The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill's default template (assets/reference-architecture-spec.html) incorporates resources from well-known services, specifically Tailwind CSS via CDN (https://cdn.tailwindcss.com) and Google Fonts (fonts.googleapis.com, fonts.gstatic.com). These are standard industry practices for frontend development.
[COMMAND_EXECUTION]: The workflow includes a verification step that mentions the use of browser automation tools such as browser-verify or Playwright. The skill explicitly instructs the agent not to run these tools or start local servers without the user's explicit choice and confirmation.
[PROMPT_INJECTION]: The skill is designed to ingest and process external technical data, which represents a surface for indirect prompt injection.
Ingestion points: Reads technical specifications, repository code, pull request descriptions, and system architectures from the agent's context as defined in SKILL.md.
Boundary markers: The instructions do not define specific delimiters or 'ignore' warnings for the ingested data.
Capability inventory: The agent can generate HTML artifacts and potentially use browser automation tools for verification (subject to user consent).
Sanitization: There are no explicit instructions for sanitizing or validating the contents of the external source material before it is processed into the visual explainer.

explain-visually