The Agent Skills Directory

[SAFE]: The skill performs routine local file management tasks, such as updating state files and markdown logs, to track project progress. All operations are confined to the local filesystem and the skill's designated state directory.
[INDIRECT_PROMPT_INJECTION]: The skill processes project-related data and task descriptions to generate summaries. While this involves ingesting data from files, the skill lacks high-risk capabilities such as network access or command execution, and the operations are restricted to documentation and state updates.

daily-review