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 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 excellent actionable code examples covering all major histolab workflows, but is severely undermined by verbosity and redundancy. Content is repeated across Core Capabilities, Typical Workflows, and Resources sections. The main SKILL.md should be a concise overview pointing to references, but instead contains extensive inline content that belongs in the reference files.
Suggestions
Cut the 'Typical Workflows' section significantly — most workflows duplicate code already shown in Core Capabilities. Keep at most 1-2 unique end-to-end workflows.
Move 'Best Practices', 'Common Use Cases', and 'Troubleshooting' to a reference file, keeping only the most critical 2-3 bullet points inline (e.g., 'always preview with locate_tiles() before extracting').
Remove the 'Resources' section's verbose re-descriptions of each reference file — a simple bulleted list with one-line descriptions suffices since the references are already described inline in Core Capabilities.
Add explicit validation/error handling in batch workflows (Workflow 4): wrap extraction in try/except, verify output tile count, and log failures for review.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~450+ lines. It repeats information extensively — the 'Typical Workflows' section largely duplicates the code examples already shown in 'Core Capabilities'. The 'Common Use Cases' section is vague prose that Claude already knows. The 'Resources' section at the end redundantly re-describes what each reference file contains after already describing them inline. Best practices and troubleshooting sections contain generic advice (e.g., 'Always inspect slide properties before processing') that wastes tokens. | 1 / 3 |
Actionability | The skill provides fully executable, copy-paste ready Python code examples throughout. Code snippets include proper imports, realistic parameters, and cover all major use cases (random tiling, grid tiling, score-based tiling, custom filtering, multi-slide processing). | 3 / 3 |
Workflow Clarity | Workflows are clearly sequenced with numbered steps and multiple complete examples. However, there are no explicit validation checkpoints or error recovery loops — for batch operations like multi-slide processing (Workflow 4), there's no try/except, no verification that tiles were actually extracted, and no feedback loop for handling failed slides. The 'always preview before extracting' guidance is mentioned but not enforced in all workflows. | 2 / 3 |
Progressive Disclosure | The skill does reference external files in `references/` which is good structure, but the main SKILL.md itself is bloated with content that should be in those reference files. The inline examples, the lengthy best practices, troubleshooting, and common use cases sections make the main file a near-monolithic document. The references are well-signaled but the main file doesn't act 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
25e1c0f
- 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.