figures

Publication-quality figures plugin. Seven skills + one QA agent. scientific-figure: svgutils composer with pre-export font-size validation against Nature/Science/Cell/PNAS minima and Inkscape/cairosvg export. transparent-icons: flat scientific icons via Codex CLI or OpenAI Images API with Pillow-threshold or rembg/BiRefNet transparency post-process. svg-figure: hand-authored or programmatic SVG schematics with text-alignment, arrow-pattern, and palette-compliance guidelines, plus an Illustrator/Affinity editor-handoff reference and the editor_prep.py handoff pass. svg-primitives: mm-precise SVG builder in Python; auto-fits text boxes from measured font metrics, snaps arrow endpoints to box edges via svgpathtools intersection, emits <marker orient='auto'> for tangent-correct arrowheads on curves and orthogonal turns, supports straight/cubic/orthogonal-h/orthogonal-v routing plus multi-waypoint paths and rounded corners, and ships Bracket/Annotation/Group primitives. ai-full-figure: AI-generated pictorial substrate plus programmatic label/arrow/scale-bar overlay; hard-ceiling rules route complex figures back to scientific-figure or svg-figure. plot-styling: library decision tree (matplotlib / seaborn / plotnine / plotly / PyVista) with SciencePlots recipes for Nature, IEEE, Science, Cell, PNAS, APS. figure-qa agent: type-dispatching QA across SVG / raster / plot-script / composed-figure inputs with strict programmatic-vs-VLM separation.