fundamental-styles: Skill for Claude Code

.claude/skills/accessibility-guide/SKILL.md

accessibility-guide is a skill for Claude Code from SAP/fundamental-styles. It costs 26 tokens per session (6,241 once invoked), scanned A, original, Apache-2.0.

A guide for writing accessible HTML component examples. It covers semantic HTML, ARIA attributes, form labels, and WCAG, a set of widely used web accessibility guidelines.

In plain words
What is it for?
Use it when creating, reviewing, or fixing component demos, especially navigation, buttons, form controls, ARIA roles, and other accessibility details.
Why use it?
It helps examples work for people using keyboards or assistive technologies and avoids replacing built-in HTML behavior with incorrect custom roles.

Skill for Claude Code ✓ vendor

Written for Claude Code: installed under .claude/. Also seen: positional $N argument.

This is SAP/fundamental-styles's own configuration. It tells Claude Code how to work on fundamental-styles 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 fundamental-styles configures →

About the project

Fundamental Library Styles is a framework-independent CSS component library for creating SAP web interfaces with reusable styles and components. Developers can use it with Angular, React, Vue, or plain HTML to build consistent SAP applications and apply supported visual themes.

SAP/fundamental-styles · 276 stars · on GitHub · sap.github.io

Reuse

Borrowing it

Nothing to install: this file belongs to SAP/fundamental-styles. 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/SAP/fundamental-styles/main/.claude/skills/accessibility-guide/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/SAP/fundamental-styles

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 accessibility-guide

README.md
[![agentmods](https://agentmods.dev/badge/skills/sap/fundamental-styles/accessibility-guide/github.svg)](https://agentmods.dev/skills/sap/fundamental-styles/accessibility-guide)
Your own site
<a href="https://agentmods.dev/skills/sap/fundamental-styles/accessibility-guide"><img src="https://agentmods.dev/badge/skills/sap/fundamental-styles/accessibility-guide/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 accessibility-guide

Your own site · 80×15
<a href="https://agentmods.dev/skills/sap/fundamental-styles/accessibility-guide"><img src="https://agentmods.dev/badge/skills/sap/fundamental-styles/accessibility-guide.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,241 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 4 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Prompt Injection · line 74
    Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.
    Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
  • high Prompt Injection · line 169
    Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.
    Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
  • high Prompt Injection · line 228
    Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.
    Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
  • medium Prompt Injection · line 20
    Subtle instructions detected that may alter agent decision-making or introduce hidden biases.
    Fix: Review content for implicit steering or bias. Ensure instructions are explicit and align with the skill's stated purpose.
How audits are shown
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 $0.00026 $0.06241
Opus 5.5 $0.00010 $0.02496
Sonnet 5.5 $0.00005 $0.01248
Haiku 4.5 $0.00003 $0.00624

Measured 2mo ago against content hash cdab7bc2591d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

accessibility-guide 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 2mo 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/accessibility-guide/SKILL.md · 884 lines

How it starts

The opening of the file, as written. The whole thing — 884 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Accessibility Guide for fundamental-styles

When to use this skill:

  • Writing HTML examples for component documentation
  • Creating new component demos
  • Reviewing component accessibility
  • Fixing accessibility issues in examples
  • Questions about ARIA roles and attributes

Core Principles

1. Semantic HTML First

Always prefer native HTML elements over ARIA roles when possible.

✅ DO:

<button>Click me</button>
<nav>...</nav>
<header>...</header>
<input type="checkbox" />

❌ DON'T:

<div role="button">Click me</div>
<div role="navigation">...</div>
<div role="banner">...</div>
<div role="checkbox"></div>

Why: Native elements provide built-in keyboard support, focus management, and semantics without JavaScript.

2. Labels MUST Be Properly Connected

Every form control must have an accessible label.

✅ DO - Use for and id:

<label for="username">Username:</label> <input id="username" type="text" name="username" />

✅ DO - Nested label (alternative):

<label>
    Username:
    <input type="text" name="username" />
</label>

✅ DO - Using aria-labelledby for complex labels:

<span id="label-firstname">First Name</span>
<span id="label-required">(required)</span>
<input type="text" aria-labelledby="label-firstname label-required" />

❌ DON'T - Missing connection:

<label>Username</label>
<input type="text" />
<!-- No for/id connection -->

❌ DON'T - Non-existent ID reference:

<label for="nonexistent">Username</label>
<input id="username" type="text" />
<!-- Mismatched IDs -->

3. ID References Must Be Valid

When using aria-labelledby, aria-describedby, or for attributes, the referenced IDs must exist in the DOM.

✅ DO:

<h2 id="dialog-title">Confirm Action</h2>
<div role="dialog" aria-labelledby="dialog-title" aria-describedby="dialog-desc">
    <p id="dialog-desc">Are you sure you want to proceed?</p>
    <button>Confirm</button>
</div>

Read the full file on GitHub · 884 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. 2mo ago First seen · 884 lines · 26 tokens per session scan A cdab7bc2591d

Subscribe to this mod's changes

accessibility-guide is a skill published in the GitHub repository SAP/fundamental-styles (276 stars, last pushed today), licensed Apache-2.0. It adds 26 tokens to every session and 6,241 once invoked, about $0.0001 per session on Opus 5.5. 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

experiment-tracking-swanlab

Provides guidance for experiment tracking with SwanLab. Use when you need open-source run tracking, local or self-hosted dashboards, and lightweight media logging for ML workflows.

Orchestra-Research/AI-Research-SKILLs · 40 tokens

ads-youtube

Audit YouTube Ads campaign setup, video inventory, Shorts, in-stream, CTV, creative, audiences, brand safety, bidding, and measurement. Use for YouTube Ads, video ads, pre-roll, bumper ads, skippable in-stream, Shorts ads, VAC migration, or CTV. Read-only; use ads-google for Google-managed campaign types and…

AgriciDaniel/claude-ads · 84 tokens

ads-launch

Draft or explicitly apply a paid-ad campaign launch through Claude Ads capability-gated adapters. Use for campaign creation, launch plans, publishing ads, activating campaigns, uploading creative, or requests to push a campaign live.

AgriciDaniel/claude-ads · 45 tokens

notifications

Send notifications through the unified notification router.

vellum-ai/vellum-assistant · 9 tokens

telegram-setup

Connect a Telegram bot to the Vellum Assistant gateway with automated webhook registration and credential storage.

vellum-ai/vellum-assistant · 22 tokens

chat-complex-documents

Chat with and search your complex documents — ask questions, extract tables and fields, and get answers grounded in the source. Connects the hosted Unstructured Transform MCP server to parse, structure, and enrich PDFs, Word/Excel/PowerPoint, images, scanned files, emails, and 60+ other formats into clean, AI-ready…

vellum-ai/vellum-assistant · 90 tokens