The Agent Skills Directory

[SAFE]: The skill operates strictly within the documentation scope of the project, focusing on creating and updating files in the docs/specs/user-stories/ and docs/specs/technical-docs/ directories.
[SAFE]: No network operations, external downloads, or execution of untrusted code were detected. The skill delegates specific tasks (task planning) to an internal sub-skill (/story-plan) rather than executing logic directly.
[SAFE]: The instructions emphasize user validation and explicitly warn against 'inventing' data, which reduces the risk of the agent hallucinating or generating unauthorized content.
[PROMPT_INJECTION]: The skill has a standard operational surface for indirect prompt injection (Category 8) as it processes user requirements into repository files.
Ingestion points: Processes user-provided functional descriptions and existing Markdown files in the docs/ folder.
Boundary markers: No specific delimiters or safety instructions are defined for processing user input strings into the templates.
Capability inventory: File system write access restricted to documentation directories; delegation to the internal /story-plan skill.
Sanitization: No explicit sanitization or filtering of user-provided input is performed before writing to Markdown files. This is considered a low-risk, standard operational characteristic for documentation agents.

story-define