The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes a local Python utility, scripts/fingerprint.py, to calculate SHA-256 digests of markdown artifacts. This is a bundled resource used for internal content integrity verification.
[COMMAND_EXECUTION]: The skill performs Git operations, including repository status checks and committing changes to artifacts. These actions are scoped to the project repository and are intended for workflow management.
[INDIRECT_PROMPT_INJECTION]: The skill has a data ingestion surface as it processes user input from interviews to generate intent.md files.
Ingestion points: User interview process described in SKILL.md Step 1.
Boundary markers: Instructions specify that user wording for outcomes and constraints must be preserved as requirements rather than optional details.
Capability inventory: File writing (intent.md), Git commits, and execution of the local fingerprint.py script.
Sanitization: No explicit sanitization of user input is performed before writing to the markdown file.

sdlc-plan