histolab

Digital pathology image processing toolkit for whole slide images (WSI). Supports WSI formats (SVS, TIFF, NDPI), tile-based analysis, and histological image preprocessing workflows.

Quality

71%

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

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/Data Analysis/histolab/SKILL.md

Quality

Content

78%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 executable examples and excellent progressive disclosure to real reference files, but it suffers from verbosity and repetition between the Core Capabilities examples and the Typical Workflows section.

Suggestions

Consolidate the 'Typical Workflows' section or fold it into 'Core Capabilities' to eliminate the near-duplicate code blocks that repeat the same tiler/mask/filter examples.

Trim 'Common Use Cases' and 'Best Practices', which restate parameters already covered, into a compact checklist.

Add an explicit post-extraction validation step (e.g., check tile count and inspect low-score tiles) to give the batch workflows a true validate->fix->retry feedback loop.

Dimension	Reasoning	Score
Conciseness	The body is mostly useful API/code content without over-explaining known concepts, but it is notably padded: the five 'Typical Workflows' largely repeat the examples already given under 'Core Capabilities', and Best Practices/Common Use Cases/Troubleshooting restate the same parameters, so it could be tightened substantially.	3 / 5
Actionability	Multiple copy-paste-ready, executable code blocks cover the common cases (random/grid/score tiling, custom filter pipelines, multi-slide processing) with concrete imports, parameters, and method calls.	5 / 5
Workflow Clarity	Workflows are clearly sequenced and repeatedly enforce an explicit validation checkpoint ('Always preview with locate_tiles() before extracting') before the batch extract step, though there is no formal validate-output-then-fix feedback loop, leaving a minor validation gap for batch operations.	4 / 5
Progressive Disclosure	The SKILL.md is a clear overview with five well-signaled one-level-deep references ('Reference: references/x.md contains comprehensive documentation on:'), all of which correspond to real files in references/, and detailed material is appropriately split out with easy navigation.	5 / 5
	Total	17 / 20 Passed

Description

65%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 clearly identifies a distinct niche and includes useful trigger terms with file extensions, but it omits any explicit 'Use when' trigger guidance and its listed actions are somewhat generic rather than comprehensive and concrete.

Suggestions

Add an explicit trigger clause such as 'Use when processing histopathology whole slide images (SVS/TIFF/NDPI), extracting tiles, or detecting tissue regions for computational pathology pipelines.'

Replace generic phrasing like 'tile-based analysis' and 'preprocessing workflows' with concrete actions (e.g., 'detects tissue regions, extracts informative tiles, scores tiles by nuclei density').

Include natural user-facing terms like 'histopathology slides', 'H&E/IHC stained tissue', and 'tissue masks' to improve trigger term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ('Digital pathology image processing toolkit for whole slide images') and lists a couple of actions ('tile-based analysis, and histological image preprocessing workflows'), but the actions are somewhat generic and not a comprehensive concrete list, matching the anchor for 1-2 concrete actions.	3 / 5
Completeness	There is a clear 'what' (toolkit supports WSI formats, tile-based analysis, preprocessing), but there is no 'Use when...' clause or equivalent explicit trigger guidance, which per the guidelines caps completeness at 3.	3 / 5
Trigger Term Quality	Good keyword coverage with synonyms ('whole slide images (WSI)', 'digital pathology') and file extensions ('SVS, TIFF, NDPI'), though common natural terms a user might say like 'histopathology slides', 'H&E', or 'tissue' are missing.	4 / 5
Distinctiveness Conflict Risk	The description carves out a clear niche (digital pathology WSI processing with named formats) with distinct triggers and minimal overlap risk with unrelated skills.	5 / 5
	Total	15 / 20 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 (704 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: aipoch/medical-research-skills
Path: scientific-skills/Data Analysis/histolab/SKILL.md
Commit: f5ef65b

Reviewed: ~3 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.