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

86%

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

72%

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

The body is highly actionable with real executable code and well-structured one-level references, but carries redundant examples and duplicated reference summaries, and its workflows lack explicit validation checkpoints for batch extraction.

Suggestions

Deduplicate the recurring RandomTiler setup: keep one canonical example in Quick Start or Core Capabilities and reference it from Workflows 1, 4, and 5 instead of repeating the full block.

Remove the duplicated per-reference bullet summaries in the Resources section, or trim the inline 'Reference: ... contains comprehensive documentation on' lists, keeping only one of the two.

Add an explicit validation/verification checkpoint to the multi-slide batch pipeline (Workflow 4) and to extraction workflows — e.g. assert tile counts or inspect the CSV report before proceeding — to lift workflow clarity above 2.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with concrete examples and no over-explanation of basics, but the RandomTiler setup recurs verbatim across Quick Start and Workflows 1/4/5, and the reference-file summaries are duplicated inline and again in the Resources section. Could be tightened without losing clarity.	2 / 3
Actionability	Code blocks are executable and copy-paste ready with real imports, parameters, and method calls (e.g. 'tiler.extract(slide)' and 'report_path="tiles_report.csv"'), matching the fully-executable anchor.	3 / 3
Workflow Clarity	Workflows are well sequenced with preview-before-extract guidance and troubleshooting, but the batch multi-slide pipeline (Workflow 4) and other extraction workflows lack explicit validation/verification checkpoints, capping clarity at 2 per the batch-operations guideline.	2 / 3
Progressive Disclosure	SKILL.md is a clear overview with one-level-deep references signaled inline (e.g. 'Reference: references/tile_extraction.md'), each verified to be a real file, and content is appropriately split for easy navigation.	3 / 3
	Total	10 / 12 Passed

Description

100%

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 description: concrete, trigger-rich, complete with both what and when, and clearly differentiated from pathml. No material weaknesses to address.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('slide processing, tissue detection, tile extraction, and stain normalization') plus explicit use/non-use guidance, matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Explicitly answers both what (lightweight WSI tile extraction/preprocessing with enumerated capabilities) and when ('Use for...', 'Best for...'), and adds a clear when-not-to-use routing to pathml.	3 / 3
Trigger Term Quality	Covers natural terms a user would say ('tile extraction', 'tissue detection', 'stain normalization', 'H&E images', 'dataset preparation', 'deep learning pipelines'), with good variation including 'spatial proteomics' and 'multiplexed imaging'.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (WSI/H&E histopathology tile extraction) with distinct triggers and an explicit boundary against the competing pathml skill, making wrong-skill triggering unlikely.	3 / 3
	Total	12 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (714 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: K-Dense-AI/scientific-agent-skills
Path: skills/histolab/SKILL.md
Commit: 757b63b

Reviewed: about 11 hours 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.