The Agent Skills Directory

[PROMPT_INJECTION]: The skill processes project source code and user input to identify and resolve contradictions in domain terminology. 1. Ingestion points: Reads local project files and user conversations (SKILL.md). 2. Boundary markers: The instructions do not define specific delimiters for separating code content from instructions. 3. Capability inventory: The skill is authorized to write to the foundation/glossary.md file. 4. Sanitization: No explicit sanitization or validation of the ingested code content is mentioned.
[COMMAND_EXECUTION]: The skill instructs the agent to cross-check the local codebase against domain definitions, which requires the use of platform-provided file-system tools to read and analyze source files.

dx-domain