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

92%

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

85%

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 executable examples, clear sequenced workflows featuring preview checkpoints, and well-structured one-level-deep references. The main weakness is redundancy: the trailing Resources section restates reference descriptions already given in the Core Capabilities sections.

Suggestions

Remove the trailing 'Resources' section (lines 621-679) — it duplicates the per-file 'references/X.md contains...' descriptions already embedded in each Core Capabilities subsection; a one-line pointer to the references/ directory suffices.

Consolidate the five 'Typical Workflows' with the inline Core Capabilities examples where they overlap (e.g., RandomTiler appears in both) to cut repeated code blocks.

Tighten 'Common Use Cases' into a compact bulleted matrix rather than five prose sections that largely restate tiler choices already covered.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and free of concept-explanation padding, but the ~680-line body duplicates reference-file descriptions: each capability section already lists 'references/X.md contains...' and the trailing 'Resources' section (lines 621-679) re-states the same descriptions, which could be tightened.	2 / 3
Actionability	Provides complete, copy-paste-ready Python with real imports and concrete parameters across slide loading, three tilers, filter composition, and visualization, plus the score-report CSV analysis example.	3 / 3
Workflow Clarity	Five numbered workflows are clearly sequenced with explicit validation checkpoints — 'Always preview with locate_tiles() before extracting' and 'Preview masks with locate_mask() before extraction' — and the Quality Control section closes the loop on score distributions; operations are non-destructive read-only extraction so no destructive-validation cap applies.	3 / 3
Progressive Disclosure	All five referenced files (slide_management, tissue_masks, tile_extraction, filters_preprocessing, visualization) exist, are one level deep with no nested references, and are clearly signaled inline with 'references/X.md contains...', giving clean one-level navigation.	3 / 3
	Total	11 / 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.

The description is specific, uses natural trigger terms, answers both what and when, and draws a clear boundary against the sibling pathml skill. No vague fluff or over-claims; all four dimensions land at the top anchor.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — 'WSI tile extraction and preprocessing', 'tissue detection, tile extraction, stain normalization for H&E images' — matching the anchor that lists several specific concrete actions.	3 / 3
Completeness	Explicitly answers both 'what' (tile extraction, preprocessing, tissue detection, stain normalization) and 'when' via the 'Use for...' clause, plus a clear boundary ('For advanced spatial proteomics... use pathml').	3 / 3
Trigger Term Quality	Uses natural terms a pathologist or researcher would actually say — 'WSI', 'tile extraction', 'tissue detection', 'H&E images', 'stain normalization', 'dataset preparation', 'pathml' — giving good coverage of common phrasings.	3 / 3
Distinctiveness Conflict Risk	Clear niche (lightweight WSI tile extraction for histolab) with explicit hand-off to pathml for advanced cases, making it unlikely to trigger for the wrong skill.	3 / 3
	Total	12 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (680 lines); consider splitting into references/ and linking	Warning
metadata_version	'metadata.version' is missing	Warning

	Total	14 / 16 Passed

Repository: foryourhealth111-pixel/Vibe-Skills
Path: bundled/skills/histolab/SKILL.md
Commit: f627ab5

Reviewed: about 7 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.