The Agent Skills Directory

[SAFE]: The skill provides instructions for a standard documentation maintenance workflow. Analysis of the instructions and required commands reveals no malicious intent, sensitive data access, or unauthorized network activity.
[INDIRECT_PROMPT_INJECTION]: The skill processes project documentation sources to generate output, which is a potential surface for indirect prompt injection if sources contain malicious instructions. \n- Ingestion points: Reads markdown and TypeScript source files from the ai-docs/src directory. \n- Boundary markers: No explicit instruction-ignoring delimiters are defined in the workflow. \n- Capability inventory: Executes project-level commands including pnpm ai-docgen and TypeScript validation via CLI. \n- Sanitization: Relies on the standard project-defined validation and generation pipeline.

ai-docs