The Agent Skills Directory

[DYNAMIC_EXECUTION]: The skill involves the dynamic generation and execution of code strings through the use_figma tool. This is a functional requirement for interacting with the Figma API to place SVGs, update node properties, and manage the canvas structure based on design catalog data.
[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from local repository files, creating a surface for potential indirect prompt injection. * Ingestion points: catalog.json, .design-parity.json, and design-map.json (SKILL.md). * Boundary markers: No explicit delimiters or instructions to ignore embedded content are documented for the ingested JSON data. * Capability inventory: use_figma (code execution), upload_assets (file upload), and get_metadata (file and Figma metadata access). * Sanitization: No specific validation or sanitization logic for the ingested fields is described in the provided instructions.
[EXTERNAL_DOWNLOADS]: The skill references external resources, including a Figma plugin zip and GitHub repositories for the design-parity and compose-ai-tools projects. As these resources are owned by the skill author (yschimke) and hosted on well-known platforms, they are documented as safe vendor-related resources.

figma-catalog-import