The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill utilizes npx to download and execute the @useclawlink/cli package from the NPM registry. This package is an official tool provided by the vendor.
[COMMAND_EXECUTION]: The skill directs the agent to execute shell commands to manage Figma authentication and design tasks such as downloading assets and converting tokens.
[INDIRECT_PROMPT_INJECTION]: The skill processes data from external Figma design files, which presents a surface for instructions hidden within design content to influence the agent.
Ingestion points: Design file content and tokens retrieved via the figma_extract_design_tokens action (SKILL.md).
Boundary markers: No specific delimiters or instructions to disregard potential commands in design files are provided.
Capability inventory: The agent has the ability to run shell commands and write back to Figma through comments and webhooks (SKILL.md).
Sanitization: No description of data sanitization or content validation is included in the skill.

figma