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.
62
75%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./scientific-skills/histolab/SKILL.mdQuality
Discovery
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.
This is a strong skill description that clearly defines its domain (lightweight WSI tile processing), lists specific capabilities (tissue detection, tile extraction, stain normalization), and provides explicit guidance on when to use it versus alternatives like pathml. The inclusion of boundary conditions ('For advanced spatial proteomics... use pathml') is particularly effective for disambiguation in a multi-skill environment.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: tissue detection, tile extraction, stain normalization for H&E images, dataset preparation, and tile-based analysis. These are clearly defined domain-specific operations. | 3 / 3 |
Completeness | Clearly answers both 'what' (tile extraction, tissue detection, stain normalization, preprocessing) and 'when' ('Use for basic slide processing...', 'Best for simple pipelines, dataset preparation, quick tile-based analysis'). Also includes explicit negative triggers distinguishing from pathml for advanced cases. | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords a user in this domain would use: 'WSI', 'tile extraction', 'tissue detection', 'stain normalization', 'H&E images', 'slide processing', 'dataset preparation'. Also distinguishes from 'pathml' for advanced use cases, which helps with routing. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche in lightweight WSI tile processing. Explicitly differentiates itself from pathml by specifying it's for basic/simple pipelines versus advanced spatial proteomics, multiplexed imaging, or deep learning pipelines, reducing conflict risk significantly. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill provides highly actionable, executable code examples for histolab workflows, which is its primary strength. However, it is significantly over-verbose with extensive repetition—the same RandomTiler pattern appears at least three times, reference descriptions are duplicated, and sections like Common Use Cases and Best Practices largely restate what's already shown in the workflows. The lack of validation checkpoints in batch/destructive workflows and the redundant structure between inline content and reference file descriptions weaken the overall quality.
Suggestions
Eliminate redundant code examples: the Quick Start RandomTiler example is nearly identical to Workflow 1. Keep Quick Start minimal and remove duplicate workflows.
Remove the 'Resources' section at the end entirely—each core capability section already describes its reference file. Alternatively, keep only the Resources section and remove inline reference descriptions.
Condense 'Common Use Cases' into a brief table or bullet list mapping use case → recommended tiler/approach, since the workflows already demonstrate these patterns.
Add explicit validation/error handling in Workflow 4 (Multi-Slide Processing): wrap extraction in try/except, verify tile count after extraction, and log failures for review.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~450+ lines. It repeats the same code patterns multiple times (e.g., RandomTiler extraction appears in Quick Start, Tile Extraction section, and Workflow 1 nearly identically). The 'Common Use Cases' section is largely redundant with the workflows. The 'Resources' section at the end repeats the same reference descriptions already given inline in each section. Best practices, troubleshooting, and use cases sections contain generic advice Claude could infer. | 1 / 3 |
Actionability | The skill provides fully executable, copy-paste ready Python code throughout. All examples use real imports, concrete parameters, and complete workflows. The code is specific with actual class names, method calls, and parameter values. | 3 / 3 |
Workflow Clarity | The workflows are clearly sequenced with numbered steps and logical progression (load → inspect → configure → preview → extract). However, there are no explicit validation checkpoints or error recovery loops. For batch operations (Workflow 4: Multi-Slide Processing), there's no error handling, no validation that tiles were actually extracted, and no feedback loop for failed slides. | 2 / 3 |
Progressive Disclosure | The skill references five separate reference files in a references/ directory, which is good structure. However, no bundle files were provided, so the references may not exist. The main SKILL.md itself contains too much inline content that should be in the reference files (e.g., the extensive filter examples, all five workflow examples, troubleshooting). The reference file descriptions at the end duplicate what's already stated inline in each section. | 2 / 3 |
Total | 8 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (677 lines); consider splitting into references/ and linking | Warning |
metadata_version | 'metadata.version' is missing | Warning |
Total | 9 / 11 Passed | |
- Repository
- K-Dense-AI/claude-scientific-skills
- Commit
cbcae7b
- 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.