agentleFS
srikanth-manivannansrikanth-manivannan/claude-agent-factory/skills/accessibility/a11y-auditor/SKILL.md

a11y-auditor

Skill1 starsChanged 5 months agoMITView on GitHub

Use this to audit a UI against WCAG and report prioritized, actionable accessibility fixes.

3 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Set the target level: Default WCAG 2.2 AA (/standards/accessibility.md).

    line 45

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Accessibility Auditor

Use this to audit a UI against WCAG and report prioritized, actionable accessibility fixes.

Tech profile — Technology: any UI · Language: any · Stack: any frontend · Toolchain: any · Domain: accessibility (Audits any markup/UI; target WCAG level is configurable.)

When to use this skill

  • Auditing a page/component against WCAG (AA default) before release.
  • Producing the findings that feed the accessibility-audit workflow.
  • Establishing an a11y baseline for an existing UI.

When NOT to use this skill

  • Applying fixes — use accessibility/aria-annotator, color-contrast-fixer, keyboard-nav-checker (this skill finds; they fix).
  • Deep screen-reader QA — use accessibility/screen-reader-tester.

Prerequisites

  • The UI to audit (markup, component, or page) and the target WCAG level.

Inputs

InputRequiredDescription
uiyesThe markup/component/page to audit
wcag_levelnoA / AA (default) / AAA
contextnoIntended use, interactions, key flows

Instructions

  1. Set the target level. Default WCAG 2.2 AA (/standards/accessibility.md).
  2. Audit across the four POUR principles, producing findings:
    • Perceivable — text alternatives, contrast, meaning not by color alone.
    • Operable — keyboard operability, focus order, visible focus, no traps.
    • Understandable — labels, error messaging, predictable behavior.
    • Robust — valid semantics, correct (non-redundant) ARIA.
  3. Cite each finding to a specific element + the WCAG success criterion (e.g. 1.4.3).
  4. Severity-tag 🔴/🟠/🟡 by user impact (blocks a task vs. annoyance).
  5. Recommend a concrete fix per finding and name the skill that applies it.
  6. Note what passed (don't only list problems).
  7. Flag what needs manual verification (e.g. screen-reader pass) — automation can't catch everything.

Output

A prioritized accessibility report: findings grouped by POUR, each with element + WCAG criterion + severity + recommended fix (and the fixer skill), a "passed" summary, and a manual-verification list. Maps onto the accessibility-review checklist.

Constraints & safety

  • Target AA by default; never silently lower the bar.
  • Findings are actionable — element-specific + criterion-cited; no vague "improve a11y".
  • Honest about automation limits — flag what needs human verification.

Examples

Minimal below; full examples in EXAMPLES.md.

Given: a form with an unlabeled input and low-contrast text. Produces: 🔴 missing label (WCAG 3.3.2 → aria-annotator), 🟠 contrast 3.1:1 (WCAG 1.4.3 → color-contrast-fixer), plus a keyboard-nav manual-check note.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.