The Agent Skills Directory

[SAFE]: The skill's functionality is restricted to local file system operations within a user-provided game project directory. It generates pixel art sprites as code textures (using a PixelRenderer.js utility) rather than downloading external assets.
[INDIRECT_PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection due to its requirement to read and process local project files.
Ingestion points: Instructions specify reading package.json, src/core/Constants.js, and all files matching src/entities/*.js in the target project.
Boundary markers: There are no explicit markers or instructions to isolate the ingested file content from the agent's command context.
Capability inventory: The skill creates multiple new files (e.g., src/core/PixelRenderer.js, src/sprites/player.js) and modifies existing entity constructors to replace shape-drawing calls with sprite-rendering calls.
Sanitization: No sanitization or validation logic is defined for the content extracted from the project files during the audit phase.
[COMMAND_EXECUTION]: The skill suggests running npm run build and /game-creator:qa-game as part of the verification process. These are standard development workflows for verifying code changes and updating visual regression snapshots in a game engine environment.

add-assets