ToolUniverse is a collection of tools, interfaces, and supporting components for building AI systems that perform scientific work. It is for developers creating AI scientist agents that use APIs, databases, machine-learning tools, and domain-specific utilities. The catalogue includes skills, commands, an MCP server, an agent, and a hook for working with the ecosystem.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add mims-harvard/ToolUniverse --skill tooluniverse-spatial-transcriptomicsgit clone --depth 1 https://github.com/mims-harvard/ToolUniverseWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/mims-harvard/tooluniverse/tooluniverse-spatial-transcriptomics)<a href="https://agentmods.dev/skills/mims-harvard/tooluniverse/tooluniverse-spatial-transcriptomics"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-spatial-transcriptomics/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/mims-harvard/tooluniverse/tooluniverse-spatial-transcriptomics"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-spatial-transcriptomics.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk warn
- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Data Exfiltration · line 320 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00070 | $0.04600 |
| Opus 5.5 | $0.00028 | $0.01840 |
| Sonnet 5.5 | $0.00014 | $0.00920 |
| Haiku 4.5 | $0.00007 | $0.00460 |
Grade A, and why
tooluniverse-spatial-transcriptomics scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 361 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spatial Transcriptomics Analysis
Comprehensive analysis of spatially-resolved transcriptomics data to understand gene expression patterns in tissue architecture context. Combines expression profiling with spatial coordinates to reveal tissue organization, cell-cell interactions, and spatially variable genes.
LOOK UP, DON'T GUESS
When uncertain about any scientific fact, SEARCH databases first rather than reasoning from memory. A database-verified answer is always more reliable than a guess.
When to Use This Skill
Triggers:
- User has spatial transcriptomics data (Visium, MERFISH, seqFISH, etc.)
- User has only an H&E histology image and no spatial assay at all --
DeepSpotM_predict_gene_expression(local model, no API/key) predicts spatial gene expression for a 224x224 H&E tile directly, a virtual readout when no real spatial data exists yet. Treat its output as a model prediction to guide follow-up (e.g. which region to actually assay), not a substitute for the platforms above when real spatial data is the goal. - Questions about tissue architecture or spatial organization
- Spatial gene expression pattern analysis
- Cell-cell proximity or neighborhood analysis requests
- Tumor microenvironment spatial structure questions
- Integration of spatial with single-cell data
- Spatial domain identification
- Tissue morphology correlation with expression
Example Questions:
- "Analyze this 10x Visium dataset to identify spatial domains"
- "Which genes show spatially variable expression in this tissue?"
- "Map the tumor microenvironment spatial organization"
- "Find genes enriched at tissue boundaries"
- "Identify cell-cell interactions based on spatial proximity"
- "Integrate spatial transcriptomics with scRNA-seq annotations"
Core Capabilities
- Data Import: 10x Visium, MERFISH, seqFISH, Slide-seq, STARmap, Xenium formats
- Quality Control: Spot/cell QC, spatial alignment verification, tissue coverage
- Normalization: Spatial-aware normalization accounting for tissue heterogeneity
- Spatial Clustering: Identify spatial domains with similar expression profiles
- Spatial Variable Genes: Find genes with non-random spatial patterns
- Neighborhood Analysis: Cell-cell proximity, spatial neighborhoods, niche identification
- Integration: Merge with scRNA-seq for cell type mapping (Cell2location, Tangram, SPOTlight)
- Ligand-Receptor Spatial: Map cell communication in tissue context via OmniPath
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago Changed · +4 lines 32d567377fab
- 1mo ago Changed · +1 lines 58d25a09a93c
- 1mo ago First seen · 356 lines · 70 tokens per session scan A ad2cc5a6ce0f
tooluniverse-spatial-transcriptomics is a skill published in the GitHub repository mims-harvard/ToolUniverse (1,744 stars, last pushed yesterday), licensed Apache-2.0. It adds 70 tokens to every session and 4,600 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
ai-agent-tool-routing
Use when designing or reviewing an AI agent tool registry or MCP router: document parameter schemas, caller authorization, execution limits, replay-safe retries and verification evidence.
nanoresearch-writing
Draft a LaTeX research paper from all previous stage outputs.
construct-toy-examples
Generate and analyze simpler examples that satisfy both the assumptions and the conclusion of a theorem statement or subgoal. Use when you are stuck in reasoning and need simpler examples to regain traction, or when you want to see where the assumptions take effect and gain intuition.
obtain-immediate-conclusions
Derive immediate mathematical consequences from a theorem statement or subgoal. Use when starting a new problem, branch, or subgoal, or when cheap progress or a cleaner reformulation is needed before deeper proof search.
clinical-research-analysis-framework
Guided workflow for statistical and ML analysis of clinical data. Use when planning or executing research analyses on MIMIC, eICU, or similar EHR data. Ensures methodological rigor through structured consultation, assumption checking, and stepwise execution with audit trails.
apache-iv-score
Calculate APACHE IV (Acute Physiology and Chronic Health Evaluation IV) score for ICU mortality prediction. Use for severity assessment, hospital mortality prediction, ICU benchmarking, or case-mix adjustment. eICU has pre-computed scores; MIMIC-IV requires custom implementation with diagnosis mapping challenges.