The Agent Skills Directory

[DYNAMIC_EXECUTION]: The skill generates and validates executable content at runtime.
The script scripts/mx_fx.py uses the Python compile() function in the mash_set_python method to perform a syntax check on MASH node scripts. This is a functional requirement for providing scriptable automation in Maya.
[COMMAND_EXECUTION]: The skill interacts with the Maya application via command-based interfaces.
scripts/mx_fx.py frequently uses maya.mel.eval to execute operations such as creating nCloth nodes, collider generation, and triggering Arnold renders. This is standard practice for Maya-based automation.
[INDIRECT_PROMPT_INJECTION]: The skill processes external data that could potentially harbor malicious instructions.
Ingestion points: Mesh data from Maya scene objects, external Alembic (.abc) caches, VDB sequences, and USD files are loaded using AbcImport, aiVolume, and pxr.Usd.
Boundary markers: Absent; the skill does not explicitly use delimiters to separate simulation data from instructions.
Capability inventory: Command execution (mel.eval), dynamic code compilation (compile()), and file system writes (alembic_export, to_json).
Sanitization: Present; the skill implements domain-specific validation gates such as scale_report and cloth_topology_verdict which verify the integrity of input data before processing.

scenario-maya-fx