tooluniverse-spatial-transcriptomics

Spatial transcriptomics analysis — Visium, MERFISH, seqFISH, Slide-seq. Maps gene expression to tissue architecture, identifies spatially variable genes (SVGs), tissue-domain segmentation, and cell-cell interaction inference. Use for spatial gene-expression questions, tissue architecture analysis, and SVG identification.

Quality

81%

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

63%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, actionable skill body with a clear 8-phase workflow and concrete tool/parameter guidance, but it is padded with conceptual reasoning sections Claude does not need and relies on reference files that are absent from the bundle.

Suggestions

Trim or move the Reasoning Framework, Evidence Grading, Interpretation Guidance, and Synthesis Questions sections into a separate reference file; keep only operationally essential guidance inline to improve token efficiency.

Provide the missing code_examples.md and report_template.md (or remove the dead links) so the 'Reference Files' pointers resolve to real bundle files.

Add explicit feedback loops for the QC and validation gates (e.g. 'if QC fails, re-examine low-quality spots and re-run') to lift workflow clarity toward full checkpoint coverage.

Dimension	Reasoning	Score
Conciseness	The operational core (workflow, tool names, QC thresholds, params) is efficient, but the Reasoning Framework, Evidence Grading (T1-T4), Interpretation Guidance, and Synthesis Questions sections explain biology and statistics Claude largely already knows and could be tightened.	3 / 5
Actionability	Provides concrete tool names with parameters (e.g. HuBMAP_search_samples(organ="LK", sample_category="block", registered_only=True)), specific QC thresholds, and executable scanpy snippets; minor gaps because the detailed per-phase code lives in a referenced code_examples.md.	4 / 5
Workflow Clarity	The 8-phase workflow is clearly sequenced with an ASCII diagram and validation checkpoints (QC filters in Phase 1, FDR<0.05 in Phase 4, marker-gene validation in Phase 6, alignment verification), but explicit validate->fix->retry feedback loops are not spelled out.	4 / 5
Progressive Disclosure	Good in-body structure with clear section headers and a dedicated 'Reference Files' section, but the 355-line body inlines content (tool catalog, reasoning framework) that belongs in separate files, and the two referenced files (code_examples.md, report_template.md) do not exist in the bundle — the references are dead.	3 / 5
	Total	14 / 20 Passed

Description

100%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, concise description that names the domain, lists concrete capabilities, and provides an explicit 'Use for' trigger clause with natural platform keywords. It is specific, complete, and clearly distinguishable from sibling skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Maps gene expression to tissue architecture, identifies spatially variable genes (SVGs), tissue-domain segmentation, and cell-cell interaction inference' — giving comprehensive coverage of the skill's analysis capabilities.	5 / 5
Completeness	Explicitly answers both what (the four analysis actions) and when ('Use for spatial gene-expression questions, tissue architecture analysis, and SVG identification') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes the natural platform names users say ('Visium, MERFISH, seqFISH, Slide-seq') plus synonyms ('SVGs' / 'spatially variable genes') and 'spatial gene-expression', covering the domain's natural trigger terms comprehensively.	5 / 5
Distinctiveness Conflict Risk	A clear niche — spatial transcriptomics with named platforms and specific analysis outputs — with distinct triggers and minimal overlap risk against other skills.	5 / 5
	Total	20 / 20 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
relative_links	Relative link issues: 3 missing	Warning

	Total	15 / 16 Passed

Repository: mims-harvard/ToolUniverse
Path: plugin/skills/tooluniverse-spatial-transcriptomics/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.