figma-audit-accessibility

figma-audit-accessibility is a skill for Claude Code from southleft/figma-console-mcp-skills. It costs 195 tokens per session (932 once invoked), scanned A, original, MIT.

A detailed accessibility review for one Figma component or component set. It checks states such as hover, focus, disabled, and error, along with contrast, non-color cues, target size, annotations, and color-vision simulations.

In plain words
What is it for?
Use it to produce a weighted accessibility scorecard for an interactive or presentational Figma component and identify prioritized improvements.
Why use it?
It finds accessibility problems in a component’s states and ranks the fixes, instead of only checking broad design files for isolated rule violations.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

Part of the figma-console-mcp-skills plugin — 23 skills shipped together

Good fit Use it to produce a weighted accessibility scorecard for an interactive or presentational Figma component and identify prioritized improvements.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/southleft/figma-console-mcp-skills/figma-audit-accessibility
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 southleft/figma-console-mcp-skills --skill figma-audit-accessibility
Clone the repo
git clone --depth 1 https://github.com/southleft/figma-console-mcp-skills

Made for: Claude Code.

Or install figma-console-mcp-skills, the plugin that ships this one along with the rest of its 23 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 figma-audit-accessibility

README.md
[![agentmods](https://agentmods.dev/badge/skills/southleft/figma-console-mcp-skills/figma-audit-accessibility/github.svg)](https://agentmods.dev/skills/southleft/figma-console-mcp-skills/figma-audit-accessibility)
Your own site
<a href="https://agentmods.dev/skills/southleft/figma-console-mcp-skills/figma-audit-accessibility"><img src="https://agentmods.dev/badge/skills/southleft/figma-console-mcp-skills/figma-audit-accessibility/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 figma-audit-accessibility

Your own site · 80×15
<a href="https://agentmods.dev/skills/southleft/figma-console-mcp-skills/figma-audit-accessibility"><img src="https://agentmods.dev/badge/skills/southleft/figma-console-mcp-skills/figma-audit-accessibility.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 195 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 932 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 pass 7 Sept 2026
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 $0.00195 $0.00932
Opus 5 $0.00097 $0.00466
Sonnet 5 $0.00039 $0.00186
Haiku 4.5 $0.00019 $0.00093

Measured 12d ago against content hash 3a5a0707620b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

figma-audit-accessibility 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 12d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/audit-accessibility.js), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

skills/figma-audit-accessibility/SKILL.md · 47 lines

How it starts

The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.

figma-audit-accessibility — per-component a11y scorecard

Run a deep accessibility audit on a single component or component set and get a weighted 0–100 scorecard with prioritized fixes. Where figma-lint-design sweeps a whole tree for many rule violations, this skill goes deep on one component: it understands variant axes, classifies the component as interactive vs presentational, and scores each a11y dimension accordingly.

All via use_figma, on any plan — it inspects the real variant tree, fills, strokes, effects, and the component description.

Skill boundaries

  • use_figma rules — load the official figma-use skill first; it is the full Figma Plugin API reference. Essentials these scripts rely on: plain JS with top-level await + return (no IIFE, no figma.closePlugin(); console.log is not returned), inputs inlined as const at the top of each script, colors in 0–1 range, load fonts before any text op, await figma.getNodeByIdAsync(...), and atomic errors (a failed script applies nothing — read the error, fix, retry).
  • Tree-wide WCAG + design-system lint → use figma-lint-design.
  • CODE-side a11y (axe-core over HTML) → use figma-scan-code-accessibility.
  • Design-vs-code drift → use figma-check-design-parity.

Workflow

  1. Target a component. Set NODE_ID to a COMPONENT_SET, COMPONENT, or INSTANCE id (the script walks INSTANCE → main component → parent set automatically). Leave it null to audit the current single selection.
  2. Set the tap-target minimum. TARGET_SIZE defaults to 24 (WCAG 2.5.8 minimum); pass 44 or 48 for stricter mobile targets.
  3. Run scripts/audit-accessibility.js via use_figma (skillNames: "figma-audit-accessibility").
  4. Read the scorecard. overallScore is a classification-weighted blend of the six category scores. See references/audit-categories.md for each category, its weight, and how to raise it.
  5. Work the recommendations. recommendations[] is already sorted by priority (high/medium/low) with the WCAG SC named. Fix, then re-run to confirm the score moved.

Read the full file on GitHub · 47 lines

Files

What ships with it

2 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. 12d ago First seen · 47 lines · 195 tokens per session scan A 3a5a0707620b

Subscribe to this mod's changes

figma-audit-accessibility is a skill published in the GitHub repository southleft/figma-console-mcp-skills (80 stars, last pushed 26d ago), licensed MIT. It adds 195 tokens to every session and 932 once invoked, about $0.0010 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

design-to-code

Use this skill when translating UI/UX designs into production-ready frontend code. Handles design source ingestion (Figma, Sketch, Adobe XD, screenshots, design specs), design token extraction, component hierarchy mapping, responsive breakpoint strategy, accessibility-first implementation (WCAG 2.1 AA minimum)…

JPeetz/agent-skills · 184 tokens

design-md

Author/validate/export Google's DESIGN.md token spec files.

mateaix/mateclaw · 14 tokens

system-pitch

Write a design system investment pitch with a business case and ROI framing. Trigger when someone says: pitch the design system, make the case for the system, sell this to leadership, justify the investment, business case for design systems, why should we invest in a design system, or anything about building an…

murphytrueman/design-system-ops · 72 tokens

token-audit

Audit a design system's token definitions for naming violations, missing semantic tiers, and structural debt. This audits how tokens are defined and organised, NOT how they are consumed in code. Trigger when someone says: audit my tokens, token naming review, are my tokens consistent, token health check, review my…

murphytrueman/design-system-ops · 93 tokens

ai-component-description

Generate AI-optimised text descriptions for components, formatted for Figma's MCP server and LLM consumption. This produces prose descriptions in a six-section format (purpose, props, anti-patterns, composition, accessibility, examples), NOT JSON schemas or structured data files. Trigger when someone says: write…

murphytrueman/design-system-ops · 132 tokens

context-engine-builder

Generate a context engine — seven structured blueprint files (UX, UI, content, accessibility, ethical, technical, business intelligence) that encode everything an AI agent needs to work with a design system. This produces YAML infrastructure in .ai/context-engine/, NOT a health score or quality assessment. Trigger…

murphytrueman/design-system-ops · 135 tokens