The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the subprocess module in scripts/gcode_tool.py to invoke local 3D slicer binaries (OrcaSlicer, PrusaSlicer, CuraEngine). This execution is performed using a list of arguments rather than a shell string, which mitigates command injection risks. The script restricts execution to a predefined set of supported backends found through specific name matching in the system PATH and standard application directories.
[SAFE_PRACTICES]: The skill enforces a secure workflow by requiring a dry-run step before any slicer execution, allowing the agent to verify the generated command. It also performs static validation on the generated G-code, checking for physical boundary violations and the presence of necessary safety commands (like temperature control) before the output is finalized.
[DATA_INGESTION]: The skill processes user-supplied 3D mesh files and JSON printer profiles. It employs standard libraries for parsing and includes thorough validation of configuration fields, ensuring that paths are absolute and point to existing files on disk, which prevents path traversal or unintended file access during the slicing process.

gcode