Ready to supercharge your AI agents?

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

Screen Reader Lab · community-access | DecimalAI

frontendby community-access

Screen Reader Lab

community-access/Screen Reader Lab

Source community-access/accessibility-agents ↗License MIT

Interactive screen reader simulation for education and debugging. Parses HTML/JSX and produces step-by-step narration of what a screen reader would announce. Supports reading order, Tab navigation, heading navigation, and form navigation modes.

SkillScore100Maintained

Automatic

QA & Test Engineering pack

Last verified 8/23/2026

What it changes

Passed 22 of 22 test cases with the skill, and 21 of 22 without it.

Without skill95%

With skill100%

Checks it passed that the model alone missed

Identify placeholder as having the lowest precedence in accessible name calculation

1 fixed21 passed either way0 still failing0 broke

Pass-rate lift: +5 pp
Tokens: +2%
Agent turns: 0%
Response time: -17%

Model gemini-3.6-flashMeasured 8/23/2026v122 of 22 cases passed with skill

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

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/community-access-screen-reader-lab/SKILL.md https://app.decimal.ai/s/community-access-screen-reader-lab-733cd5/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add community-access-screen-reader-lab-733cd5, 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/community-access-screen-reader-lab/ and pins it in .decimal/skills.lock

decimalai skills add community-access-screen-reader-lab-733cd5

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

curl -fsSL --create-dirs -o .claude/skills/community-access-screen-reader-lab/SKILL.md https://app.decimal.ai/s/community-access-screen-reader-lab-733cd5/SKILL.md

Raw file: /s/community-access-screen-reader-lab-733cd5/SKILL.md ↗ · machine-readable summary at /s/community-access-screen-reader-lab-733cd5.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

A test case the skill fixed. Same model, same prompt, with and without the skill.

Prompt

Among aria-labelledby, aria-label, native label, element text content, title, and placeholder, identify which attribute holds the absolute lowest priority in accessible name computation.

What was checked, without and with the skill
Checked	Without skill	With skill
Identify placeholder as having the lowest precedence in accessible name calculation	Missed	Passed

case-06 · gemini-3.6-flash · 8/23/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md26 linessingle file

You are a screen reader simulation agent. You parse HTML/JSX and produce a step-by-step narration of what a screen reader would announce, helping developers understand the accessible experience.

Disclaimer: This is an educational simulation. Real screen reader behavior varies between NVDA, JAWS, VoiceOver, and Narrator.

Simulation Modes

Mode 1: Reading Order

Walk the DOM in reading order. For each element announce: role, accessible name, state, description.

Mode 2: Tab Navigation

Simulate Tab through focusable elements. Flag focus traps, unreachable interactive elements.

Mode 3: Heading Navigation (H Key)

List all headings by level. Flag skipped levels, missing H1, multiple H1s.

Mode 4: Form Navigation (F Key)

List form controls with labels. Flag unlabeled inputs, missing required indicators.

Accessible Name Computation

aria-labelledby → 2. aria-label → 3. Native <label> → 4. Element content → 5. title → 6. placeholder

Process

Read the file or code snippet
Parse HTML/JSX and build accessibility tree
Walk the tree in selected mode
Report findings with recommended fixes

Track record

Benchmark

22 / 22

test cases passed, vs 21 / 22 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 v4 — 8/3/2026

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

community-access / accessibility-agents

.gemini/extensions/a11y-agents/skills/screen-reader-lab/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1

Other skills for the same job

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

community-access/screen-reader-labInteractive screen reader simulation for education and debugging. Parses HTML/JSX and produces step-by-step narration of what a screen reader would announce. Supports reading order, Tab navigation, heading navigation (H key), and form navigation (F key) modes. Not a replacement for real screen reader testing.Close match+23 pp pass-rate lift

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