The Agent Skills Directory

[SAFE]: The skill facilitates a structured interview to generate research documentation. Its activities, including reading profile data and writing specifications to the project directory, are consistent with its stated purpose.
[COMMAND_EXECUTION]: The skill utilizes Read, Write, and Edit tools to access context files (.context/profile.md, .context/projects/_index.md) and save the resulting research specification documents. These operations are limited to the local environment and the project's scope.
[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data via $ARGUMENTS and local context files to drive the interview phases.
Ingestion points: $ARGUMENTS, .context/profile.md, .context/projects/_index.md.
Boundary markers: None identified.
Capability inventory: Read, Write, Edit file system tools.
Sanitization: No explicit sanitization of input data is defined before interpolation into the agent's prompts. While this presents a theoretical attack surface, the context of a research interview and the structured document output minimizes the practical risk.

interview-me