pathology-roi-selector

Use pathology roi selector for data analysis workflows that need structured execution, explicit assumptions, and clear output boundaries.

Quality

25%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/Data Analysis/pathology-roi-selector/SKILL.md

Quality

Content

25%Weight 40%Scale 1-5

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

The body is verbose boilerplate that references a packaged script which does not exist, providing verification-only commands and abstract workflow steps without executable guidance or genuine validation checkpoints.

Suggestions

Either ship an actual scripts/main.py with documented CLI arguments or remove all references to the packaged executable and replace them with concrete, runnable instructions inline.

Collapse the duplicated process guidance (When to Use, Key Features, Dependencies, Implementation Details, Output Requirements, Response Template, Input Validation, Error Handling) into a single concise workflow section, eliminating the verbatim description repetition and triple-repeated py_compile block.

Add an explicit validation checkpoint to the workflow (e.g. verify ROI coordinates fall within image bounds and confirm output crops are non-empty before returning them), since this is a batch image operation.

Dimension	Reasoning	Score
Conciseness	The body is noticeably padded: the description sentence is repeated verbatim in 'When to Use' and 'Key Features', the py_compile command appears three times, and multiple sections (Dependencies, Implementation Details, Output Requirements, Response Template, Input Validation, Error Handling) restate the same generic 'confirm inputs, state assumptions, bounded deliverable' guidance.	2 / 5
Actionability	The skill repeatedly references 'scripts/main.py' as a packaged executable, but no scripts/ bundle exists, and the only commands shown (py_compile, --help) are verification rather than functional guidance; Parameters and Returns are vague labels with no real invocation example or output schema.	2 / 5
Workflow Clarity	The 5-step Workflow is abstract ('Confirm the user objective...', 'Validate that the request matches the documented scope') with no real validation checkpoint for batch/destructive image operations; the per-rubric destructive/batch cap of 3 applies, and the missing checkpoints and rough sequence pull it to 2.	2 / 5
Progressive Disclosure	No references/, scripts/, or assets/ directories exist, yet the body repeatedly references scripts/main.py and external structure as if present; all content is inlined in a single monolithic file with buried, non-functional references rather than real one-level-deep split files.	2 / 5
	Total	8 / 20 Passed

Description

25%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description identifies a domain but fails to specify concrete capabilities, omits any 'when to use' trigger, and leans on generic process boilerplate that overlaps heavily with other skills.

Suggestions

Replace the generic process phrasing with concrete actions the skill performs, e.g. 'Detect and extract tissue regions of interest from whole-slide images (WSI), export cropped tiles, and report ROI coordinates and tissue-percentage metrics.'

Add an explicit trigger clause such as 'Use when working with whole-slide images (.svs, .ndpi, .tiff), pathology ROI selection, or generating AI training patches from WSI files.'

Include natural user-facing synonyms and file extensions (WSI, ROI, tumor/normal regions, 20x/40x magnification) so the skill matches the phrasing users actually employ.

Dimension	Reasoning	Score
Specificity	The description names the domain ('pathology roi selector') but lists no concrete actions, relying instead on generic process language ('structured execution, explicit assumptions, and clear output boundaries') that describes any data-analysis workflow rather than what the skill actually does (region detection, coordinate extraction, cropping).	2 / 5
Completeness	It offers a vague 'what' with no 'when' clause: there is no explicit trigger scenario for when to use the skill, and the per-rubric guideline caps completeness at 3 for a missing 'Use when...' clause, with the additionally vague 'what' pulling it down to 2.	2 / 5
Trigger Term Quality	Only the keyword 'pathology' is present and it is buried mid-sentence; natural user terms like 'whole slide image', 'WSI', 'ROI', 'tumor regions', or 'tissue detection' are entirely absent, and the surrounding phrasing ('data analysis workflows that need structured execution') is abstract jargon users would not say.	2 / 5
Distinctiveness Conflict Risk	The bulk of the description ('data analysis workflows that need structured execution, explicit assumptions, and clear output boundaries') is broadly applicable to almost any analytical skill, leaving only 'pathology roi' to distinguish it, which produces high overlap risk with similar data-analysis skills.	2 / 5
	Total	8 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 9 missing	Warning

	Total	14 / 16 Passed

Repository: aipoch/medical-research-skills
Path: scientific-skills/Data Analysis/pathology-roi-selector/SKILL.md
Commit: 63c61d3

Reviewed: 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.