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

82%

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

65%

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

The content is highly actionable with concrete tools, code, and thresholds in a clear 8-phase workflow. Its weaknesses are missing validation checkpoints in the workflow and inline-heavy content referencing bundle files that do not exist.

Suggestions

Add explicit validation/verification checkpoints (e.g., 'verify alignment before clustering', 'confirm FDR filtering passed') to satisfy workflow-clarity feedback loops and lift that dimension.

Provide the missing code_examples.md and report_template.md bundle files, or move the inlined HuBMAP biospecimen and ToolUniverse tool-catalog material into them, so references resolve and the body stays an overview.

Trim tutorial-style interpretation prose (e.g., 'Spatial data adds location to expression...') that restates concepts Claude already knows to improve conciseness.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with concrete tool calls, but several sections restate concepts Claude already knows ("Spatial data adds location to expression. The key question...", lengthy interpretation prose), so it could be tightened. Not a 1 because most content is actionable, not padding.	2 / 3
Actionability	Provides executable Python (HuBMAP calls), specific tool names with params, and concrete thresholds (min 200 genes, min 500 UMI, <20% MT, Moran's I > 0.3, FDR < 0.05). Not below 3 because guidance is copy-paste ready, not pseudocode.	3 / 3
Workflow Clarity	The 8-phase sequence is clear and ordered, but there are no explicit validation/verification checkpoints or validate-then-proceed feedback loops, which the rubric caps at 2 for multi-step risky operations. Not a 1 because the sequence is present and well-ordered.	2 / 3
Progressive Disclosure	References code_examples.md and report_template.md as one-level-deep pointers, but those bundle files are not present in the package, and lengthy material (HuBMAP biospecimen layer, ToolUniverse tool catalog) is inlined that would fit better in separate files. Not a 1 because references are signaled and not deeply nested.	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.

The description is specific, covers natural trigger terms, and explicitly states both capability and use conditions, with a distinct spatial-transcriptomics niche. It is a strong, concise description.

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" — matching the multiple-specific-actions anchor.	3 / 3
Completeness	Explicitly answers both what (maps expression to architecture, identifies SVGs, segments domains, infers interactions) and when ("Use for spatial gene-expression questions, tissue architecture analysis, and SVG identification").	3 / 3
Trigger Term Quality	Includes natural user-facing terms ("spatial transcriptomics", "spatial gene-expression questions", "tissue architecture analysis", "SVG identification") plus platform names a user would plausibly say. Not below 3 because coverage is broad, not just jargon.	3 / 3
Distinctiveness Conflict Risk	A clear niche (spatial transcriptomics on named platforms) with distinct triggers unlikely to fire for unrelated skills. Not below 3 because the domain and platforms are specific enough to avoid overlap.	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
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: 089eb8e

Reviewed: about 9 hours 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.