The Agent Skills Directory

[SAFE]: The skill instructions focus on refining project documentation (Glossary and ADRs) and identifying terminology conflicts. It operates entirely within the project's own file structure.
[SAFE]: No network operations, sensitive file access (such as credentials or SSH keys), or remote code execution patterns were detected in the instructions or templates.
[INDIRECT_PROMPT_INJECTION]: The skill has an attack surface related to processing untrusted project data, though the risk is negligible as it only produces markdown documentation.
Ingestion points: The skill reads project source code from the src/ directory and existing markdown files (GLOSSARY.md, GLOSSARY-MAP.md, and docs/adr/*.md).
Boundary markers: There are no explicit delimiters or safety instructions provided to the agent to distinguish between code content and logic when processing files.
Capability inventory: The skill is designed to read file contents for analysis and write markdown documentation to the project repository.
Sanitization: The instructions do not specify sanitization or validation steps for content extracted from source code before it is written into documentation files.

domain-modeling