Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Skill: Accessibility Audit · plugin87 | DecimalAI

frontendby plugin87

Skill: Accessibility Audit

plugin87/a11y-audit

Source plugin87/ux-ui-agent-skills ↗License MIT

Audit a UI or design against WCAG 2.2 AA/AAA and ARIA patterns, returning criterion-referenced findings with severity and specific fixes.

NewMaintained

Automatic

Design & UX Review pack

Last verified 8/20/2026

What it changes

Passed 2 of 11 test cases with the skill, and 2 of 11 without it.

Without skill18%

With skill18%

Checks it passed that the model alone missed

Uses P0/P1/P2 severity classification.
Classifies contrast failures using the P0/P1/P2 scale.
Assigns P0 severity level to color-only communication defects.

and 1 more in the full report

3 fixed1 passed either way15 still failing3 broke

Pass-rate lift: 0 pp
Tokens: +60%
Agent turns: 0%
Response time: +60%

Model gemini-3.6-flashMeasured 8/20/2026v1 · latest is v24 of 22 cases passed with skill · 11 comparable

Tokens, turns and time describe resource use, not a dollar price.

This benchmark measured an earlier version of the skill.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/plugin87-a11y-audit/SKILL.md https://app.decimal.ai/s/plugin87-a11y-audit/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add plugin87-a11y-audit, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/plugin87-a11y-audit/ and pins it in .decimal/skills.lock

decimalai skills add plugin87-a11y-audit

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/plugin87-a11y-audit/SKILL.md https://app.decimal.ai/s/plugin87-a11y-audit/SKILL.md

Raw file: /s/plugin87-a11y-audit/SKILL.md ↗ · machine-readable summary at /s/plugin87-a11y-audit.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 3 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 3

Prompt

We are considering foreground `#595959` and background `#EEEEEE` for card subheadings. What script should be executed to measure contrast compliance, and what is the severity if it fails?

What was checked, without and with the skill
Checked	Without skill	With skill
Identifies python3 scripts/contrast.py as the required measurement tool.	Missed	Passed
Classifies contrast failures using the P0/P1/P2 scale.	Missed	Passed

case-18 · gemini-3.6-flash · 8/20/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md20 linessingle file

Skill: Accessibility Audit

Step 0 — is the kit here? This skill reads files from the kit. Check once: ls ${CLAUDE_SKILL_DIR}/../../../tokens >/dev/null 2>&1 && echo KIT_OK || echo KIT_MISSING On KIT_MISSING only the skill folders were installed, which is what npx skills add does. Say so plainly, point the user at npx ux-ui-agent-skills init or the plugin install, and stop. Do not guess the contents of a file you could not open.

Evaluate against WCAG 2.2 and the project's ARIA patterns.

Steps

Read ${CLAUDE_SKILL_DIR}/../../../accessibility/wcag-checklist.md (POUR-organized, P0/P1/P2) and ${CLAUDE_SKILL_DIR}/../../../accessibility/aria-patterns.md.
Check the mandatory P0 set per component: keyboard navigable, focus visible (≥3:1), screen-reader name/role/state, contrast (4.5:1 text / 3:1 UI), target size ≥24×24, no color-only signaling.
Verify WCAG 2.2 additions: Focus Not Obscured (2.4.11), Target Size (2.5.8), Accessible Authentication (3.3.8).
Contrast — measure, don't eyeball. For rendered HTML, RUN the real-render gates and report their actual output (CLAUDE.md → Verification Protocol): node ${CLAUDE_SKILL_DIR}/../../../scripts/measure_render.mjs <file> [--dark] (every text element) AND node ${CLAUDE_SKILL_DIR}/../../../scripts/verify_states.mjs <file> [--dark] (every interactive element in default/hover/focus — catches hover-state failures). For loose color pairs, python3 ${CLAUDE_SKILL_DIR}/../../../scripts/contrast.py "<fg>" "<bg>". Never state a ratio you did not measure.
Check reduced-motion handling (${CLAUDE_SKILL_DIR}/../../../taste/motion-choreography.md).

Output

A findings table: WCAG criterion (e.g. 1.4.3) · severity (P0/P1/P2) · what fails · specific fix. Confirm passes explicitly. Accessibility may never be traded for aesthetics.

Track record

Benchmark

2 / 11

test cases passed, vs 2 / 11 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v5 — 10/9/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

plugin87 / ux-ui-agent-skills

.claude/skills/a11y-audit/SKILL.md

View on GitHub ↗

License MITImported 10/9/2026Version v2

Other skills for the same job

Published skills whose descriptions closely match this one, with their headline benchmark lift.

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

Skill: Accessibility Audit

Steps

Output

Track record

Benchmark

Adoption

SkillSafety

Source

Other skills for the same job

Related skills