of design tokens, creative interpretations of designs, and redundant components that duplicate existing ones. Catching these early prevents accumulated visual debt.

The most common violations are hardcoded values (AI writes specific color values instead of reusing established tokens) and redundant components (AI creates new components from scratch instead of reusing existing ones every time new designs are shared).

Beyond these technical issues, AI-generated UI has recognizable aesthetic fingerprints: the same fonts, the same color palettes, the same card layouts. These patterns are cataloged in the design critique references – consult them when the implementation looks "correct" but feels generic.

Interaction Method

If AskUserQuestion is available, use it for all prompts below.

If not, present each question as a numbered list and wait for a reply before proceeding. For multiSelect questions, accept comma-separated numbers (e.g. 1, 3). Never skip or auto-answer without explicit user consent.


Step 1: Determine Review Method

question: "How do you want to review the implementation?"
header: "Review Method"
options:
  - label: "Compare with Figma designs (via Figma plugin)"
    description: "Side-by-side comparison using Figma plugin data"
  - label: "Review screenshots"
    description: "Analyze provided screenshots of the implementation"
  - label: "Review live URL (via Playwright)"
    description: "Navigate to a URL and take automated screenshots"
  - label: "Review code only"
    description: "Audit the codebase for design system violations without visual comparison"
  - label: "Review HTML prototype"
    description: "Audit an HTML prototype file for UX and visual quality"

When "Review HTML prototype" is selected, read the HTML file at the path the user provides (default: .design-engineer-plugin/prototype/prototype.html). Run the UX non-negotiables check (Step 3) and an adapted visual audit that focuses on spacing, typography, hierarchy, and interactive states rather than design system token compliance (since prototypes use inline tokens, not a formal design system).

Read the full file on GitHub · 179 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 6d ago First seen · 179 lines · 51 tokens per session scan A aaecab0fed05

Subscribe to this mod's changes

ui-design-to-code-qa is a skill published in the GitHub repository volomydyr/design-engineer-plugin (19 stars, last pushed 2mo ago), licensed MIT. It adds 51 tokens to every session and 1,877 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens