The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes shell commands to compile LaTeX documents and execute data processing scripts (R, Python). These actions are limited by the environment's allowed-tools configuration.
[DYNAMIC_EXECUTION]: The skill generates and executes R and Python scripts at runtime to create presentation figures, ensuring reproducibility of visual assets.
[INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied project files to generate content, which represents a potential surface for indirect prompt injection. * Ingestion points: Phase 1 gathers context from project files. * Boundary markers: No explicit delimiters are used to separate external content. * Capability inventory: Includes file system write access and shell execution. * Sanitization: No explicit sanitization of input text is performed.

beamer-deck