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

82%

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%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.

The body is highly actionable with real, well-organized reference files, but is let down by duplicated reference listings and a batch workflow lacking validation checkpoints. Conciseness and workflow_clarity are the weakest dimensions.

Suggestions

Remove the trailing '## Resources' section (or the inline 'Reference:' bullets) so each reference is described once, cutting roughly 60 lines of duplicated content.

Consolidate the repeated RandomTiler example so the core extraction pattern appears once and Workflows 1 and 4 reference it rather than re-inlining the full snippet.

Add a per-slide validation/feedback loop to Workflow 4 (e.g., check that extracted tile count > 0 and wrap each slide in try/except with continue) so the batch operation has an explicit checkpoint and error-recovery path.

Dimension	Reasoning	Score
Conciseness	Content is mostly efficient actionable code, but the per-section 'Reference: references/X.md contains comprehensive documentation on:' bullet lists are duplicated verbatim in the trailing '## Resources' section, and RandomTiler examples recur across Quick Start, section 3, and Workflows 1/4, leaving clear tightening opportunities.	3 / 5
Actionability	Provides copy-paste-ready, executable Python for loading slides, all three tiler strategies, filter composition, visualization, and batch processing, with specific imports and concrete parameters covering the common cases.	5 / 5
Workflow Clarity	Workflows are sequenced and include a preview-before-extract checkpoint, but the batch Workflow 4 loops over all slides with no per-slide validation or error-recovery feedback loop; per rubric this caps workflow_clarity at 3.	3 / 5
Progressive Disclosure	SKILL.md is a clear overview with well-signaled, one-level-deep references (references/slide_management.md, tissue_masks.md, tile_extraction.md, filters_preprocessing.md, visualization.md), all of which exist as real files with no nested reference chains.	5 / 5
	Total	16 / 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.

The description is concrete, trigger-rich, and answers both what and when explicitly, with clear boundary guidance against a sibling skill. Its only minor gap is a few missing natural synonyms for full trigger coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'WSI tile extraction and preprocessing', 'tissue detection, tile extraction, stain normalization for H&E images', 'dataset preparation, quick tile-based analysis' — giving comprehensive coverage of the domain rather than vague abstraction.	5 / 5
Completeness	Explicitly answers both 'what' (WSI tile extraction and preprocessing with concrete capabilities) and 'when' ('Use for basic slide processing...', 'Best for simple pipelines, dataset preparation'), plus an explicit boundary clause ('For advanced... use pathml').	5 / 5
Trigger Term Quality	Includes natural domain terms users would say ('tile extraction', 'H&E images', 'stain normalization', 'dataset preparation', 'spatial proteomics', 'multiplexed imaging') with good coverage, though a few common synonyms or file extensions are absent.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear digital-pathology niche (WSI tile extraction for H&E) with distinct triggers and an explicit hand-off to pathml for adjacent domains, minimizing overlap risk.	5 / 5
	Total	19 / 20 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: 3a6c3a9

Reviewed: 1 day 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.