histolab

Lightweight WSI tile extraction and preprocessing. Use for basic slide processing, tissue detection, tile extraction, and stain normalization for H&E images. Best for simple pipelines, dataset preparation, and quick tile-based analysis. For advanced spatial proteomics, multiplexed imaging, or deep learning pipelines use pathml.

Quality

89%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

86%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, highly actionable skill body with executable quick-start code and clean one-level-deep progressive disclosure to real reference files. The main improvement is removing the duplicate reference summaries and adding an explicit validate/retry loop to the batch extraction workflow.

Suggestions

Collapse the per-file bullet summaries in the Resources section into a single terse index, since Core Capabilities already introduces and links each reference file.

Add an inline validation feedback loop to the Quick Start (e.g. preview with locate_tiles, adjust tissue_percent/mask if preview is mostly background, then extract) to satisfy the batch-operation validation expectation.

Trim the Overview paragraph, which restates capabilities already enumerated in the Core Capabilities list.

Dimension	Reasoning	Score
Conciseness	Mostly efficient actionable bullets and copy-paste code, but the Resources section re-summarizes the contents of each reference file after Core Capabilities already links to them, a minor redundancy that could be trimmed.	4 / 5
Actionability	Fully executable Quick Start with copy-paste Python, concrete install commands, and specific API names (RandomTiler, NucleiScorer, locate_tiles, tissue_percent, MacenkoStainNormalizer) throughout Best Practices, Use Cases, and Troubleshooting.	5 / 5
Workflow Clarity	Clear load → configure → preview → extract sequence with a preview checkpoint reinforced by 'Always preview with locate_tiles() before extracting', but there is no inline validate-then-retry feedback loop in the main workflow.	4 / 5
Progressive Disclosure	Clear overview in SKILL.md with well-signaled, one-level-deep markdown links to seven real reference files (all present in ./references/), with content appropriately split by topic and easy to navigate.	5 / 5
	Total	18 / 20 Passed

Description

92%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, specific description that clearly answers both what the skill does and when to use it, with explicit boundary guidance against a sibling skill. The only gap is the absence of common WSI file extensions as trigger terms.

Suggestions

Add common WSI file extensions (e.g. .svs, .ndpi, .tiff, .mrxs) to the trigger terms so users naming a file format are routed to this skill.

Consider mentioning 'whole slide image' as a synonym alongside 'WSI' since some users spell out the acronym.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'basic slide processing, tissue detection, tile extraction, and stain normalization' — giving comprehensive coverage of the library's capability areas.	5 / 5
Completeness	Explicitly states what it does ('Lightweight WSI tile extraction and preprocessing') and when to use it ('Use for basic slide processing... Best for simple pipelines, dataset preparation...'), with concrete trigger phrases.	5 / 5
Trigger Term Quality	Strong natural domain terms users would say (WSI, H&E images, tissue detection, tile extraction, stain normalization, dataset preparation), but no file extensions (.svs/.ndpi/.tiff) that users often mention.	4 / 5
Distinctiveness Conflict Risk	Clear niche in WSI/digital pathology tile extraction with an explicit boundary clause ('For advanced spatial proteomics, multiplexed imaging, or deep learning pipelines use pathml'), minimizing conflict risk.	5 / 5
	Total	19 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: K-Dense-AI/scientific-agent-skills
Path: skills/histolab/SKILL.md
Commit: 49c6e97

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

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.