The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses gcloud and kubectl commands to perform infrastructure discovery. This is the primary function of the skill and is performed within the user's authenticated GCP context.
[COMMAND_EXECUTION]: The script scripts/render_architecture_png.py utilizes subprocess.run() to invoke the local Graphviz dot utility. The implementation uses a list-based argument structure (shell=False) and passes data via stdin, which is a secure practice that prevents shell injection vulnerabilities.
[SAFE]: The skill includes explicit instructions for maintaining a structured documentation cache in the workspace using JSON and Markdown files. It uses invoke_subagent to handle these tasks asynchronously, preventing blocking of the main conversation thread while performing long-running discovery operations.

gcp-architecture-discovery