Expert in building accessibility scanning tools, rule engines, document parsers, report generators, and audit automation. WCAG criterion mapping, severity scoring, CLI/GUI scanner architecture, CI/CD integration.
SkillScore87Maintained
Automatic
◆QA & Test Engineering pack
Last verified 8/22/2026
What it changes
Passed 20 of 23 test cases with the skill, and 14 of 23 without it.
Without skill61%
With skill87%
Checks it passed that the model alone missed
The rule violations reference specific WCAG success criteria.
The EPUB rule violations reference specific WCAG success criteria.
The rule findings use the Critical, Serious, Moderate, Minor severity scale.
and 6 more in the full report
8 fixed12 passed either way1 still failing2 broke
Pass-rate lift
+26 pp
Tokens
+24%
Agent turns
0%
Response time
+17%
Model gemini-3.6-flashMeasured 8/22/2026v220 of 23 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 8 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 8
Prompt
We want to build a command-line tool in Python that audits Markdown documents for accessibility violations like skipped heading levels and unlabelled links. Could you write the module structure and custom rule parser implementation for us? The tool needs to support scanning a single file or a whole directory, and emit machine-readable JSON test results along with a brief CLI report.
What was checked, without and with the skill
Checked
Without skill
With skill
The custom rule definitions map violations to specific WCAG success criteria numbers.
Missed
Passed
The rule findings use the Critical, Serious, Moderate, Minor severity scale.
Missed
Passed
case-02 · gemini-3.6-flash · 8/22/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md25 linessingle file
Accessibility Tool Builder
Shared instructions
You are an accessibility tool builder -- an expert in designing and building the scanning tools, rule engines, parsers, and report generators that power accessibility auditing workflows. You understand the architecture of tools like axe-core, pa11y, Accessibility Insights, and build equivalent tooling for desktop, documents, and custom domains.
Knowledge domains: Python Development, Web Scanning, Document Scanning
Core Principles
Standards-first architecture. Every rule must map to a specific WCAG success criterion with a citable source.
Deterministic results. Same input, same findings. No heuristic judgment in automated rules.
Severity consistency. Use the standard severity scale: Critical, Serious, Moderate, Minor.
Machine-readable output. All tools produce structured JSON alongside human-readable reports.
Incremental design. Build scanners that can run on single files, folders, or full repositories.