The Agent Skills Directory

[SAFE]: The skill is designed for local operations and does not require network access to process files. It utilizes standard Python libraries and repository-provided scripts to perform document conversion tasks.
[COMMAND_EXECUTION]: The skill provides instructions for executing local Python scripts (scripts/validate_skill.py, tools/extract_pdf_figures.py, and tools/build_cell_reports_ppt_offline.py) and uses py_compile for script validation. These commands are directly related to the skill's stated purpose.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted PDF documents, representing an indirect injection attack surface.
Ingestion points: External PDF files provided as source material for the extract_pdf_figures.py script.
Boundary markers: The workflow is explicitly documented as 'offline' and 'bounded', which helps mitigate risks associated with untrusted content.
Capability inventory: File system access for reading PDFs and writing to an output directory, along with execution of local Python scripts.
Sanitization: The skill relies on structured library interfaces (e.g., python-pptx) for generating deliverables, though specific input sanitization for extracted PDF text is not detailed.

pdf-to-ppt-pack