The Agent Skills Directory

[SAFE]: The skill's primary purpose is to generate and update markdown-based product vision statements. All operations are confined to reading and writing documentation within standard project directories such as strategy/, vision/, and docs/.
[DATA_EXPOSURE]: No sensitive system paths, credentials, or environment variables are accessed. The skill specifies search locations for vision documents which are typical for project documentation.
[COMMAND_EXECUTION]: There are no shell commands, subprocess calls, or scripts executed by this skill. It relies entirely on natural language instructions for the agent to manipulate text files.
[EXTERNAL_DOWNLOADS]: The skill does not perform any network operations, download external content, or reference third-party scripts or packages.
[PROMPT_INJECTION]: The instructions do not contain attempts to override agent safety protocols, reveal system prompts, or bypass constraints. The logic for mode detection is focused on task-specific keywords.

vision-statement