The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the Bash tool to invoke unity-cli for operations such as renaming GameObjects, modifying component properties, and deleting objects from the Unity hierarchy.
[DYNAMIC_EXECUTION]: The references/runtime-checklist.md file instructs the agent to use cargo run as a fallback method to execute the unity-cli tool if the binary is not found on the system PATH. This involves runtime compilation and execution of the source code present in the workspace.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and act upon data from Unity scenes (GameObjects, Tags, Layers, and Components), which represents an external input surface.
Ingestion points: Accessing and modifying Unity scene hierarchies and component fields using unity-cli (referenced in SKILL.md).
Boundary markers: No specific boundary markers or "ignore instructions" delimiters are implemented when processing scene data.
Capability inventory: The skill has access to command execution via Bash (including tool invocation and cargo run) and file system access through Read, Grep, and Glob (defined in the allowed-tools section of SKILL.md).
Sanitization: The instructions do not define sanitization or validation logic for the data retrieved from Unity scenes before it is processed by the agent.

unity-gameobject-edit