The Agent Skills Directory

[COMMAND_EXECUTION]: The skill provides instructions to execute several local Python scripts (scripts/generate_schematic.py, scripts/query_template.py, scripts/customize_template.py, scripts/validate_format.py) that accept user-provided strings as command-line arguments. This represents a standard capability for the skill's intended purpose of document automation.
[EXTERNAL_DOWNLOADS]: The skill references external documentation and guidelines from well-known and trusted organizations, including Nature Portfolio (nature.com), the Science family (science.org), PLOS (plos.org), Cell Press (cell.com), and federal agencies like the NSF (nsf.gov) and NIH (grants.nih.gov). These references are informative and point to official repositories of academic standards.
[PROMPT_INJECTION]: The skill contains an indirect prompt injection surface through its automated diagram generation and template customization features.
Ingestion points: User-provided natural language descriptions for scientific diagrams via scripts/generate_schematic.py and metadata fields (title, authors) via scripts/customize_template.py.
Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the command-line usage examples.
Capability inventory: The skill performs file system write operations to the figures/ directory and creates new LaTeX (.tex) files. It also utilizes system tools like pdflatex and latexmk for document compilation.
Sanitization: The documentation does not specify internal sanitization or validation routines for the user-supplied strings before they are passed to the CLI scripts.

venue-templates