The Agent Skills Directory

[SAFE]: The skill defines a purely conceptual analysis workflow for structural explanation. It contains no executable scripts or commands that pose a security risk.
[COMMAND_EXECUTION]: The skill includes a 'Codebase Analysis Mode' that utilizes standard tools like Grep and Read to inspect local files. These are used strictly for analysis and do not involve shell injection or unsafe argument passing.
[EXTERNAL_DOWNLOADS]: The skill metadata references a GitHub repository (github.com/jacob-balslev/skill-graph) for version tracking and source attribution. This is a neutral reference to the author's own repository and does not involve automated downloads or runtime execution.
[DATA_EXFILTRATION]: No network tools are requested or used. The workflow is designed for local explanation without sending data to external endpoints.

semantic-center