pathml

Full-featured computational pathology toolkit. Use for advanced WSI analysis including multiplexed immunofluorescence (CODEX, Vectra), nucleus segmentation, tissue graph construction, and ML model training on pathology data. Supports 160+ slide formats. For simple tile extraction from H&E slides, histolab may be simpler.

2.74x

Quality

67%

Does it follow best practices?

Impact

96%

2.74x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./scientific-skills/pathml/SKILL.md

Evaluation results

90%

75%

Multi-Site H&E Slide Preprocessing Pipeline

H&E preprocessing pipeline

Criteria

Without context

With context

QC first in pipeline

10%

100%

Noise reduction before tissue detect

100%

Tissue mask for stain normalization

100%

TissueDetectionHE before StainNormalization

37%

100%

Stain normalization method chosen

37%

100%

Morphological mask cleanup

50%

100%

Overlapping tiles for segmentation

Pyramid level selection

100%

SlideDataset for batch processing

100%

Dask distributed processing

100%

HDF5 output

40%

100%

44%

Tumor Microenvironment Spatial Proteomics Analysis

CODEX multiparametric workflow

Criteria

Without context

With context

CODEXSlide class

100%

CODEXSlide stain parameter

100%

CollapseRunsCODEX in pipeline

100%

CollapseRunsCODEX z_slice

100%

CollapseRunsCODEX method

40%

100%

SegmentMIF after CollapseRunsCODEX

100%

Mesmer model specified

100%

image_resolution parameter

100%

Cytoplasm channel choice

100%

QuantifyMIF after SegmentMIF

100%

AnnData output format

100%

Spatial coordinates in AnnData

100%

Multi-slide AnnData concatenation

100%

65%

Nucleus Detection Model Training and Production Deployment

HoVer-Net training and ONNX deployment

Criteria

Without context

With context

HoVerNet class used

100%

Pretrained initialization

50%

100%

NP branch uses BCE

100%

HV branch uses MSE

100%

NC branch uses CE

100%

NC loss weighted 2x

100%

hovernet_postprocess used

100%

AJI metric

100%

Panoptic Quality metric

37%

100%

ONNX export opset version

100%

ONNX dynamic axes

100%

Repository: K-Dense-AI/claude-scientific-skills
Commit: b58ad7e

Evaluated: 27 days ago
Agent: Claude Code
Model: Claude Sonnet 4.6

Table of Contents

Multi-Site H&E Slide Preprocessing Pipeline Tumor Microenvironment Spatial Proteomics Analysis Nucleus Detection Model Training and Production Deployment

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.