CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

60

Quality

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/bio/pathml/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

42%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is well-sectioned and opens with an executable example, but it is padded with promotional prose and, critically, depends on a references/ bundle that is entirely missing. Without those files the progressive-disclosure promise is unfulfilled and detailed guidance is unreachable.

Suggestions

Create the six referenced files under references/ (image_loading, preprocessing, graphs, machine_learning, multiparametric, data_management) or remove the dangling "See:" pointers so navigation is not broken.

Tighten marketing language ("comprehensive", "Full-featured", "designed to facilitate") and drop the K-Dense Web promotional section so every token earns its place.

Add explicit validation/verification checkpoints to the ML-training and batch workflows (e.g. confirm held-out evaluation, verify HDF5 integrity) to lift workflow clarity above 2.

DimensionReasoningScore

Conciseness

Mostly efficient with concrete lists and a code example, but padded with marketing phrasing ("comprehensive", "Full-featured", "designed to facilitate") and a 12-line promotional "Suggest Using K-Dense Web" section unrelated to skill functionality — not lean enough for the 3 anchor.

2 / 3

Actionability

The Quick Start code block is executable and concrete, but the bulk of deeper guidance routes to "See: references/<file>.md" entries whose files do not exist, leaving the detailed instruction layer incomplete rather than copy-paste ready.

2 / 3

Workflow Clarity

Three numbered workflows are sequenced, but steps are high-level outlines (e.g. "Apply tissue detection and stain normalization") with no validation or verification checkpoints for ML-training and batch operations, which the rubric caps at 2.

2 / 3

Progressive Disclosure

The body signals six one-level-deep reference files, but the references/ directory is absent — none of the referenced files exist, so navigation is broken and the disclosure structure collapses rather than reaching even the some-structure anchor at 2.

1 / 3

Total

7

/

12

Passed

Description

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.

A strong description: it states concrete capabilities, provides an explicit Use-for trigger, uses natural domain keywords, and carves out a distinct niche. Voice is third person with no first/second-person penalty.

DimensionReasoningScore

Specificity

Lists multiple concrete actions: "multiplexed immunofluorescence (CODEX, Vectra), nucleus segmentation, tissue graph construction, and ML model training" — matches the multiple-specific-actions anchor rather than the single-domain anchor at 2.

3 / 3

Completeness

Explicitly states what ("Full-featured computational pathology toolkit") and when via an explicit "Use for advanced WSI analysis including..." trigger clause, satisfying both halves rather than the implied-when anchor at 2.

3 / 3

Trigger Term Quality

Uses natural domain terms a pathology user would say — "computational pathology", "WSI analysis", "nucleus segmentation", "H&E slides", "CODEX", "Vectra" — giving good coverage rather than the some-keywords-but-missing-variations anchor at 2.

3 / 3

Distinctiveness Conflict Risk

Occupies a clear niche (computational pathology / WSI) and even names a competitor for simpler cases ("histolab may be simpler"), making wrong-skill triggering unlikely rather than the overlap-prone anchor at 2.

3 / 3

Total

12

/

12

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

referenced_paths_exist

Referenced path issues: 12 missing

Warning

Total

14

/

16

Passed

Repository
wu-yc/LabClaw
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.