The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to perform environment discovery by executing ls on common skill installation paths (e.g., ~/.claude/skills/, ~/.agent/skills/) to determine if companion skills are present.\n- [PROMPT_INJECTION]: Indirect Prompt Injection surface evaluation.\n
Ingestion points: The skill processes user-provided source code, HTML, and UI component implementations provided during accessibility audits.\n
Boundary markers: No explicit delimiters or instructions to ignore embedded content are defined for the processed user data.\n
Capability inventory: The skill can execute local directory listings (ls) and recommend the execution of installation commands (npx).\n
Sanitization: There is no specific evidence of sanitization or filtering for instructions that might be contained within the analyzed user code.\n- [EXTERNAL_DOWNLOADS]: The skill references and provides usage examples for standard accessibility auditing tools including axe-core, lighthouse, and jest-axe. It also provides instructions for adding companion skills via the npx skills add command using the vendor's repository.

accessibility-wcag