liranmao
- 3 skills
- 0 followers
- 18 hours ago last updated
- ▌ Paper Figure · liranmao bundleBuild submission-grade manuscript figures in Python or R from one shared style spec, for bioinformatics data (single-cell, spatial omics, histology, model benchmarks). Use when creating, restyling, or QA-ing a figure or panel for a paper, thesis, or preprint - including UMAP/embedding plots, expression heatmaps, image plates, forest/effect plots, and multi-panel composites. Triggers on "figure", "panel", "plot for the paper", "publication quality", "Nature figure", "journal figure", "figure legend", "export figure", "colorblind safe", "300/600 dpi".
- ▌ Make Basic Academic Slides · liranmao bundleCreate or revise concise academic PowerPoint presentations in a plain title-and-key-points style. Use when the user asks for a simple, basic, clean, non-decorative, or less AI-like PPT/PPTX; a paper, literature-review, PI, lab-meeting, or research presentation; or asks to remove cards, boxes, columns, timelines, icons, and decorative framing from slides.
- ▌ Prepare Pathologist Geojson · liranmao bundlePrepare a pathology-review handoff from an H&E image plus spatial, cellular, regional, mask-based, or model-derived annotations by registering coordinates to the image, converting annotation tables or existing polygons into one QuPath-compatible GeoJSON, embedding classification colors, validating alignment, and documenting how to share and import the files. Use when Codex needs to create an annotation overlay for a pathologist, convert CSV/TSV x-y labels or segmentation masks to GeoJSON, consolidate same-slide GeoJSON layers, or troubleshoot annotations that appear offset, scaled, flipped, or rotated over a whole-slide image.