CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

62

Quality

73%

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

The canonical home for this skill is tooluniverse-image-analysis in mims-harvard/ToolUniverse

SKILL.md
Quality
Evals
Security

Quality

Content

53%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.

A well-structured overview with strong progressive disclosure to real reference files, but it is held back by a broken raw-image code example, duplicated percentage guidance, missing validation for batch operations, and two ghost script references.

Suggestions

Fix the raw-image example: count_cells_in_image does not exist in scripts/segment_cells.py — replace it with the actual count_cells_watershed or count_cells_basic signature so the example is executable.

De-duplicate the 'relative proportion -> percentage' guidance, which appears as both the top CRITICAL section and an Answer Formatting subsection; keep a single authoritative version.

Add validation checkpoints for batch/destructive operations (e.g., verify segmentation output before batch processing) and remove the two non-existent script references (colony_morphometry.py, statistical_comparison.py) from the References section.

DimensionReasoningScore

Conciseness

Mostly efficient with useful tables and a decision tree, but the 'relative proportion -> percentage' guidance is duplicated (CRITICAL section and Answer Formatting subsection) and the abstract 'Core Principles' list pads, so it could be tightened.

3 / 5

Actionability

Contains substantial executable code (Phase 0, imports, R-to-Python equivalents, formatting), but the flagship raw-image example imports count_cells_in_image, a function that does not exist in scripts/segment_cells.py, so the copy-paste example fails.

3 / 5

Workflow Clarity

A clear sequence exists (RULE ZERO -> decision tree -> phases), but there are no validation/feedback checkpoints, and batch operations (batch_process.py) lack validation, capping this at 3 per the batch-operations rule.

3 / 5

Progressive Disclosure

Good one-level-deep structure with well-signaled .md references that all resolve, but the References section lists two non-existent scripts (colony_morphometry.py, statistical_comparison.py) and troubleshooting.md is unreferenced.

4 / 5

Total

13

/

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, specific description that clearly conveys both capabilities and trigger conditions with natural domain terms. The only notable gap is the absence of file extensions and synonyms in the trigger-term coverage.

DimensionReasoningScore

Specificity

Names five concrete analytical actions (colony morphometry, fluorescence intensity quantification, cell-count statistics, dose-response curves, ANOVA/Dunnett) plus the toolchain, matching the 'multiple specific concrete actions; comprehensive coverage' anchor.

5 / 5

Completeness

Explicitly states both what (enumerated analysis actions) and when ('Use for analyzing tabular outputs from CellProfiler/ImageJ, image-derived measurement statistics, and image-based assay quantification'), matching the anchor with concrete trigger phrases.

5 / 5

Trigger Term Quality

Strong natural domain terms (microscopy, fluorescence, cell-count, dose-response) and software names users say (CellProfiler/ImageJ), but file extensions (.tif/.csv) and synonyms are absent, keeping it below the comprehensive-coverage anchor.

4 / 5

Distinctiveness Conflict Risk

Scoped specifically to image-derived measurements and image-based assays — a clear niche with distinct triggers and minimal overlap with generic statistics skills.

5 / 5

Total

19

/

20

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
mims-harvard/ToolUniverse
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.