tooluniverse-spatial-omics-analysis

Computational analysis framework for spatial multi-omics data integration. Given spatially variable genes (SVGs), spatial domain annotations, tissue type, and disease context from spatial transcriptomics/proteomics experiments (10x Visium, MERFISH, DBiTplus, SLIDE-seq, etc.), performs comprehensive biological interpretation including pathway enrichment, cell-cell interaction inference, druggable target identification, immune microenvironment characterization, and multi-modal integration. Produces a detailed markdown report with Spatial Omics Integration Score (0-100), domain-by-domain characterization, and validation recommendations. Uses 70+ ToolUniverse tools across 9 analysis phases. Use when users ask about spatial transcriptomics analysis, spatial omics interpretation, tissue heterogeneity, spatial gene expression patterns, tumor microenvironment mapping, tissue zonation, or cell-cell communication from spatial data.

Quality

77%

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/bio/tooluniverse-spatial-omics-analysis/SKILL.md

Quality

Content

55%

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

Highly actionable and well-sequenced with excellent tool-parameter accuracy and validation checkpoints, but it is a monolithic ~1100-line document that is overly verbose and makes no use of progressive disclosure or bundle files. The skill would benefit substantially from splitting reference material into separate files and trimming Claude-known background.

Suggestions

Split the large reference tables (immune cell markers, ligand-receptor pairs, immune checkpoints, tool parameter reference) into separate files under references/ and link to them one level deep, keeping SKILL.md a concise overview.

Trim domain background Claude already knows (e.g., canonical cell-type marker lists, checkpoint biology) and remove duplicated tool-parameter descriptions that already appear in the parameter reference table.

Move the full report template into its own referenced file, retaining only the filename convention and section list in SKILL.md to reduce the inline markdown block.

Dimension	Reasoning	Score
Conciseness	At ~1100 lines the body is verbose and restates information Claude already knows (cell-type marker lists, ligand-receptor pairs, immune checkpoint tables, repeatedly enumerated tool parameters), padding the context budget rather than earning each token.	1 / 3
Actionability	Provides concrete, executable guidance: named tools with exact verified parameter names, response formats, a critical parameter-reference table flagging common mistakes, fallback strategies, and a copy-paste report template.	3 / 3
Workflow Clarity	Sequences work across 9 numbered phases each with an explicit workflow, includes a report-first 'validate progressively' loop, a mandatory completeness checklist, batch-size guidance, and decision logic with error/fallback handling.	3 / 3
Progressive Disclosure	No bundle files exist (references/scripts/assets absent) and the body is a monolithic wall of text with everything inline; the single inline report template and all reference material live in one file rather than being split into navigable one-level-deep references.	1 / 3
	Total	8 / 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 actions, explicit trigger terms, and a clear when-to-use clause. It is comprehensive without being padded and distinct from adjacent ToolUniverse skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions explicitly ('pathway enrichment, cell-cell interaction inference, druggable target identification, immune microenvironment characterization, and multi-modal integration'), matching the score-3 anchor.	3 / 3
Completeness	Clearly answers both what it does (the listed analyses and report output) and when to use it via an explicit 'Use when...' clause, matching the score-3 anchor.	3 / 3
Trigger Term Quality	Covers natural user phrasings the user would actually say: 'spatial transcriptomics analysis, spatial omics interpretation, tissue heterogeneity, spatial gene expression patterns, tumor microenvironment mapping, tissue zonation, or cell-cell communication from spatial data.'	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (spatial multi-omics integration) with distinct triggers and named platforms; unlikely to trigger for the non-spatial skills it distinguishes from.	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
skill_md_line_count	SKILL.md is long (1103 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

Repository: wu-yc/LabClaw
Path: skills/bio/tooluniverse-spatial-omics-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.