AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

BrailleTest

skill-cg-shmoop-claude-skills-brailletest · by cg-shmoop

>

↗ Repository
— No reviews yet
0 installs
36 views
0.0% view→install

Install

$ agentstack add skill-cg-shmoop-claude-skills-brailletest

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • ✓ Prompt-injection patterns
  • ✓ Secret / credential exfiltration
  • ✓ Dangerous shell & filesystem operations
  • ✓ Untrusted network calls
  • ✓ Known-malicious package signatures

What it can access

  • ✓ Network access No
  • ✓ Filesystem access No
  • ✓ Shell / process execution No
  • ✓ Environment & secrets No
  • ✓ Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-cg-shmoop-claude-skills-brailletest)

Reliability & compatibility

✓ Security review passed
0 installs to date
— no reviews yet
● 2mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of BrailleTest? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

BrailleTest

Tests websites from the perspective of a blind user with a 40-cell refreshable braille display using JAWS screen reader navigation.

What It Does

  • Navigates pages using only JAWS keyboard commands (heading nav, landmarks, tab, form fields)
  • Simulates a 40-cell braille display — sees only 40 characters at a time
  • Records every braille display state, command, and agent decision in a human-readable transcript
  • Detects accessibility failures invisible to automated scanners: missing headings, unlabeled forms, excessive navigation cost, silent dynamic content
  • Produces session logs that show exactly what a braille user would experience

What It Does NOT Do

  • Does not replace axe-core scanning (complementary, not duplicative)
  • Does not test visual accessibility (color contrast, text size)
  • Does not emulate speech-only screen reader users (braille-specific)

Workflows

| Workflow | Trigger | Purpose | |----------|---------|---------| | SinglePage | "braille test [URL]" | Test one page with orientation + optional form completion | | BatchTest | "braille test all pages" | Test multiple pages from a URL list (Phase 4) | | TaskFlow | "test if a braille user can [task]" | Multi-page user journey (Phase 4) |

Requirements

  • Windows (for UI Automation APIs)
  • .NET 8 Runtime (for UIA adapter)
  • Node.js / Bun (for TypeScript orchestrator)
  • JAWS (optional — enhanced fidelity when present)

Output

Session transcripts saved to:

C:\projects\accessibility-audits\braille-tests\YYYY-MM\domain\sessions\

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Write a review

Versions

  • v0.1.0 Imported from the upstream source.

More in Agent Skills