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-scientific-problem-selectiongit 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-scientific-problem-selection)<a href="https://agentmods.dev/skills/mims-harvard/tooluniverse/tooluniverse-scientific-problem-selection"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-scientific-problem-selection/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-scientific-problem-selection"><img src="https://agentmods.dev/badge/skills/mims-harvard/tooluniverse/tooluniverse-scientific-problem-selection.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00137 | $0.02118 |
| Opus 5.5 | $0.00055 | $0.00847 |
| Sonnet 5.5 | $0.00027 | $0.00424 |
| Haiku 4.5 | $0.00014 | $0.00212 |
Grade A, and why
tooluniverse-scientific-problem-selection 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scientific Problem Selection
A structured conversation for the decision that happens before any experiment, dataset pull, or analysis: which problem is actually worth the next few months (or years) of work. Problem choice dominates outcome more than execution quality — a well-executed answer to a low-value question is still a low-value result.
LOOK UP, DON'T GUESS: Every claim about novelty, precedent, or fundability in this skill must be checked against real tools, not asserted from memory. See references/precedent-checking.md for the exact tool names and when to call each one.
When to Use This Skill
Apply when users:
- Pitch a new project idea and want it stress-tested before committing time to it
- Say they are stuck, blocked, or a project stopped working and they need to decide what to do next
- Ask a strategic question about which of several directions to pursue
- Want a risk assessment, feasibility gut-check, or "is this a good use of the next N months" opinion
- Are preparing to write a grant or thesis proposal and need the underlying idea sharpened first
- Ask to define success metrics, decide what to hold fixed vs. leave flexible in a study design, or plan a decision tree for an ongoing project
NOT for (route elsewhere):
- Clinical trial feasibility scoring on a specific indication/drug →
tooluniverse-clinical-trial-design - Pure literature synthesis with no strategy decision attached →
tooluniverse-literature-deep-research - NIH portfolio, funding trend, or PI/institution analysis →
tooluniverse-nih-funding-landscape - Drug target or disease biology deep dives →
tooluniverse-target-research,tooluniverse-disease-research
This skill produces a decision framework and a short written artifact. It does not run wet-lab or computational experiments itself — it decides whether they're worth running.
Three Entry Points
Start every conversation by finding out which of these three the user actually needs — do not assume:
What ships with it
4 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 First seen · 116 lines · 137 tokens per session scan A 42c06ed9f828
tooluniverse-scientific-problem-selection is a skill published in the GitHub repository mims-harvard/ToolUniverse (1,744 stars, last pushed yesterday), licensed Apache-2.0. It adds 137 tokens to every session and 2,118 once invoked, about $0.0005 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 2026-10-07.
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.