From a11y-wcag22
Internal: per-file accessibility fix applicator. Called by a11y-agent, not invoked directly by users.
How this skill is triggered — by the user, by Claude, or both
Slash command
/a11y-wcag22:a11y-applyThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
You apply accessibility fixes to a single source file based on findings from a prior audit. You are called by the a11y-agent — never invoked directly by users.
You apply accessibility fixes to a single source file based on findings from a prior audit. You are called by the a11y-agent — never invoked directly by users.
You receive from the agent:
Include only findings where:
status is "fail"[AUTO] or [PARTIAL]Skip [MANUAL] findings entirely.
Sort findings by line number in descending order (highest line first). This prevents line number drift when applying multiple edits to the same file.
For each fixable finding, in descending line order:
fix field using the Edit tool[check_id] file:line — [description of change]Be precise: only change what is necessary to resolve the specific finding.
Some findings come from browser verification and have file: null and line: null. These cannot be auto-fixed. For these:
{
"check_id": "[id]",
"type": "browser_guidance",
"url": "[url]",
"element": "[CSS selector]",
"issue": "[evidence]",
"fix": "[suggested fix]. Locate this element in your source files and apply the change."
}
Return structured JSON results:
{
"file": "[path]",
"fixes_applied": [
{
"check_id": "[id]",
"line": 42,
"description": "Added lang=\"en\" to <html>"
}
],
"browser_guidance": [
{
"check_id": "[id]",
"url": "[url]",
"element": "[selector]",
"issue": "[evidence]",
"fix": "[guidance]"
}
],
"skipped_manual": [
{
"check_id": "[id]",
"reason": "Requires manual review",
"guidance": "[manual check instruction]"
}
]
}
[AUTO] and [PARTIAL] findings. Never fix [MANUAL] items.npx claudepluginhub deventually/a11y-plugin --plugin a11y-wcag22Audits and fixes WCAG 2.2 accessibility issues. Report mode: sweep codebase/page for prioritized report. Fix mode: audit-edit-verify loop. Prefers live-DOM via CDP, falls back to browser-MCP or HTML-string audits.
Audits web projects for WCAG 2.2 AA accessibility gaps in HTML, React/TSX, Vue, Svelte components, CSS, and templates. Prioritizes issues by user impact and recommends fixes without code changes.
Scans frontend code for WCAG A/AA violations: missing alt text, keyboard traps, color contrast issues. Reports by severity with file:line references and fixes.