The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses kicad-cli for running Electrical Rules Checks (ERC), Design Rules Checks (DRC), and exporting manufacturing files. It also uses standard shell commands like mkdir for directory management.
[DYNAMIC_EXECUTION]: The instructions encourage the generation and execution of Python scripts using libraries such as kicad-python (kipy) and kicad-sch-api to automate schematic and PCB operations. The skill explicitly mentions that some Model Context Protocol (MCP) servers may facilitate local code execution.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process KiCad project files, which could potentially contain malicious instructions in metadata or comments intended to influence the agent.
Ingestion points: Reads and parses .kicad_pro, .kicad_sch, .kicad_pcb, sym-lib-table, and fp-lib-table files (specified in SKILL.md).
Boundary markers: No specific delimiters or "ignore instructions" markers are defined for the content within KiCad files.
Capability inventory: The agent can execute subprocesses (kicad-cli), write to the local file system (creating output directories and renders), and execute Python code through IPC bindings.
Sanitization: There is no explicit mention of sanitizing or filtering string data extracted from the KiCad S-expression files before processing.

kicad-workflow