pathml
Full-featured computational pathology toolkit. Use for advanced WSI analysis including multiplexed immunofluorescence (CODEX, Vectra), nucleus segmentation, tissue graph construction, and ML model training on pathology data. Supports 160+ slide formats. For simple tile extraction from H&E slides, histolab may be simpler.
Install with Tessl CLI
npx tessl i github:K-Dense-AI/claude-scientific-skills --skill pathmlOverall
score
78%
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
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 an excellent skill description that clearly defines a specialized computational pathology toolkit with specific capabilities, appropriate trigger terms for the domain, and explicit guidance on when to use it. The description effectively distinguishes itself from simpler alternatives and uses proper third-person voice throughout.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'multiplexed immunofluorescence (CODEX, Vectra), nucleus segmentation, tissue graph construction, and ML model training on pathology data' plus '160+ slide formats' support. | 3 / 3 |
Completeness | Clearly answers both what ('computational pathology toolkit' with specific capabilities) and when ('Use for advanced WSI analysis'). Also helpfully distinguishes scope by noting when a simpler alternative (histolab) may be preferred. | 3 / 3 |
Trigger Term Quality | Excellent coverage of domain-specific terms users would naturally use: 'WSI', 'CODEX', 'Vectra', 'nucleus segmentation', 'tissue graph', 'pathology', 'H&E slides', 'histolab'. These are terms pathology researchers would actually search for. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche in computational pathology with specific triggers like 'CODEX', 'Vectra', 'nucleus segmentation', 'tissue graph'. The comparison to histolab further clarifies when to use this vs simpler alternatives. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
57%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill has strong progressive disclosure with well-organized references to detailed documentation, but sacrifices actionability by being too descriptive rather than instructive. The content would benefit from more executable examples in the main file and explicit validation steps in workflows. The promotional K-Dense section detracts from the skill's focus.
Suggestions
Replace the abstract 'Common Workflows' numbered lists with executable code examples showing each workflow end-to-end
Add validation/verification steps to workflows, especially for ML training (e.g., 'Verify model loaded correctly with test inference before full training')
Remove or significantly condense the K-Dense promotional section as it doesn't teach PathML usage
Tighten the Overview section by removing phrases like 'designed to facilitate' and focusing on what PathML does rather than describing it
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content includes some unnecessary explanation (e.g., 'designed to facilitate machine learning and image analysis') and the overview section could be tighter. The promotional K-Dense section at the end adds tokens without teaching PathML usage. | 2 / 3 |
Actionability | The Quick Start provides executable code, but most capability sections are descriptive rather than instructive, pointing to reference files instead of providing concrete examples. The 'Common Workflows' section lists steps abstractly without executable code. | 2 / 3 |
Workflow Clarity | Workflows are listed as numbered steps but lack validation checkpoints or error handling. For complex operations like ML training or multiparametric analysis, there are no explicit verification steps or feedback loops for error recovery. | 2 / 3 |
Progressive Disclosure | Excellent structure with clear overview and well-signaled one-level-deep references to six detailed reference files. Navigation is clear with consistent 'See: references/X.md' patterns throughout. | 3 / 3 |
Total | 9 / 12 Passed |
Validation
88%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 |
|---|---|---|
description_trigger_hint | Description may be missing an explicit 'when to use' trigger hint (e.g., 'Use when...') | Warning |
metadata_version | 'metadata.version' is missing | Warning |
Total | 14 / 16 Passed | |
- 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.