CtrlK
BlogDocsLog inGet started
Tessl Logo

histolab

Lightweight WSI tile extraction and preprocessing. Use for basic slide processing, tissue detection, tile extraction, and stain normalization for H&E images. Best for simple pipelines, dataset preparation, and quick tile-based analysis. For advanced spatial proteomics, multiplexed imaging, or deep learning pipelines use pathml.

65

Quality

77%

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 ./skills/histolab/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%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.

A well-structured, largely actionable skill body with executable Quick Start and concrete API-level guidance throughout. The main weakness is redundancy between the Core Capabilities pointers and the trailing Resources section, which inflates token usage without adding navigational value.

Suggestions

Remove or condense the per-file content bullet lists in the Resources section; the Core Capabilities section already signals each reference with a link and one-line description, so the duplicated blurbs are pure padding.

Tighten the Common Use Cases bullets to concrete action/parameter pairs (e.g. 'RandomTiler with seed=42 across slides for balanced datasets') rather than descriptive suggestions.

Add an explicit feedback loop to Quick Start (e.g. 'If locate_tiles() preview shows mostly background, raise tissue_percent or switch mask, then re-preview') to lift workflow clarity toward 5.

DimensionReasoningScore

Conciseness

Quick Start and Best Practices are reasonably tight, but the closing Resources section (≈60 lines) re-describes each reference file's contents, duplicating the Core Capabilities pointers, and the Common Use Cases bullets add descriptive padding that could be trimmed.

3 / 5

Actionability

Quick Start is copy-paste executable and Best Practices/Troubleshooting cite concrete APIs and parameters ('locate_tiles()', 'tissue_percent 70-90%', 'check_tissue=True', 'MacenkoStainNormalizer'), with only minor abstract bullets like 'Implement custom annotation-exclusion masks'.

4 / 5

Workflow Clarity

Quick Start sequences load → configure → preview → extract with an explicit locate_tiles() preview checkpoint reinforced in Best Practices; the batch-operation validation cap at 3 does not bind because preview/check_tissue validation is present, but no explicit error-recovery feedback loop pushes it to 5.

4 / 5

Progressive Disclosure

Seven real reference files are clearly signaled one level deep via markdown links in Core Capabilities with a usage-pattern note, but the duplicated per-file content blurbs in Resources are a minor organization gap keeping it from 5.

4 / 5

Total

15

/

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 concise, third-person description that clearly states capabilities and usage triggers while disambiguating from the adjacent pathml skill. Minor gains possible from naming more concrete sub-actions and adding file-extension synonyms.

DimensionReasoningScore

Specificity

Lists several concrete actions — 'tissue detection, tile extraction, and stain normalization for H&E images' — but they remain somewhat high-level without enumerating the full range of tiler/mask strategies, so a comprehensive 5 is not reached.

4 / 5

Completeness

Explicitly answers both what ('Lightweight WSI tile extraction and preprocessing...') and when ('Use for basic slide processing...', 'Best for simple pipelines, dataset preparation, and quick tile-based analysis') with concrete trigger phrases, plus a redirect to pathml for adjacent advanced cases.

5 / 5

Trigger Term Quality

Strong domain-natural terms ('WSI', 'slide processing', 'tissue detection', 'tile extraction', 'stain normalization', 'H&E images', 'dataset preparation') that a pathology user would say, but a few common synonyms/extensions (e.g. '.svs', 'whole slide image' spelled out) are absent.

4 / 5

Distinctiveness Conflict Risk

Carves a clear digital-pathology WSI niche with distinct triggers and explicitly redirects advanced spatial proteomics/multiplexed imaging to pathml, minimizing overlap risk with related skills.

5 / 5

Total

18

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
K-Dense-AI/scientific-agent-skills
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.