The Agent Skills Directory

[SAFE]: The skill consists entirely of static Markdown files intended to guide an AI agent in writing product specifications, PRDs, and user stories. No malicious patterns or behaviors were detected.
[NO_CODE]: Analysis of the 11 provided files confirms there are no executable scripts (e.g., .py, .js, .sh), no package management configurations (e.g., requirements.txt, package.json), and no binary executables.
[DATA_EXFILTRATION]: There are no commands or instructions that access sensitive local files or perform network operations to external domains.
[PROMPT_INJECTION]: The content contains standard instructional language for requirements engineering and does not attempt to bypass safety filters or override the agent's core behavioral constraints.
[COMMAND_EXECUTION]: No shell commands, subprocess calls, or dynamic context injection patterns (such as !command syntax) are present in the skill files.

specification-techniques