The Agent Skills Directory

[SAFE]: The skill provides structured instructions for scientific writing, referencing standard formats like IMRAD and common citation styles. All instructions are consistent with professional academic writing assistance.
[COMMAND_EXECUTION]: The skill instructs the agent to execute local Python scripts (scripts/generate_schematic.py, scripts/generate_image.py) and a LaTeX compiler (xelatex). These commands are task-appropriate for the generation of scientific schematics and the compilation of professional reports. The scripts referenced are internal to the skill's file structure.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process external research data retrieved via the research-lookup tool.
Ingestion points: Research data and citations are ingested from the research-lookup tool as described in the drafting workflow.
Boundary markers: The instructions do not specify explicit delimiters for the external content in the planning stage.
Capability inventory: The skill possesses capabilities for local script execution (python) and file compilation (xelatex).
Sanitization: No explicit sanitization or filtering of external data is defined in the text, relying on standard agent safety guardrails. This constitutes a standard research surface and does not indicate malicious intent.

scientific-writing