The Agent Skills Directory

[COMMAND_EXECUTION]: The skill generates and executes Python scripts via uv run for data analysis. This is the intended primary function and follows modern standards (PEP 723) for reproducible environments.
[EXTERNAL_DOWNLOADS]: Utilizes the uv package manager to fetch dependencies from standard registries.
[PROMPT_INJECTION]: Processes external data files which could contain malicious instructions (Indirect Prompt Injection). The skill mitigates this through a 'human-in-the-loop' design, requiring the agent to explain intent and obtain user confirmation for every action.

scientific-eda