The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to use standard system utilities such as git and sed to retrieve project metadata, commit history, and specific code segments for analysis. It also references the execution of local scripts (e.g., node bin/archify.mjs) associated with auxiliary developer tools to generate visualizations.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process external data sources including conversation history and project files. It mitigates potential injection risks by explicitly directing the agent to treat this content as source data for analysis rather than as a source of new operational instructions, and by enforcing strict output formatting rules.

explain