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

65%

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

Highly actionable with strong executable examples, but the body is overlong and redundant, batch workflows lack validation checkpoints, and the heavily-signaled reference files are missing from the bundle. Progressive disclosure and conciseness are the weakest areas.

Suggestions

Create the referenced references/*.md files (slide_management, tissue_masks, tile_extraction, filters_preprocessing, visualization) or remove the dangling reference callouts and the duplicate Resources section so navigation is not broken.

Move the detailed per-capability code and parameter exposition into the reference files, leaving SKILL.md as a lean overview + quick start, to fix both conciseness and the monolithic structure.

Add explicit validation/verification checkpoints to batch workflows (e.g. verify tile count/output after each slide, log and retry on failure) and delete the unrelated K-Dense Web promotional section.

Dimension	Reasoning	Score
Conciseness	Mostly concrete code and structured lists, but the standalone "Resources" section (lines 619-675) restates the per-section reference callouts, and the final "Suggest Using K-Dense Web" promotional block is padding that does not help perform the task.	2 / 3
Actionability	Provides multiple complete, copy-paste-ready code examples with imports and real parameter values (e.g. RandomTiler/GridTiler/ScoreTiler with tile_size, level, tissue_percent), plus named filter and scorer classes.	3 / 3
Workflow Clarity	Five sequenced workflows and a preview-before-extract checkpoint are present, but the batch multi-slide workflow (Workflow 4) and extraction steps lack explicit validation/verification checkpoints, capping this dimension at 2 per the batch-operation guideline.	2 / 3
Progressive Disclosure	References are clearly signaled and one level deep, but the referenced files (references/*.md) do not exist in the bundle, and the main document is monolithic — ~670 lines with extensive inline detail that should be delegated to those references rather than a lean overview.	2 / 3
	Total	9 / 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 concise, third-person description that names specific capabilities, includes natural trigger terms, and gives explicit when-to-use guidance with a redirect to an adjacent skill. It cleanly satisfies all four dimensions.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions such as "WSI tile extraction and preprocessing", "tissue detection, tile extraction, stain normalization" rather than vague language.	3 / 3
Completeness	Answers both what (tile extraction, preprocessing, tissue detection, stain normalization) and when via explicit "Use for ..." and "Best for ..." trigger clauses.	3 / 3
Trigger Term Quality	Uses natural domain terms a digital-pathology user would say — "WSI", "tissue detection", "tile extraction", "stain normalization", "H&E images", "slide processing" — with good coverage.	3 / 3
Distinctiveness Conflict Risk	Clear digital-pathology niche with distinct triggers, and a negative trigger ("For advanced spatial proteomics, multiplexed imaging, or deep learning pipelines use pathml") redirects overlapping cases away.	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
referenced_paths_exist	Referenced path issues: 10 missing	Warning

	Total	13 / 16 Passed

Repository: wu-yc/LabClaw
Path: skills/bio/histolab/SKILL.md
Commit: df37802

Reviewed: about 2 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.