AI Skill MartBrowse skillsPromptsProgramsLearnWhat is a Skill?
 
← Back to list

histolab WSI Tile Extraction Assistant

A guided skill for using histolab to detect tissue, extract tiles, and normalize stains from whole slide pathology images.

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

What it does

  • Walks through opening gigapixel WSIs (.svs and friends) with histolab and inspecting properties, pyramid levels, and thumbnails.
  • Detects tissue with TissueMask / BiggestTissueBoxMask and picks the right tiler (RandomTiler, GridTiler, ScoreTiler) for the goal.
  • Covers deep-learning dataset prep: Macenko/Reinhard stain normalization, filter chains, locate_tiles() previews, and CSV tile reports.
  • Includes troubleshooting for no tiles extracted, too many background tiles, slow extraction, and artifact-laden tiles.

Who it's for

  • Medical-AI researchers and students building datasets from H&E slides.
  • Data engineers setting up a pathology image preprocessing pipeline for the first time.
  • Anyone needing quick slide QC or tissue-coverage statistics.

Example uses

  1. "Extract 100 random 512×512 tiles from slide.svs with a fixed seed" → produces RandomTiler config plus a preview step.
  2. "Cover the whole tissue with a grid at level 1 and write a CSV report" → GridTiler + reporting workflow.
  3. "Stain color varies across slides and hurts my model" → guidance on Macenko normalization and tuning tissue_percent for reproducibility.

· · · 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/histolab/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 AI Skill Mart.
Copy the skills/histolab folder from the GitHub repo K-Dense-AI/scientific-agent-skills into my ~/.claude/skills/histolab/.
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/histolab ~/.claude/skills/

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

  1. Install the OpenSlide system libraries first (macOS: brew install openslide; Ubuntu: sudo apt install openslide-tools). histolab 0.7.0 does not support Windows.
  2. In a Python 3.8–3.11 environment run pip install histolab (or uv pip install histolab); add pip install pooch for the built-in TCGA sample slides.
  3. Clone the repo: git clone https://github.com/K-Dense-AI/scientific-agent-skills.git.
  4. Create the skills folder: mkdir -p ~/.claude/skills.
  5. Copy the whole skill folder including references/: cp -r scientific-agent-skills/skills/histolab ~/.claude/skills/.
  6. Restart Claude Code and try a prompt like "use histolab to extract tiles from this WSI".
View source on GitHub ↗License: MIT