The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructions specify the installation of a core dependency using the command npx skills add suzheng/k2f. This resource is maintained by the same author and is required for the syllabus generation workflow.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data, including catalog descriptions, outlines, and legacy syllabi.
Ingestion points: User-provided prompts, outlines, and legacy syllabi as described in the workflow section of SKILL.md.
Boundary markers: The instructions do not define specific delimiters or guardrails to isolate user-supplied content from the agent's internal logic.
Capability inventory: The skill involves generating semantic blueprints (content_and_design.md) and interacting with the k2f engine to pack, verify, and export files to PDF format.
Sanitization: The instructions mandate that user-supplied policy text be included "verbatim," which provides a surface for embedded instructions in legacy data to influence the agent's output or behavior during the drafting process.

k2f-syllabus