The Agent Skills Directory

[SAFE]: The skill is designed to manage domain-specific documentation within a repository. It reads existing context files and ADRs to ensure terminology consistency and updates them based on user input. These are standard operations for a development-focused AI assistant.
[PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it is instructed to read and interpret data from the user's codebase and documentation files.
Ingestion points: File exploration of the repository, specifically reading CONTEXT.md, CONTEXT-MAP.md, and files in docs/adr/ as specified in SKILL.md.
Boundary markers: None present; the skill does not explicitly use delimiters to separate instructions from the data it reads from the repository.
Capability inventory: The skill can read file structures, explore the codebase, and write or update markdown files (CONTEXT.md and ADRs).
Sanitization: No explicit sanitization or validation of the ingested repository content is performed before it is processed.

domain-model