The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to use local shell commands such as find, grep, and git log to gather facts about the repository. These commands are used to identify existing models, migration frequency, and API patterns to inform the design process. The usage is restricted to local analysis and does not involve piping to remote shells or dangerous flags.
[SAFE]: The skill does not demonstrate any patterns of data exfiltration, credential harvesting, or remote code execution. It operates locally on the project files and generates documentation in designated directories as per its stated purpose. All identified behaviors align with legitimate development tool functionality.

spec