tooluniverse-image-analysis

Microscopy and quantitative imaging analysis — colony morphometry, fluorescence intensity quantification, cell-count statistics, dose-response curves, and ANOVA/Dunnett on image-derived measurements. Uses pandas/numpy/scipy/scikit-image. Use for analyzing tabular outputs from CellProfiler/ImageJ, image-derived measurement statistics, and image-based assay quantification.

Quality

80%

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

Quality

Content

68%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 highly actionable with executable examples and a clear decision tree, but loses points for duplicated percentage guidance and missing validation feedback loops in a batch-processing workflow. One reference points to scripts not present in the bundle.

Suggestions

Consolidate the duplicated 'relative proportion of A to B' guidance into a single section; remove the standalone 'Production-ready skill...' line that repeats the description's package list.

Add explicit validation checkpoints to the workflow (e.g. verify loaded DataFrame shape/columns, confirm N per group before running ANOVA/Dunnett) and a validate-then-fix feedback loop for batch image processing.

Reconcile the References section with the actual bundle: remove or add `colony_morphometry.py` and `statistical_comparison.py`, which are listed but not present in scripts/.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with code blocks and tables, but the 'relative proportion of A to B' guidance is duplicated across the RULE ZERO critical section and the Answer Formatting section, and the standalone 'Production-ready skill...' line repeats the description's package list. Not a 4 because the duplication is noticeable padding.	3 / 5
Actionability	Copy-paste-ready code (e.g. `count_cells_in_image(image_path="cells.tif", channel=0, min_area=50)`), a Common Patterns table mapping example questions to workflows, and concrete R-to-Python equivalents fully cover the common cases.	5 / 5
Workflow Clarity	A clear decision tree and phased workflow exist, but there are no explicit validation checkpoints or error-recovery feedback loops, and the skill drives batch image processing — the batch-operations cap holds this at 3. Not a 4 because validation is implicit rather than stated.	3 / 5
Progressive Disclosure	Good structure with one-level-deep references ('See references/statistical_analysis.md', segmentation/cell_counting/image_processing docs) and a References section listing scripts and docs. Not a 5 because the References section lists `colony_morphometry.py` and `statistical_comparison.py` scripts that do not exist in the bundle.	4 / 5
	Total	15 / 20 Passed

Description

92%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.

A strong description that clearly states concrete capabilities and provides an explicit 'Use for...' trigger clause scoped to microscopy imaging analysis. Minor room to add file extensions and synonyms for trigger terms.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions — 'colony morphometry, fluorescence intensity quantification, cell-count statistics, dose-response curves, and ANOVA/Dunnett' — giving comprehensive coverage of what the skill does.	5 / 5
Completeness	Explicitly answers both 'what' (the analysis actions) and 'when' via a concrete 'Use for analyzing tabular outputs from CellProfiler/ImageJ, image-derived measurement statistics, and image-based assay quantification' clause with trigger phrases.	5 / 5
Trigger Term Quality	Good natural-term coverage including tool names ('CellProfiler/ImageJ') and phrases ('image-based assay quantification', 'tabular outputs'), but lacks file extensions and a few common synonyms. Not a 5 because no file extensions like .csv/.tif are mentioned.	4 / 5
Distinctiveness Conflict Risk	Clear niche (microscopy/quantitative imaging) with distinct triggers (CellProfiler, ImageJ, image-derived measurements); the statistics scope is explicitly tied to imaging, minimizing conflict with general stats skills.	5 / 5
	Total	19 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: mims-harvard/ToolUniverse
Path: plugin/skills/tooluniverse-image-analysis/SKILL.md
Commit: 1b02920

Reviewed: 1 day 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.