Summary
This teaches Claude how to work with GitHub's official accessibility scanner action, which runs axe-core against live URLs in CI and files issues for each violation. You'd use this when a repo has the scanner configured and you want Claude to parse those auto-generated issues, correlate them with local scan results for confidence boosting, or track which ones Copilot has been assigned to fix. The skill maps scanner severity levels to agent scoring, explains the cache-based delta detection (new, fixed, persistent), and shows how to detect scanner presence by grepping workflows. Solid integration pattern if you're running accessibility checks in both CI and development.
Install to Claude Code
npx -y skills add community-access/accessibility-agents --skill github-a11y-scanner --agent claude-codeInstalls into .claude/skills of the current project.
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
Files
SKILL.md
Select a file.
Featured
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
