The Agent Skills Directory

[COMMAND_EXECUTION]: The script scripts/generate_schematic.py invokes the internal logic in scripts/generate_schematic_ai.py using subprocess.run(). This call is implemented using an argument list rather than a raw shell string, which is a secure implementation that effectively mitigates command injection risks.
[EXTERNAL_DOWNLOADS]: The skill performs network requests to the OpenRouter API to access Google's Gemini models for both image generation and quality review. These interactions target well-known and reputable services necessary for the skill's primary functionality.
[PROMPT_INJECTION]: The skill ingests user-supplied text as a diagram description. It uses the SCIENTIFIC_DIAGRAM_GUIDELINES template in scripts/generate_schematic_ai.py as a boundary marker, wrapping the untrusted user input within a strict framework of technical requirements to ensure the model produces valid scientific content.
[SAFE]: The skill manages API credentials through standard environment variables and .env files. No hardcoded secrets, sensitive file access patterns, or obfuscation techniques were detected during the analysis.

scientific-schematics