The Agent Skills Directory

[SAFE]: The skill's primary function is to manage project documentation, specifically domain glossaries (CONTEXT.md) and Architectural Decision Records (ADRs). It operates entirely within the scope of markdown file manipulation.
[INDIRECT_PROMPT_INJECTION]: The skill ingests user-provided domain terminology and architectural context to generate documentation. While this creates a potential surface for processing untrusted content, the skill lacks high-risk capabilities such as network access or shell execution, limiting the impact of potential injection to the project's documentation integrity. Ingestion points include user conversation and existing repository documentation; the capability inventory is restricted to file system operations for documentation files; no explicit sanitization is performed on user-supplied terms.

domain-modeling