The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external project sources including tickets, UI components, API schemas, and documentation to refine the domain model. * Ingestion points: The Modeling Loop identifies project docs, tickets, UI, APIs, and code as sources for term extraction. * Boundary markers: There are no explicit instructions to use delimiters or ignore embedded instructions when reading untrusted project data. * Capability inventory: The skill allows the agent to read the codebase and write to project documentation files (CONTEXT.md, ADRs). * Sanitization: No content validation or sanitization routines are specified for external project data.

domain-modeling