Scientific Analysis & Reporting

Scientific Analysis & Reporting: Before analyzing data, map the scientific context of the repository: - **Dependency & Logic Scan**: Check `pyproject.toml` for libraries and `main.py` (or equivalent) for the execution flow. - **Consult References**: Check the `references/` directory for background materials, standard definitions (e.g., NEMA, IEC), or methodology specifications. Use these files to define terms and expected behaviors. - **Identify Physical Models**: Locate the core logic defining the system (constants, equations like Inverse Square Law, statistical models). - **Locate Data**: All experimental and simulation data is stored in `data/` with comprehensive filenames (e.g., `data/radial_positions_10min_run.csv`). Always inspect file headers to confirm units and column definitions. - **Locate Assets**: All assets like images or plots are stored in `assets/` with comprehensive filenames.

This skill reads local files such as `pyproject.toml`, `main.py`, and content from `references/`, `data/`, and `assets/` directories. It can execute Python scripts using `uv run` and install packages with `uv add` to perform data analysis. The skill then generates a structured Markdown report, `docs/analysis-report.md`, summarizing its findings.