CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

67

Quality

81%

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

The canonical home for this skill is tooluniverse-spatial-transcriptomics in mims-harvard/ToolUniverse

SKILL.md
Quality
Evals
Security

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.

The body delivers strong, concrete guidance with a clear multi-phase workflow and executable tool calls, but it is somewhat padded (intro redundancy, Workflow Overview/Phase Summaries overlap) and its progressive disclosure is undermined by references to bundle files that are not actually present.

Suggestions

Provide the referenced bundle files (code_examples.md, report_template.md) or remove the links, since following them currently leads nowhere.

Collapse the 'Workflow Overview' ASCII diagram and the 'Phase Summaries' into a single sequenced section to eliminate duplication and save tokens.

Move the long HuBMAP tool catalog and/or the Reasoning Framework into separate reference files to keep SKILL.md a lean overview.

DimensionReasoningScore

Conciseness

Mostly efficient with real domain specifics (tool names, QC thresholds, organ codes), but the intro paragraph restates the description and the ASCII 'Workflow Overview' overlaps heavily with the 'Phase Summaries' section, so it could be tightened.

3 / 5

Actionability

Provides concrete executable guidance — parameterized tool calls like HuBMAP_search_samples(organ="LK", sample_category="block", registered_only=True, limit=5), explicit QC numbers, and runnable scanpy code blocks — with minor gaps where some phases are described only at a high level inline.

4 / 5

Workflow Clarity

The Phase 1-8 sequence with an ASCII flow diagram and embedded thresholds (min 200 genes, 500 UMI, <20% MT, FDR<0.05) is clearly ordered with most checkpoints present, but explicit validate->fix->retry feedback loops are not spelled out.

4 / 5

Progressive Disclosure

Sections are well-organized and reference links are clearly signaled one level deep, but the referenced files (code_examples.md, report_template.md) do not exist in any bundle directory, and large chunks that could be separate files (the HuBMAP tool catalog, the Reasoning Framework) are inlined.

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.

The description is third-person, concise, and explicit: it names concrete capabilities and platforms, then gives a clear 'Use for' trigger clause. It cleanly satisfies all four dimensions without padding or over-claims.

DimensionReasoningScore

Specificity

Lists multiple concrete actions ('Maps gene expression to tissue architecture, identifies spatially variable genes (SVGs), tissue-domain segmentation, and cell-cell interaction inference') plus four named platforms, giving comprehensive coverage rather than just 1-2 actions.

5 / 5

Completeness

Explicitly answers both what ('Maps gene expression... identifies SVGs... segmentation... cell-cell interaction inference') and when ('Use for spatial gene-expression questions, tissue architecture analysis, and SVG identification') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Covers natural user terms including platform names (Visium, MERFISH, seqFISH, Slide-seq), 'spatial gene-expression', 'tissue architecture', and 'SVG' synonyms; a user would naturally say these when asking for this skill.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear spatial-transcriptomics niche with platform-specific triggers, distinct from general single-cell or gene-enrichment skills; minimal conflict risk.

5 / 5

Total

20

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 3 missing

Warning

Total

15

/

16

Passed

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.