The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to invoke the runcomfy command-line interface. This tool is used to send image editing requests to a remote API and handle the local storage of generated results.
[EXTERNAL_DOWNLOADS]: The skill requires the installation of the @runcomfy/cli package from the npm registry to function. It also manages the download of generated image assets from the runcomfy.net and runcomfy.com domains.
[PROMPT_INJECTION]: The skill is subject to indirect prompt injection risks as it processes external, potentially untrusted data to perform its primary tasks.
Ingestion points: The skill ingests user-provided text prompts and external image URLs (image_urls) that are fetched by the model server.
Boundary markers: The skill defines specific prompting templates (e.g., leading with preservation goals and ending with change requests) to structure model instructions.
Capability inventory: The skill has the capability to execute local CLI commands, perform network requests to the Model API, and download files to the local file system.
Sanitization: The documentation explicitly warns the user to treat external URLs as untrusted and identifies image-based prompt injection as a known risk for image-edit models.

nano-banana-edit