The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill installs the super-prototyping-tools using uv tool install from the vendor's repository at github.com/ReScienceLab/super-prototyping. It also fetches SVG icons from unpkg.com for the @lobehub/icons-static-svg package.
[COMMAND_EXECUTION]: The skill uses shell commands to manage the project environment, such as configuring .gitignore and organizing directory structures for mockups and assets.
[DYNAMIC_EXECUTION]: The instructions guide the agent to generate and execute a Python script (gen.py) to automate the production of HTML artboards. This script is used for UI reconstruction and asset management.
[INDIRECT_PROMPT_INJECTION]: The skill possesses a vulnerability surface for indirect prompt injection.
Ingestion points: The skill processes external image data (screenshots) and third-party search results from the Mobbin MCP as detailed in SKILL.md.
Boundary markers: No specific boundary markers or instructions to ignore embedded content within ingested screenshots are identified.
Capability inventory: The skill environment allows for subprocess calls, file operations, and tool installations (uv, curl, python3).
Sanitization: No explicit logic for sanitizing or filtering ingested image content is defined, though the workflow is highly structured.

clone-prototype