The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to process external, untrusted content like user notes and highlights, which could contain adversarial instructions intended to influence the agent's behavior during the interview or synthesis phase. 1. Ingestion points: The skill reviews source material provided by the user or fetched by an upstream skill, including highlights, notes, bullet points, outlines, or drafts, as defined in the Ingestion & Topic Framing section. 2. Boundary markers: The instructions do not specify any delimiters or special handling to distinguish user-provided data from agent instructions. 3. Capability inventory: The skill is limited to conversational interaction and text synthesis; it requests no tool permissions and contains no scripts or binaries. 4. Sanitization: There are no explicit sanitization, filtering, or validation steps defined for the ingested content.
[NO_CODE]: The skill consists entirely of natural language instructions in a markdown file and does not include any executable scripts, binaries, or package dependencies.

interviewer