CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugin/skills/tooluniverse-spatial-transcriptomics/SKILL.md
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 is a dense, knowledgeable guide with concrete thresholds, named tools, and a well-sequenced 8-phase workflow. Its main weaknesses are token redundancy between the workflow diagram and phase summaries, and progressive disclosure: it points to two reference files that are absent from the bundle while inlining API-detail content that should itself be split out.

Suggestions

Ship the referenced files or remove the links: neither code_examples.md nor report_template.md exists in the bundle, so 'See [code_examples.md](code_examples.md)' and the report_template.md pointer currently dead-end.

Cut the redundancy between the ASCII workflow diagram and the Phase Summaries — keep the diagram as a map and move any detail that appears in both into the summaries only; also drop the restating intro paragraph and the generic 'Limitations' list.

Move the HuBMAP API details (samples/donors subsection, fallback examples) and the 'Programmatic Access' cookbook into a reference file, leaving SKILL.md as a navigable overview with one-level-deep pointers.

DimensionReasoningScore

Conciseness

Mostly efficient and rich in non-obvious information (ToolUniverse tool names, params, QC thresholds), but the intro paragraph restates the description, the ASCII workflow diagram and the Phase Summaries duplicate each other substantially, and sections like 'Limitations' list facts Claude already knows. This is 'mostly efficient but could be tightened' (anchor 3) rather than anchor 4, because the diagram/summary duplication alone accounts for ~40 redundant lines.

3 / 5

Actionability

Concrete, executable guidance throughout: specific QC thresholds ("min 200 genes, 500 UMI, <20% MT"), named tools with params ("OmniPath_get_ligand_receptor_interactions ... Use `partners` param"), and runnable Python snippets. Not anchor 5 because Phases 1–6 defer full pipelines to code_examples.md rather than including copy-paste-ready code, leaving minor gaps.

4 / 5

Workflow Clarity

A clearly sequenced 8-phase workflow with most checkpoints present: QC gates in Phase 1, "Filter significant spatial genes (FDR < 0.05)", "Validate with marker genes" in Phase 6, and a T1–T4 evidence-grading scheme. Not anchor 5 because some validations are implicit and no explicit fix-and-retry error-recovery loops are described.

4 / 5

Progressive Disclosure

References are clearly signaled one level deep ([code_examples.md](code_examples.md), [report_template.md](report_template.md)), but neither file exists in the bundle — no references/, scripts/, or assets/ directories are present — so the pointers are broken. Additionally, bulky material (HuBMAP API details, programmatic-access cookbook) is inlined in SKILL.md where it belongs in a reference file. This fits anchor 3 ('could be better organized; content that should be separate is inline') rather than anchor 4, since dangling reference paths exceed a minor organization gap.

3 / 5

Total

14

/

20

Passed

Description

88%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 description: third-person voice, concrete named actions, platform keywords, and an explicit 'Use for...' clause covering both what and when. Only minor gaps — a few natural trigger synonyms and slight overlap risk with sibling single-cell skills.

DimensionReasoningScore

Specificity

Quotes four concrete actions — "Maps gene expression to tissue architecture", "identifies spatially variable genes (SVGs)", "tissue-domain segmentation", "cell-cell interaction inference" — plus four platform names, giving comprehensive coverage of the skill's capabilities. This matches the anchor-5 example's breadth; it is not anchor 4 because no core capability from the body is unrepresented.

5 / 5

Completeness

Explicitly answers both: what ("Maps gene expression to tissue architecture, identifies spatially variable genes (SVGs), tissue-domain segmentation, and cell-cell interaction inference") and when ("Use for spatial gene-expression questions, tissue architecture analysis, and SVG identification"). Matches anchor 5's what+when pattern with concrete trigger phrases; not anchor 4 since the 'when' clause is already explicit and specific.

5 / 5

Trigger Term Quality

Good natural keywords — "spatial transcriptomics", "Visium", "MERFISH", "tissue architecture", "SVG" — that users would actually say. Not anchor 5 because common variations like "spatial data", "spatial omics", or dataset phrasings ("Visium dataset") are missing.

4 / 5

Distinctiveness Conflict Risk

Clear niche anchored by platform names (Visium, MERFISH, seqFISH, Slide-seq) and SVG-specific triggers, so it is mostly distinct. Not anchor 5 because deconvolution/cell-cell interaction territory overlaps with closely related single-cell analysis skills.

4 / 5

Total

18

/

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 3 missing

Warning

Total

15

/

16

Passed

Repository

mims-harvard/ToolUniverse

Path

plugin/skills/tooluniverse-spatial-transcriptomics/SKILL.md

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.