project-starter-template-es-ai: Skill for Claude Code

.claude/skills/design-system-audit/SKILL.md

design-system-audit is a skill for Claude Code from brayandiazc/project-starter-template-es-ai. It costs 92 tokens per session (772 once invoked), scanned A, original, MIT.

An audit skill that checks a user interface against the project's design tokens, approved components, interaction states, and accessibility requirements.

In plain words
What is it for?
Use it to review a component or page and report concrete issues with file locations and suggested corrections.
Why use it?
It finds inconsistent styling, missing interface states, and accessibility gaps before they reach users.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is brayandiazc/project-starter-template-es-ai's own configuration. It tells Claude Code how to work on project-starter-template-es-ai itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything project-starter-template-es-ai configures →

Reuse

Borrowing it

Nothing to install: this file belongs to brayandiazc/project-starter-template-es-ai. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/brayandiazc/project-starter-template-es-ai/main/.claude/skills/design-system-audit/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/brayandiazc/project-starter-template-es-ai

Made for: Claude Code.

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-system-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/brayandiazc/project-starter-template-es-ai/design-system-audit/github.svg)](https://agentmods.dev/skills/brayandiazc/project-starter-template-es-ai/design-system-audit)
Your own site
<a href="https://agentmods.dev/skills/brayandiazc/project-starter-template-es-ai/design-system-audit"><img src="https://agentmods.dev/badge/skills/brayandiazc/project-starter-template-es-ai/design-system-audit/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-system-audit

Your own site · 80×15
<a href="https://agentmods.dev/skills/brayandiazc/project-starter-template-es-ai/design-system-audit"><img src="https://agentmods.dev/badge/skills/brayandiazc/project-starter-template-es-ai/design-system-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 92 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 772 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 $0.00092 $0.00772
Opus 5 $0.00046 $0.00386
Sonnet 5 $0.00018 $0.00154
Haiku 4.5 $0.00009 $0.00077

Measured 4d ago against content hash 3fdb109034a3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

design-system-audit 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 4d 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.

.claude/skills/design-system-audit/SKILL.md · 50 lines

What it actually says

Audita la UI indicada frente al design system de design/.

Los colores no los revisas tú. El job Design system del CI (.github/scripts/check-design-tokens.sh) ya falla ante cualquier hex, rgb(), utilidad de paleta (bg-blue-500) o valor arbitrario (bg-[#0A7A9D]) en las vistas. Si crees ver un color crudo, es que el check no cubre esa ruta: dilo, y propón añadir la carpeta al script en vez de convertirte en un linter humano.

Tu trabajo es lo que ningún script puede comprobar:

  1. Lee design/README.md (el sistema) y docs/conventions/ui.md (cómo se organizan las vistas y dónde están los assets de marca).

  2. Primitiva nativa antes que componente reinventado. Un diálogo hecho con <div> y position: fixed es un hallazgo aunque se vea bien: <dialog>, <details> y popover traen foco, teclado y Escape resueltos por el navegador. Si hay un componente custom donde había una primitiva, señálalo con el reemplazo concreto.

  3. Si el componente custom es inevitable, señálalo y remite su accesibilidad (focus trap, Escape, aria-*, tabulación) a /accessibility-audit — esa lista vive allí, en un solo sitio, a propósito.

  4. Estados de interacción: default, hover, active y disabled. (El foco visible y la navegación por teclado los audita /accessibility-audit.)

  5. Los cuatro estados de datos, en toda vista que cargue algo: loading (skeleton con la forma del contenido, no un spinner genérico ni "Cargando…"), empty (icono + por qué está vacío + CTA que oriente), error (mensaje + acción de reintento) y éxito. El estado vacío es el que más define el producto y el que más se salta.

  6. Ambos temas: claro y data-theme="dark" — que la vista use los tokens en los dos y ninguna pieza quede pegada a un solo tema. (La medición de contraste AA es de /accessibility-audit; design/preview.html la trae para los tokens base.)

  7. Jerarquía antes que decoración: ¿se entiende qué es lo importante de la vista sin leer el texto? Espaciado y peso tipográfico antes que bordes y sombras.

Informa una lista: cada ítem Pasa / Falla, con archivo:línea y la corrección concreta. Ejemplo: Modal.tsx:12 — <div role="dialog"> sin focus trap; usa <dialog>.

NO rediseñes ni reestilices por iniciativa propia: informas y propones. Para una revisión de accesibilidad completa (contraste medido, lectores de pantalla), usa accessibility-audit. design/ siempre manda.

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. 4d ago Changed · +28 lines · -15 tokens per session 3fdb109034a3
  2. 10d ago First seen · 22 lines · 107 tokens per session scan A 9db9de0de7a4

Subscribe to this mod's changes

design-system-audit is a skill published in the GitHub repository brayandiazc/project-starter-template-es-ai (15 stars, last pushed 4d ago), licensed MIT. It adds 92 tokens to every session and 772 once invoked, about $0.0005 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 2026-09-01.

Related

Other skills, from other repositories

dxf

Generate, regenerate, and validate 2D DXF drawings from Python build123d sources. Use for DXF files, .py drawing scripts, @dxf models, 2D profiles, outlines, templates, gaskets, panels, flat patterns, laser/plasma/waterjet cut layouts, and 2D drawing exports of CAD geometry.

earthtojake/text-to-cad · 75 tokens

frontend-ui-dark-ts

Build dark-themed React applications using Tailwind CSS with custom theming, glassmorphism effects, and Framer Motion animations. Use when creating dashboards, admin panels, or data-rich interfaces with a refined dark aesthetic.

microsoft/skills · 48 tokens

openkb-html-critic

Use to review a generated HTML deck or single-page artifact for visual quality and structural correctness. Especially good at catching CSS specificity bugs where slide-modifier classes (.divider, .center, .q, .flow etc.) accidentally override the base .slide{display:none} and cause one slide to stack on top of every…

VectifyAI/OpenKB · 132 tokens

decocms-ui

Build or style React UI with the decocms product design system (@decocms/ui). Use when creating interfaces, pages, or components in a project that should look like decocms products, when the user mentions "design system", "@decocms/ui", "decocms style", or asks to make UI consistent with Studio. Covers installation…

decocms/studio · 91 tokens

multi-surface-render

Multi-surface rendering with json-render — one JSON spec produces React web, Next.js, React Native, Ink terminal UIs, PDFs, emails, Remotion videos, OG images, and 3D scenes. Covers renderer target selection, registry mapping, and platform APIs (renderToBuffer, renderToStream, renderToFile). Use when generating output…

yonatangross/orchestkit · 98 tokens

design-stylecards

Declarative catalog of named aesthetic recipes — exact shadow stacks, glass surfaces, gradient treatments, and type scales as copy-paste values with Use-When and Avoid rules. Use when the user asks for polished elevation, glassmorphism, a border gradient, a mesh background, or any 'make it look like X' request where…

yonatangross/orchestkit · 86 tokens