agentsclimarketplace

Skimage otsu segmentation starter

Skill ma-compbio-lab/SkillFoundry/skills/imaging-and-phenotype-analysis/skimage-otsu-segmentation-starter

A framework for discovering, compiling, and validating reusable skills for scientific agents.

Install
npx -y skills add ma-compbio-lab/SkillFoundry --skill skimage-otsu-segmentation-starter

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

SKILL.md

1.1 KB, 254 tokens by cl100k_base, as published. Nobody here has run it

scikit-image Otsu Segmentation Starter

Use this skill to generate a deterministic toy microscopy-like image, segment bright objects with Otsu thresholding, and summarize labeled regions.

What it does

  • Creates a synthetic grayscale image with three bright disk-shaped objects.
  • Smooths the image, applies Otsu thresholding, removes tiny objects, and labels connected components.
  • Returns compact JSON with threshold, object count, and per-object measurements.

When to use it

  • You need a local imaging starter in an officially documented ecosystem.
  • You want a minimal segmentation baseline before moving to heavier microscopy pipelines.

Example

slurm/envs/scientific-python/bin/python skills/imaging-and-phenotype-analysis/skimage-otsu-segmentation-starter/scripts/run_skimage_otsu_segmentation.py \
  --out scratch/skimage/segmentation_summary.json

Verification

  • Skill-local tests: python3 -m unittest discover -s skills/imaging-and-phenotype-analysis/skimage-otsu-segmentation-starter/tests -p 'test_*.py'
  • Repository smoke: python3 -m unittest tests.smoke.test_frontier_domain_skills -v

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.