The Agent Skills Directory

[COMMAND_EXECUTION]: The build process involves executing local CLI tools to process frontend assets.
The scripts/build.py script uses subprocess.run to call the tailwindcss CLI found within the project's node_modules directory.
It also uses the macOS sips utility for image resizing when building on Darwin systems.
[EXTERNAL_DOWNLOADS]: The skill fetches necessary presentation assets from well-known and trusted services.
scripts/build.py downloads CSS and font files from Google Fonts (fonts.googleapis.com).
It retrieves material design icon codepoints from Google's official GitHub repository (raw.githubusercontent.com/google/material-design-icons).
[DYNAMIC_EXECUTION]: The skill generates and executes code dynamically to facilitate the build and verification process.
scripts/build.py creates a temporary TypeScript configuration file that imports and executes the project's own Tailwind configuration.
scripts/shot.mjs utilizes the Playwright library to launch a Chromium instance and render the generated HTML file, executing the bundled JavaScript for verification.
[INDIRECT_PROMPT_INJECTION]: The skill acts as a processing engine for untrusted project files, which creates a potential surface for instructions embedded in source code to influence the agent.
Ingestion points: Reads all JSX, TSX, and CSS files within the user-specified frontend directory (SKILL.md, scripts/build.py).
Boundary markers: There are no specific boundary markers or instructions to the agent to ignore prompt-like content found within the source files.
Capability inventory: The skill can execute shell commands via subprocess.run, write files to the repository, and execute scripts in a browser environment via Playwright.
Sanitization: Source content is extracted as literal strings for the UI porting process without sanitization of potential AI instructions.

ui-snapshot