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.
78
75%
Does it follow best practices?
Impact
Pending
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 scope within computational pathology. It lists specific capabilities, includes domain-appropriate trigger terms, explicitly states when to use it versus when to use the alternative (pathml), and occupies a well-defined niche. Minor improvement could include slightly better punctuation (missing commas in the list) but the content is excellent.
| 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 capabilities in the digital pathology domain. | 3 / 3 |
Completeness | Clearly answers both 'what' (tile extraction, tissue detection, stain normalization) and 'when' ('Use for basic slide processing...', 'Best for simple pipelines, dataset preparation'). Also includes explicit negative triggers directing to pathml for advanced use 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 differentiates from pathml with explicit contrast terms like 'spatial proteomics' and 'multiplexed imaging'. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche in lightweight WSI tile processing. Explicitly differentiates itself from pathml by specifying boundary conditions (advanced spatial proteomics, multiplexed imaging, 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 covering the full histolab workflow, which is its primary strength. However, it is significantly over-verbose, repeating examples across sections, including obvious best practices, and duplicating reference file descriptions. The document would benefit greatly from trimming to roughly half its size by removing redundant workflows, obvious guidance, and leveraging its reference files more aggressively.
Suggestions
Cut the document by ~50%: remove the 'Common Use Cases' section entirely (it's descriptive, not actionable), consolidate the 5 workflow examples down to 2-3, and eliminate the redundant 'Resources' section since each core capability already links to its reference file.
Remove obvious best practices that Claude already knows (e.g., 'Always inspect slide properties before processing', 'Enable logging for large datasets') and keep only domain-specific, non-obvious guidance.
Add validation/error-handling steps to the multi-slide processing workflow (Workflow 4), such as checking if tiles were actually extracted, handling corrupt slides, or verifying output counts.
Move the Troubleshooting section to a reference file and keep only a brief pointer to it in the main SKILL.md.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~450+ lines. It repeats information extensively (e.g., the same tiler examples appear in Core Capabilities AND Typical Workflows), explains concepts Claude already knows (what WSI formats are, what grid extraction means), and the Resources section redundantly re-lists everything already covered in the reference pointers within each section. The Best Practices, Common Use Cases, and Troubleshooting sections contain mostly obvious guidance that doesn't add unique value. | 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 snippets are specific and functional, covering all major use cases with real class names and method calls. | 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 feedback loops. For batch operations (Workflow 4: Multi-Slide Processing), there's no validation step to check if extraction succeeded or handle failures, which should cap this at 2. | 2 / 3 |
Progressive Disclosure | The skill does reference external files in `references/` directory with clear signaling, which is good. However, the main SKILL.md itself is monolithic with excessive inline content that should be in the reference files. The detailed workflow examples, extensive best practices, common use cases, troubleshooting, and the redundant Resources section at the end all bloat the main file when they could be offloaded. The references are well-organized but the main document doesn't serve as a lean overview. | 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
b58ad7e
- 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.