The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data in the form of 'source papers' and 'existing slides' provided by the user during the intake phase.
Ingestion points: Phase 0 and Phase 1 involve reading and extracting ideas from external PDFs or slides.
Boundary markers: The skill does not define specific delimiters or instructions to ignore potential commands embedded within the analyzed documents.
Capability inventory: The skill has access to the Bash, Write, and Edit tools, which are used to generate LaTeX source and execute compilation scripts.
Sanitization: No explicit sanitization or filtering of the content extracted from external papers is mentioned before it is used to structure the lecture.
[COMMAND_EXECUTION]: The skill uses the Bash tool to perform '3-pass compilation' and run 'R scripts' for figure generation. These commands are executed locally to produce the final lecture output.
[DYNAMIC_EXECUTION]: The workflow involves generating executable R scripts and LaTeX code based on the analyzed source materials, which are then processed by local compilers. This behavior is central to the skill's primary function of scaffolding and building lecture decks.

create-lecture