The Agent Skills Directory

[DYNAMIC_EXECUTION]: The skill generates and executes Python scripts using the mcp__blender__execute_blender_code tool to perform format-specific exports at runtime.
[INDIRECT_PROMPT_INJECTION]: The skill processes external data from Blender scenes (e.g., object names, scene metadata) that could be manipulated to influence the agent's behavior during script generation or file operations.
Ingestion points: Data retrieved via mcp__blender__get_scene_info and mcp__blender__get_object_info (SKILL.md).
Boundary markers: None present to separate scene data from instructional context.
Capability inventory: Access to Bash for file system operations and mcp__blender__execute_blender_code for Python execution.
Sanitization: The instructions do not specify sanitization or validation of data extracted from the Blender environment before use in tools.
[COMMAND_EXECUTION]: The skill documentation advises using the Bash tool to perform file system checks, such as verifying the existence and size of exported assets using ls -la.
[EXTERNAL_DOWNLOADS]: Includes references to external documentation and best practices from the Blender Foundation, the Khronos Group, and specialized 3D platforms (e.g., alpha3d.io, tripo3d.ai, fixie3d.com).

blender-export