histolab

Lightweight WSI tile extraction and preprocessing. Use for basic slide processing tissue detection, tile extraction, stain normalization for H&E images. Best for simple pipelines, dataset preparation, 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 a sound progressive-disclosure structure pointing to real reference files, but it is verbose — the Resources section and the five Typical Workflows duplicate content already in Core Capabilities. Batch workflows also lack inline validation checkpoints.

Suggestions

Remove the 'Resources' section (or collapse it to one line per file): it duplicates the reference bullet lists already given in each 'Core Capabilities' subsection.

Trim 'Typical Workflows' to two representative examples and point to the reference files for the rest, cutting roughly 150 lines of repeated code.

Add an inline validation/verification step to the multi-slide batch workflow (Workflow 4) — e.g. confirm tile count per slide and wrap extraction in try/except with logging — so batch operations have a real feedback loop.

Dimension	Reasoning	Score
Conciseness	Mostly informative but padded: the 'Resources' section repeats the reference bullet lists already given in 'Core Capabilities', and the five 'Typical Workflows' largely re-state the inline examples, so the body could be tightened considerably. Not a 1 because the code examples are concrete and there is little concept-explanation fluff.	2 / 3
Actionability	Provides numerous complete, executable code blocks with real imports, concrete parameters (tile_size, level, seed, tissue_percent) and full call sequences — copy-paste ready, matching the top anchor.	3 / 3
Workflow Clarity	Workflows are sequenced and include a 'preview before extracting' checkpoint, but batch operations (Workflow 4's multi-slide loop) lack validation/verification steps and error-recovery checkpoints are isolated in a separate Troubleshooting section rather than inline. Per the batch-operations rule this caps the score at 2.	2 / 3
Progressive Disclosure	The SKILL.md is an overview with five well-signaled, one-level-deep references (slide_management, tissue_masks, tile_extraction, filters_preprocessing, visualization), all verified to exist in references/ — clear navigation and appropriate content split.	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, concise description that names concrete capabilities, gives explicit use-when triggers, and carves out a clear niche with a hand-off to a complementary skill. It hits the top anchor on all four dimensions.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'WSI tile extraction and preprocessing', 'tissue detection, tile extraction, stain normalization' — matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Answers both 'what' (tile extraction and preprocessing) and 'when' with explicit trigger clauses ('Use for basic slide processing…', 'Best for simple pipelines, dataset preparation, quick tile-based analysis').	3 / 3
Trigger Term Quality	Covers natural domain terms a pathology user would say — 'WSI', 'slide processing', 'H&E images', 'tissue detection', 'stain normalization', 'dataset preparation' — rather than abstract jargon.	3 / 3
Distinctiveness Conflict Risk	Clear niche (digital pathology WSI processing) with distinct triggers, and it even disambiguates from a sibling skill ('For advanced spatial proteomics, multiplexed imaging, or deep learning pipelines use pathml').	3 / 3
	Total	12 / 12 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (678 lines); consider splitting into references/ and linking	Warning
metadata_version	'metadata.version' is missing	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: synthetic-sciences/openscience
Path: backend/cli/skills/biology/histolab/SKILL.md
Commit: 52845c3

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.