design-parity-review

design-parity-review is a skill for Claude Code from yschimke/skills. It costs 133 tokens per session (2,584 once invoked), scanned A, original, Apache-2.0.

A review tool that compares a rendered Compose interface with its intended Figma, Stitch, or Claude Design reference. It checks visual differences, meaning-related differences, and design values such as spacing or colour.

In plain words
What is it for?
It is for reviewing interface pull requests, selecting the matching design reference, rendering the changed code, comparing both versions, and posting a parity verdict.
Why use it?
It helps prove whether a UI code change matches its design reference and reports specific mismatches in the pull request.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the yschimke-skills plugin — 8 skills shipped together

Good fit It is for reviewing interface pull requests, selecting the matching design reference, rendering the changed code, comparing both versions, and posting a parity verdict.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/yschimke/skills/design-parity-review
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.

Any agent
npx skills add yschimke/skills --skill design-parity-review
Clone the repo
git clone --depth 1 https://github.com/yschimke/skills

Made for: Claude Code.

Or install yschimke-skills, the plugin that ships this one along with the rest of its 8 skills.

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 design-parity-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/yschimke/skills/design-parity-review/github.svg)](https://agentmods.dev/skills/yschimke/skills/design-parity-review)
Your own site
<a href="https://agentmods.dev/skills/yschimke/skills/design-parity-review"><img src="https://agentmods.dev/badge/skills/yschimke/skills/design-parity-review/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for design-parity-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/yschimke/skills/design-parity-review"><img src="https://agentmods.dev/badge/skills/yschimke/skills/design-parity-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 133 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,584 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00133 $0.02584
Opus 5 $0.00067 $0.01292
Sonnet 5 $0.00027 $0.00517
Haiku 4.5 $0.00013 $0.00258

Measured 11d ago against content hash 9c27bfc3cfb6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

design-parity-review 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 11d 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/design-parity-review/SKILL.md · 206 lines

How it starts

The opening of the file, as written. The whole thing — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Design parity — reviewing code against its design

design-parity is a tool-neutral bot that proves a UI pull request is at parity with its intended design. On a UI PR it:

  1. resolves which design reference matches the changed component,
  2. renders the new code — the candidate — via compose-preview,
  3. diffs candidate vs reference (visual + semantic + token),
  4. posts a verdict in the PR — e.g. "implements Figma Button/Primary; padding 12dp vs spec 16dp; dark-theme contrast fails AA."

The candidate side is the upstream compose-preview renderer (the compose-preview skill). What design-parity owns is the reference side and the correspondence layer that decides which design maps to which code.

Source

Maintained at github.com/yschimke/skills under skills/design-parity-review/. The tool ships from yschimke/design-parity and on npm as design-parity — run it with npx design-parity …, no checkout needed. That repo's docs/README.md indexes the full contracts; when it disagrees with this skill, it wins.

Which direction is this?

The two directions are different tools and it is worth being explicit, because picking the wrong one wastes a lot of setup:

You want Direction Skill
"Does this PR's code match the Figma design?" design → code this skill
"Publish our component system into Figma as a sticker sheet" code → design compose-design-catalogfigma-catalog-import
"Is the rendered UI different from last commit?" neither — no design involved compose-preview-review

Round-tripping — running both directions on one project — is supported and covered in references/round-trip.md. Read the direction policy section below first: which side is canonical is a committed decision, not a per-run choice.

Read the full file on GitHub · 206 lines

Files

What ships with it

3 files 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. 11d ago First seen · 206 lines · 133 tokens per session scan A 9c27bfc3cfb6

Subscribe to this mod's changes

design-parity-review is a skill published in the GitHub repository yschimke/skills (2 stars, last pushed yesterday), licensed Apache-2.0. It adds 133 tokens to every session and 2,584 once invoked, about $0.0007 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 2026-08-31.

Related

Other skills, from other repositories

tastemaker

Generate genuinely beautiful, on-brand UI instead of generic "AI slop" — use whenever the user asks to build, design, style, or improve a UI, landing page, dashboard, app screen, or component, whenever a PRD/spec needs a design pass before implementation, whenever the user pastes reference images/Pinterest/Dribbble…

codeswithroh/tastemaker · 202 tokens

ideagram

Turn a concept, feature description, blog post, or pitch into a single beautiful, on-brand illustration by matching it to a real unDraw illustration in a local library and recoloring it to the brand accent — genuine illustrator quality, not an AI-drawn approximation. Use whenever the user asks to "make an…

codeswithroh/tastemaker · 142 tokens

design-standards

Apply production-grade design standards when building or reviewing pages, components, or UI. Use this skill whenever the user asks to build a page, design a component, lay out a section, review the UI, fix the layout, or check design quality. Triggers on build a page, create a component, design a section, hero, card…

rampstackco/claude-skills · 122 tokens

image-to-psd

A skill that reconstructs images as editable, layered Photoshop files. It separates the repaired background, visual components, and text into layers instead of leaving the page as one flat image.

DSY-Xueai/image2editable · 75 tokens

review-arch

Conduct a principal-level architecture review of a system, specification, diagram, or set of design decisions. Use when asked to review an architecture, evaluate a design, assess coupling/cohesion, check for anti-patterns, audit system boundaries, or produce an Architecture Review Board (ARB) style verdict. Also use…

sergeyklay/.agents · 199 tokens

review-impl

Review implementation changes for a given task against architectural standards. Use when reviewing a PR, evaluating recently committed code, assessing whether implementation changes are correct and architecturally sound, or when asked to 'review my changes', 'check this implementation', 'review what I built', 'is this…

sergeyklay/.agents · 155 tokens