Icarus-Figures
SkillSelf-contained Claude skill for generating publication-grade scientific figures using matplotlib and TikZ with journal-grade composition standards.
git clone https://github.com/TAO-QKV/Icarus-FiguresTurn "a dataset + a claim" into a publication-grade figure — the kind a top-journal editor accepts with no revision request. Icarus Figures is a self-contained Claude/Codex skill: reproducible matplotlib/seaborn plots for data figures, and original TikZ for hero/method figures.
The point is not "many chart thumbnails"; it is complex paper figures with hierarchy, insets, cross-panel evidence, and honest uncertainty.
Complex biomedical evidence panel - a single integrated figure with a hero response manifold, decision field, calibration/ROC diagnostics, volcano + Manhattan omics evidence, imaging plate, survival validation, forest plot, covariance heatmap, and mechanism graph (`examples/complex_panels.py`):
Complex spatial-physical evidence panel - field + streamline + trajectory + sensors as the hero panel, with response surface, spectrum, time-series uncertainty, QQ residual check, phase portrait, anomaly zoom, and registered imaging readouts:
- Source
- community
- Known advisories
- 0
- Maintenance
- maintained
- License
- MIT
- Age
- 4 months