Ready to supercharge your AI agents?

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

Get Started Free →

Accessibility Pass — measured AI agent skill | DecimalAI

archive228/a11y-pass

SkillScore95Maintained

Catch the accessibility failures that ship in almost every AI-built UI. Use after building any interactive component.

Frontendby archive228

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

Frontend / UI pack

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

pip install decimalai

2 · Get the skill — writes .claude/skills/archive228-a11y-pass/SKILL.md

decimalai skills pull archive228-a11y-pass --out .claude/skills/

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

curl -fsSL --create-dirs -o .claude/skills/archive228-a11y-pass/SKILL.md https://app.decimal.ai/s/archive228-a11y-pass/SKILL.md

Raw file: /s/archive228-a11y-pass/SKILL.md ↗ · machine-readable summary at /s/archive228-a11y-pass.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

22 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 7h ago

Yes — +14% lift+11% tokens0% turns95% of whole cases pass with skill (21/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-01	✗→✓	▲ Improved	118%	0%
case-03	✗→✓	▲ Improved	-17%	0%
case-15	✗→✓	▲ Improved	56%	0%
case-02	✓→✓	＝ Same ✓	-5%	0%
case-04	✓→✓	＝ Same ✓	11%	0%

Showing 5 of 22 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

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

archive228 / loopkit

skills/a11y-pass/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1

Skill contents

SKILL.md

Accessibility Pass

Keyboard — every interactive element reachable and operable by Tab/Enter/Esc. Modals trap focus and restore it on close.
Labels — every input has a real <label>; icon-only buttons have aria-label.
Images — meaningful alt; decorative images alt="".
Contrast — text ≥ 4.5:1 (3:1 for large). Don't encode meaning in color alone.
Semantics — real <button>/<a>, not a clickable <div>. Headings in order.
Focus — visible focus ring. Never outline: none without a replacement.

Output: each failure with the element + the fix. Test it with Tab only, no mouse.

Want to see if archive228/a11y-pass would activate on your phrasing? Try it before you install — no LLM call, no signup.

Other measured skills in the registry, with their headline benchmark lift.