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.

68

Quality

82%

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

SKILL.md
Quality
Evals
Security

Quality

Content

65%

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

A well-organized, mostly actionable skill body with strong executable code and a useful pre-computed-results checkpoint. It loses points for restated guidance, Phases 1-3 delegated without inline checkpoints, and a References section that names files not present in the bundle.

Suggestions

Deduplicate the 'relative proportion of A to B → percentage' guidance into a single canonical section and cross-reference it once instead of restating it in both the CRITICAL block and Answer Formatting.

Inline at least the key validation/test step for Phases 1-3 (e.g., a grouped_summary → Dunnett's → report sequence with an explicit sanity check) instead of fully deferring to references/statistical_analysis.md.

Reconcile the References list with the actual bundle: remove or create the missing colony_morphometry.py and statistical_comparison.py, and add inline links from the body to fluorescence_analysis.md and troubleshooting.md so every listed file is discoverable.

DimensionReasoningScore

Conciseness

Mostly lean with executable code and no padding about what imaging/microscopy is, but the 'relative proportion → percentage' guidance is restated twice (the CRITICAL block near the top and again in Answer Formatting), so it is not maximally tight. Not level 3 because of that redundancy; not level 1 because it does not explain basic concepts Claude already knows.

2 / 3

Actionability

Provides fully executable, copy-paste-ready code (e.g. `from scripts.segment_cells import count_cells_in_image; result = count_cells_in_image(...)` and concrete `glob`/pandas loading), plus specific formatting recipes like `int(round(val, -3))`. This matches the highest anchor rather than the pseudocode (level 2) or vague (level 1) tiers.

3 / 3

Workflow Clarity

The decision tree and RULE ZERO pre-computed-results checkpoint give a clear sequence, but Phases 1-3 are only summarized as 'See references/statistical_analysis.md' rather than enumerated inline, leaving implicit checkpoints. Not level 3 (checkpoints not fully explicit) and not level 1 (sequence is present with at least one validation gate).

2 / 3

Progressive Disclosure

Body inline references are well-signaled and one level deep, but the References section lists scripts that do not exist in ./scripts/ (colony_morphometry.py, statistical_comparison.py — only 3 of 5 listed scripts are present) and several docs (fluorescence_analysis.md, troubleshooting.md) are listed but never linked from the body. This is structure-with-imperfections rather than the clean, fully-navigable level 3.

2 / 3

Total

9

/

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.

A strong, third-person description that names concrete capabilities, supplies natural trigger terms, and explicitly states when to use it. It is clearly scoped to a distinct microscopy-quantification niche.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'colony morphometry, fluorescence intensity quantification, cell-count statistics, dose-response curves, and ANOVA/Dunnett on image-derived measurements' — matching the highest anchor rather than the partial 'Names domain and some actions' level 2.

3 / 3

Completeness

Explicitly answers both 'what' (the enumerated analysis actions) and 'when' via the 'Use for analyzing tabular outputs from CellProfiler/ImageJ...' clause, satisfying the explicit-trigger requirement rather than capping at 2.

3 / 3

Trigger Term Quality

Covers natural user-facing terms like 'CellProfiler/ImageJ', 'image-derived measurement statistics', and 'image-based assay quantification', giving good coverage of phrasings a user would actually say; not generic jargon (level 1) and not missing common variations (level 2).

3 / 3

Distinctiveness Conflict Risk

The microscopy/imaging quantification niche with CellProfiler/ImageJ triggers is clearly distinct and unlikely to fire for the wrong skill; it is not generic (level 1) nor merely 'Works with document files'-level overlap (level 2).

3 / 3

Total

12

/

12

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.