The Agent Skills Directory

[NO_CODE]: The skill consists entirely of Markdown and YAML documentation. It does not contain scripts, binaries, or automated tooling that executes on the host system.
[COMMAND_EXECUTION]: The skill explicitly instructs the agent not to invent facts, edit product source, stage, commit, or push files without authorization. It emphasizes that business rules must remain independent of frameworks and deployment structures.
[DATA_EXFILTRATION]: No network-related commands (curl, wget) or external data transfer mechanisms are present. The ask-ai reference is described as a lightweight handoff for research and explicitly states it 'never implies sending' data externally.
[PROMPT_INJECTION]: The instructions focus on methodology and business logic. There are no patterns attempting to bypass safety filters or override system-level agent instructions.
[EXTERNAL_DOWNLOADS]: The skill does not reference or download any external dependencies, packages, or remote code.

domain-modeling