The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses platform-specific commands to open generated HTML files in the default browser: open for macOS, xdg-open for Linux, and start for Windows. This is standard behavior for presenting content to the user.
[COMMAND_EXECUTION]: The skill invokes python3 to run extraction scripts for PowerPoint files, which is a routine operation for its conversion functionality.
[EXTERNAL_DOWNLOADS]: The skill requests the installation of the python-pptx library from the standard Python Package Index (PyPI) to handle slide conversion tasks.
[PROMPT_INJECTION]: The skill processes untrusted external data by ingesting user-supplied notes and content from .ppt or .pptx files. While it lacks explicit boundary markers or sanitization for this data, the risk is minimal and inherent to the task of content conversion.
Ingestion points: Reads text and images from user-uploaded .ppt/.pptx files and accepts text drafts (SKILL.md).
Boundary markers: None identified; external content is processed directly for slide generation.
Capability inventory: Executes shell commands for opening files and runs Python scripts for data processing (SKILL.md).
Sanitization: No specific sanitization or filtering of the ingested slide content is described.

frontend-slides