Claude Skill MartBrowse skillsQuick linesLearn by videoTerminal guideWhat is a Skill?
 
← Back to list

PathML Computational Pathology Workflow

A research-only skill for using PathML 3.0.5 to tile slides, build preprocessing/QC pipelines, quantify multiplex images, construct spatial graphs, and plan bounded local inference.

Data & AnalyticsAdvanced★ 33,030⑂ 3,248AI score 8/10Last updated: Aug 9, 2026

What it does

  • Gives a reproducible install path: uv + Python 3.11, pathml==3.0.5, plus native prerequisites for OpenSlide, BLAS/LAPACK, and Java/Bio-Formats.
  • Provides stable-API code (HESlide, Pipeline, SlideData.run()) and explicitly warns against APIs that do not exist in 3.0.5.
  • Lays out an 8-step research workflow: local inventory, patient-level split freezing, resource bounds, pilot preprocessing, coordinate-preserving runs, spatial data construction, batched inference, provenance reporting.
  • Ships local CLIs for manifest validation, tile/RAM planning, image QC, spatial schema validation, and inference planning — all offline and dependency-free.
  • Enforces safety rules: PHI de-identification, no-network default with explicit consent gates for Hugging Face/Zenodo downloads, pickle/.pt checkpoint warnings, ONNX checksum verification.

Who it's for

  • Computational pathology researchers and grad students working with whole-slide images or CODEX/Vectra multiplex data.
  • Bioimaging engineers who must operate under institutional data-use and de-identification policy.
  • ML teams that need leakage-free splits and reproducible provenance for pathology models.

Example uses

  1. "Run tissue detection + blur on this .svs and write an .h5path" → produces stable-API code with tile size/stride 512 at level 0.
  2. "How many tiles and how much RAM for a 100000×80000 slide at 512px?" → runs scripts/plan_pipeline.py and returns a bounded plan.
  3. "Check whether my cells.csv and graph.json match the expected schema" → uses validate_spatial_schema.py to verify channel order and node-feature alignment.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/K-Dense-AI/scientific-agent-skills/HEAD/skills/pathml/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the skills/pathml folder from the GitHub repo K-Dense-AI/scientific-agent-skills into my ~/.claude/skills/pathml/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/K-Dense-AI/scientific-agent-skills.git && mkdir -p ~/.claude/skills && cp -r scientific-agent-skills/skills/pathml ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal and cd into the folder where you keep source checkouts.
  2. Clone the repo: git clone https://github.com/K-Dense-AI/scientific-agent-skills.git
  3. Create the skills directory: mkdir -p ~/.claude/skills
  4. Copy just this skill: cp -r scientific-agent-skills/skills/pathml ~/.claude/skills/
  5. Confirm ~/.claude/skills/pathml/SKILL.md exists along with the references/ and scripts/ folders.
  6. Restart Claude Code and try a prompt like "Build a PathML preprocessing pipeline for this slide".
  7. Before real runs, install the native prerequisites (OpenSlide, JDK 17, BLAS/LAPACK) and uv pip install "pathml==3.0.5" inside a Python 3.11 virtual environment.
View source on GitHub ↗License: MIT