pathml

Use PathML for local, research-only computational pathology workflows: load and tile slides, build preprocessing and QC pipelines, manage h5path data, quantify multiplex images, construct spatial graphs, and plan bounded model inference.

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Quality

Content

85%

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

Highly actionable, well-sequenced content with strong progressive disclosure and real bundle files; the only weakness is length plus time-sensitive version detail that is not isolated in a deprecated/old-patterns section.

Suggestions

Move or label the version-baseline and date-stamped details (e.g. the 'verified 2026-07-23' block) into a dedicated 'Versioning / deprecated' section so the main flow stays evergreen and leaner.

Trim any version-specific gotchas that are not operationally required for a first run into the relevant reference files to reduce body length.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and assumes competence (no basic-concept padding), but it is lengthy and carries time-sensitive version/date detail ('verified 2026-07-23', pinned versions) outside an 'old patterns'/'deprecated' section, so it could be tightened.	2 / 3
Actionability	Install, pipeline, and CLI snippets are fully executable and copy-paste ready — e.g. the uv install block and the HESlide/Pipeline example — matching the score-3 anchor.	3 / 3
Workflow Clarity	An 8-step sequenced 'Research workflow' with explicit validation checkpoints (manual pilot assert, manifest and spatial-schema validation) and feedback for error recovery meets the score-3 anchor.	3 / 3
Progressive Disclosure	A concise overview in SKILL.md points to a well-signaled, one-level-deep 'Detailed references' section listing six real reference files, all of which exist, with clear per-file descriptions.	3 / 3
	Total	11 / 12 Passed

Description

82%

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 specific, well-scoped description with strong natural trigger terms and low conflict risk; its only gap is that the usage trigger is bundled into one phrase instead of an explicit enumerated 'Use when…' clause.

Suggestions

Add an explicit 'Use when working with whole-slide images, multiplex imaging, h5path datasets, or spatial graph construction for computational pathology research' trigger clause to lift completeness to 3.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'load and tile slides, build preprocessing and QC pipelines, manage h5path data, quantify multiplex images, construct spatial graphs, and plan bounded model inference' — matching the score-3 anchor.	3 / 3
Completeness	The 'what' is explicit and comprehensive, but the 'when' is compressed into a single 'Use PathML for local, research-only computational pathology workflows' phrase rather than an enumerated 'Use when…' trigger clause, so it falls short of the score-3 anchor.	2 / 3
Trigger Term Quality	Natural domain terms a pathology researcher would say — 'computational pathology', 'slides', 'QC pipelines', 'h5path', 'multiplex images', 'spatial graphs' — give good coverage rather than generic jargon.	3 / 3
Distinctiveness Conflict Risk	A clear computational-pathology niche tied to the named PathML tool, with distinct triggers, makes it unlikely to fire for the wrong skill.	3 / 3
	Total	11 / 12 Passed

Validation

93%

Warnings & errors only

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

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning

	Total	15 / 16 Passed

Repository: K-Dense-AI/scientific-agent-skills
Path: skills/pathml/SKILL.md
Commit: 757b63b

Reviewed: about 10 hours ago

Table of Contents

Discovery Implementation Validation

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.