The Agent Skills Directory

[SAFE]: The skill is designed for product discovery and sprint planning, providing structured templates for specification documents and task registries. All operations are local to the project workspace.
[SAFE]: File system operations are restricted to searching, reading, and writing Markdown files in common project documentation directories (e.g., specs/, planning/).
[INDIRECT_PROMPT_INJECTION]: The skill processes user-provided product plans and existing specification files, which constitutes a potential attack surface.
Ingestion points: Processes rough product ideas, technical concerns, and existing specification files in Interview Mode and Sprint Breakdown Mode.
Boundary markers: The instructions do not define explicit delimiters or 'ignore' warnings for the data being shaped.
Capability inventory: The skill's capabilities are limited to file system read/write operations for documentation purposes. It lacks network access, command execution, or dynamic code evaluation tools.
Sanitization: There is no explicit validation or escaping of the ingested product content. However, since the primary use case is content transformation for project planning, the risk is negligible.

spec-shaping