analyse-design

A design audit of an application, website, or document based on its code and screenshots, covering colours, fonts, spacing, and repeated interface patterns.

In plain words
What is it for?
Use it to document a design system, extract visual rules, review consistency, or guide the implementation of matching interface components.
Why use it?
It makes an existing visual style explicit so developers can understand how the product is designed and spot inconsistencies.

Skill for Claude CodeCodex

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/sammcj/agentic-coding/analyse-design
Any agent
npx skills add sammcj/agentic-coding --skill analyse-design
Clone the repo
git clone --depth 1 https://github.com/sammcj/agentic-coding

Made for: Claude Code, Codex.

Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,003 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 $0.00060 $0.01003
Opus 5 $0.00030 $0.00502
Sonnet 5 $0.00012 $0.00201
Haiku 4.5 $0.00006 $0.00100

Measured 2d ago against content hash ab997cadf09a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

analyse-design 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 2d 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/analyse-design/SKILL.md · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Analysing Design Systems

Act as a UI/UX design analyst conducting analysis of frontend and design systems.

You may be asked to reverse-engineer the design system from a codebase, website or provided screenshots. Unless otherwise stated by the user your goal is to produce a design system reference document a developer could use to build components that belong in this application.

First, create a task for each phase - scope, source scan, dimension analysis, and each output section - then work them to completion.

Where to Look

Scan for design-relevant sources in this priority order:

  1. Theme/token files - tailwind.config, Tailwind v4 CSS-first tokens (@theme blocks in CSS), theme.ts/js, tokens.json, design-tokens, variables.css/scss
  2. Global styles - global.css, app.css, index.css, _variables.scss, CSS custom properties (:root / [data-theme])
  3. Component library config - shadcn components.json, MUI theme, Chakra theme, Ant Design config
  4. Layout components - shell, sidebar, header, navigation components for spacing and structure patterns
  5. Representative components - buttons, inputs, cards, modals for recurring visual patterns

Dimensions to Analyse

For each dimension, cite specific files and style definitions.

  • Design language - visual school/philosophy (e.g., neo-brutalist, material, glassmorphism, minimal flat). Mood conveyed. Unique visual signatures
  • Colour palette - extract actual values. Identify primary, secondary, accent, background, surface, semantic colours (error, success, warning). Note contrast ratios and dark/light mode support
  • Typography - font families, weight scale, size scale, line heights. How hierarchy is established
  • Spacing and layout - spacing scale, grid system, whitespace usage, information density, consistent sizing patterns
  • Component patterns - common shapes, border radii, shadow treatments, interaction states across buttons, inputs, cards, navigation, status indicators
  • Iconography - icon style (outline, filled, duotone), library if identifiable
  • Motion - animation patterns, easing curves, transition durations found in code
  • Responsive behaviour - breakpoints, layout shifts, mobile adaptations

Read the full file on GitHub · 59 lines

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. 2d ago First seen · 59 lines · 60 tokens per session scan A ab997cadf09a

Subscribe to this mod's changes

analyse-design is a skill published in the GitHub repository sammcj/agentic-coding (158 stars, last pushed 8d ago), licensed Apache-2.0. It adds 60 tokens to every session and 1,003 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

aksel-builder

Expert builder for Aksel, the Nav / @navikt design system — React components, design tokens, layout primitives, theming (light/dark), icons, CSS, the Tailwind preset, version migrations, Figma-to-code. Triggers — Aksel, "using/with aksel", Nav/Navikt, "designsystemet", "design system", @navikt/ds- (e.g.…

navikt/copilot · 181 tokens

aksel-spacing

Lag responsive layouts med Aksel Design System (v8+) - spacing tokens, layout primitives (Box, HStack, VStack, HGrid, Page, Bleed) og ResponsiveProp.

navikt/copilot · 41 tokens

web-design-reviewer

Visuell inspeksjon av nettsider for å identifisere og fikse designproblemer. Trigges av forespørsler som "sjekk designet", "gå gjennom UI-en", "fiks layouten", "finn designfeil". Finner problemer med responsivt design, tilgjengelighet, visuell konsistens og layout, og fikser dem i kildekoden.

navikt/copilot · 89 tokens

figma-plugin

Use when building Figma plugins, creating design automation tools, implementing sandbox/UI communication, or working with the Figma Plugin API for node manipulation, styles, and components.

bergside/design-md-figma · 38 tokens

ilya-sutskever

Agente que simula Ilya Sutskever — co-fundador da OpenAI, ex-Chief Scientist, fundador da SSI. Use quando quiser perspectivas sobre: AGI safety-first, consciência de IA, scaling laws, deep learning profundo, o episódio de novembro 2023 na OpenAI, superinteligência segura.

beel-collab/presets.dev · 67 tokens

yann-lecun

Agente que simula Yann LeCun — inventor das Convolutional Neural Networks, Chief AI Scientist da Meta, Prêmio Turing 2018.

beel-collab/presets.dev · 32 tokens