The Agent Skills Directory

External API Connectivity: The skill is designed to communicate with an external endpoint at https://mcp.figma.com/mcp. This connection is used to fetch design context, screenshots, and assets from Figma, which is necessary for the skill's primary function.
Environment Variable Configuration: The reference documentation provides instructions for setting up a FIGMA_OAUTH_TOKEN. It suggests potentially persisting this token in shell profile files such as ~/.zshrc or ~/.bashrc. This is a common practice for CLI-based tools, and users should ensure their tokens are handled in accordance with their local security requirements.
Data Processing Surface: The skill processes design data retrieved from external Figma nodes (via get_design_context and get_metadata) to generate implementation code. This represents a potential surface for indirect prompt injection if the source design data contains unexpected instructions. The skill utilizes these tools to inform its code generation process.
Ingestion points: get_design_context, get_metadata, and get_screenshot fetch data from remote Figma layers (described in SKILL.md and references/figma-tools-and-prompts.md).
Boundary markers: No specific delimiters or "ignore instructions" markers are defined for the design data payload within the skill files.
Capability inventory: The skill is intended to help the agent generate code (React + Tailwind) based on design data, which the agent may then write to the local file system.
Sanitization: The skill does not explicitly define sanitization or filtering steps for the incoming design data.

figma