CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/histolab/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

61%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 complete, executable code for every major workflow, and the reference bundle is well structured with real, clearly signaled one-level-deep files. However, it is heavily padded — duplicated reference summaries, triplicated tiler examples, and a promotional footer — and its batch-processing workflow lacks output verification, capping workflow clarity.

Suggestions

Remove the "Resources" section (or reduce it to a five-line file list): it duplicates the per-section reference bullet lists almost verbatim, saving ~60 lines without losing any information.

Deduplicate the RandomTiler/GridTiler/ScoreTiler configuration examples: keep one full example in the Tile Extraction section and have the Typical Workflows reference it instead of repeating near-identical code three times.

Add a validation step to the multi-slide batch workflow (Workflow 4), e.g. count extracted tiles per slide and warn or retry when a slide yields zero tiles, mirroring the existing "No tiles extracted" troubleshooting guidance.

DimensionReasoningScore

Conciseness

The document is noticeably verbose with systematic duplication: the "Resources" section (lines 617-674) restates the per-section reference bullet lists almost verbatim, RandomTiler configuration code appears three times (Quick Start, capability 3, Workflow 1), and the closing K-Dense Web promotional paragraph is unrelated to executing the skill. This goes beyond the "could be tightened" level of anchor 3.

2 / 5

Actionability

The Quick Start and all five Typical Workflows are complete, executable, copy-paste-ready code covering the common cases (random/grid/scored extraction, custom filter masks, multi-slide loops), with only a few inline fragments assuming variables from earlier snippets. This matches anchor 5.

5 / 5

Workflow Clarity

Sequences are clear and "Always preview with locate_tiles() before extracting" is an explicit checkpoint, but Workflow 4 (batch multi-slide processing) and the extraction workflows lack verification that tiles were actually produced, and the rubric caps workflow clarity at 3 for batch operations missing validation steps.

3 / 5

Progressive Disclosure

All five referenced files exist, are one level deep, and are clearly signaled inline ("**Reference:** `references/tile_extraction.md` contains comprehensive documentation on:"), but the ~670-line main file inlines substantial workflow/troubleshooting content that belongs in the references and the Resources section duplicates the inline navigation, keeping it below the lean-overview anchor 5.

4 / 5

Total

14

/

20

Passed

Description

87%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.

A strong description: it states concrete capabilities in third person, provides an explicit "Use for" trigger clause with natural domain keywords, and actively disambiguates from the adjacent pathml skill. The only weaknesses are minor keyword gaps (no spelled-out "whole slide image", "histopathology", or file extensions) and unmentioned secondary features.

DimensionReasoningScore

Specificity

"tissue detection, tile extraction, stain normalization for H&E images" names multiple concrete, domain-specific actions, but coverage has minor gaps (filters, visualization, and scoring tilers are unmentioned), matching anchor 4 rather than the comprehensive anchor 5.

4 / 5

Completeness

Both what ("Lightweight WSI tile extraction and preprocessing") and when (explicit "Use for basic slide processing tissue detection, tile extraction, stain normalization for H&E images" plus "Best for simple pipelines, dataset preparation") are clearly answered with concrete trigger phrases, matching anchor 5 exactly.

5 / 5

Trigger Term Quality

Good natural keyword coverage ("WSI", "tile extraction", "H&E images", "stain normalization", "dataset preparation") that a digital-pathology user would plausibly say, but common variations like "whole slide image" spelled out, "histopathology", and file extensions (.svs, .ndpi) are missing, so it falls short of anchor 5.

4 / 5

Distinctiveness Conflict Risk

The WSI tile-extraction niche is distinct and the description even disambiguates against the nearest neighbor ("For advanced spatial proteomics, multiplexed imaging, or deep learning pipelines use pathml"), giving minimal conflict risk per anchor 5.

5 / 5

Total

18

/

20

Passed

Validation

87%

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

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (678 lines); consider splitting into references/ and linking

Warning

metadata_version

'metadata.version' is missing

Warning

Total

14

/

16

Passed

Repository

googolme/run0204

Path

scientific-skills/histolab/SKILL.md

Reviewed

Table of Contents

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.