The Agent Skills Directory

[SAFE]: The skill acts as a high-level instructional framework, guiding the agent on how to synthesize information from other analysis skills ('how', 'why', and 'unslop') into user-friendly explanations. It focuses on pedagogical structure and communication style.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process external technical data, creating a potential surface for indirect prompt injection.
Ingestion points: The agent reads and analyzes external source code, git diffs, and subsystem documentation provided in the conversation or repository context.
Boundary markers: The instructions do not define specific delimiters or warnings for the agent to distinguish between its instructions and instructions potentially embedded in the data being analyzed.
Capability inventory: The skill orchestrates other internal analysis skills, reads file contents, and utilizes an image-generation tool to create diagrams.
Sanitization: There are no explicit sanitization steps described to filter or escape instructions found within the processed technical documentation or source code.

teach