The Agent Skills Directory

[SAFE]: The skill serves as a discoverability shim to guide the agent between analysis and rendering tasks. No suspicious command execution or network operations were identified.
[COMMAND_EXECUTION]: The documentation suggests a command-line invocation for a local script: node "${CLAUDE_PLUGIN_ROOT}/scripts/render.cjs" tour-spec.json. This uses the plugin's root environment variable to reference its own internal assets, which is standard behavior for this type of agent extension.
[PROMPT_INJECTION]: No attempts to override safety filters, bypass instructions, or extract system prompts were detected. The decision tree logic is purely functional for task routing.

learning-guide