The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute local Python scripts to facilitate research scoring and diagram generation.
Evidence: python scripts/generate_schematic.py "your diagram description" -o figures/output.png and python scripts/calculate_scores.py --scores <dimension_scores.json> --output <report.txt>.
These scripts are part of the skill's local directory and are intended for the primary purpose of visualizing and aggregating research evaluation data.
[PROMPT_INJECTION]: The skill processes untrusted research documents, creating an attack surface for indirect prompt injection.
Ingestion points: External research papers, proposals, abstracts, and literature reviews provided by the user (SKILL.md).
Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded prompts within the documents being evaluated.
Capability inventory: Local script execution and file writing to the figures/ directory and report files.
Sanitization: No explicit sanitization or validation of the input scholarly text is described prior to processing or script execution.

scholar-evaluation