tooluniverse-image-analysis

Production-ready microscopy image analysis and quantitative imaging data skill for colony morphometry, cell counting, fluorescence quantification, and statistical analysis of imaging-derived measurements. Processes ImageJ/CellProfiler output (area, circularity, intensity, cell counts), performs Dunnett's test, Cohen's d effect size, power analysis, Shapiro-Wilk normality tests, two-way ANOVA, polynomial regression, natural spline regression with confidence intervals, and comparative morphometry. Supports CSV/TSV measurement tables, multi-channel fluorescence data, colony swarming assays, and neuron counting datasets. Use when analyzing microscopy measurement data, colony area/circularity, cell count statistics, swarming assays, co-culture ratio optimization, or answering questions about imaging-derived quantitative data.

Quality

71%

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 ./skills/med/tooluniverse-image-analysis/SKILL.md

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-structured with a strong decision tree and phased workflow, but it is verbose for a claimed overview and, critically, every referenced bundle file (references/*.md and scripts/*.py) is missing, breaking progressive disclosure and weakening actionability.

Suggestions

Add the missing references/*.md (statistical_analysis.md, cell_counting.md, segmentation.md, fluorescence_analysis.md, image_processing.md, troubleshooting.md) and scripts/*.py (segment_cells.py, measure_fluorescence.py, batch_process.py, colony_morphometry.py, statistical_comparison.py) so signaled references resolve.

Trim redundancy: drop or merge the Quick Reference Table and the 'Detailed Reference Guides' list, since they restate references already cited inline in the decision tree and sections.

Add explicit validation/feedback steps (validate output, retry on failure) around batch and destructive operations like batch_process.py.

Dimension	Reasoning	Score
Conciseness	Mostly action-oriented but padded: the Quick Reference Table and 'Detailed Reference Guides' section restate the inline decision-tree references, and the body is long for an overview that claims to defer details to references/.	2 / 3
Actionability	Some executable code is present (grouped_summary, file-discovery snippet), but many pointers ('See references/statistical_analysis.md', 'scripts/segment_cells.py') reference bundle files that do not exist, so the guidance is partly non-executable.	2 / 3
Workflow Clarity	A clear decision tree and Phase 0-3 sequence exist plus a completeness checklist, but batch/destructive operations (batch_process.py) lack explicit validate->fix->retry feedback loops, capping this at 2.	2 / 3
Progressive Disclosure	The body signals one-level-deep references to references/.md and scripts/.py, but those directories do not exist in the bundle, so the disclosure structure is broken rather than real.	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.

The description is specific, complete, and well-triggered, with concrete actions and explicit use-when guidance tied to a distinctive microscopy-quantification niche. Its only minor weakness is verbosity, which the conciseness-oriented guidelines lightly disfavor.

Dimension	Reasoning	Score
Specificity	Lists many concrete actions ('Processes ImageJ/CellProfiler output', 'performs Dunnett's test', 'Cohen's d effect size', 'power analysis', 'natural spline regression') rather than vague language.	3 / 3
Completeness	Explicitly answers both what it does and when to use it via the 'Use when analyzing...' clause, satisfying the full what+when requirement.	3 / 3
Trigger Term Quality	Covers natural user-facing terms ('microscopy measurement data', 'colony area/circularity', 'cell count statistics', 'swarming assays', 'co-culture ratio optimization') that a user would actually say.	3 / 3
Distinctiveness Conflict Risk	The microscopy-imaging-quantification niche is specific with distinct triggers (colony morphometry, swarming assays, neuron counting) unlikely to conflict with other skills.	3 / 3
	Total	12 / 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
referenced_paths_exist	Referenced path issues: 27 missing	Warning

	Total	15 / 16 Passed

Repository: wu-yc/LabClaw
Path: skills/med/tooluniverse-image-analysis/SKILL.md
Commit: df37802

Reviewed: 2 days 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.