Agent skill

Tooluniverse

by lamm-mit in lamm-mit/scienceclaw

Access 1000+ scientific tools from Harvard's ToolUniverse — bioinformatics, drug discovery, genomics, clinical research, and more

Apache-2.0Auto-check passedResearch & Science

Install Tooluniverse

skills CLI
$ npx skills add lamm-mit/scienceclaw --skill tooluniverse -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install lamm-mit/scienceclaw tooluniverse --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/lamm-mit/scienceclaw.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/tooluniverse .claude/skills/tooluniverse && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
tooluniverse
GitHub stars
244
Token cost
~950 tokens
SKILL.md length
210 words
Files
6 (incl. scripts)
Skills in repo
86
Repo updated
First seen
Licence
Apache-2.0

At a glance

Access 1000+ scientific tools from Harvard's ToolUniverse — bioinformatics, drug discovery, genomics, clinical research, and more

  • Tasks that involve Bioinformatics
  • SKILL.md covers Overview, Usage, Parameters (tooluniverse_run.py) and Available Research Workflows…, plus 3 more sections
  • Runs Python scripts from its folder; calls python3 and pip
  • Tasks that involve Drug discovery and cheminformatics

What it does

Tooluniverse is an agent skill from lamm-mit/scienceclaw. Access 1000+ scientific tools from Harvard's ToolUniverse — bioinformatics, drug discovery, genomics, clinical research, and more

Its SKILL.md is about 950 tokens, which your agent loads only when the skill is triggered. The skill folder holds 7 other files, including scripts (for example `scripts/tooluniverse_run.py`, `scripts/tooluniverse_search.py` and `setup_tu_skills.py`).

It sits in Research & Science, covering Bioinformatics, Drug discovery and cheminformatics and Clinical and healthcare research. The licence is Apache-2.0.

When your agent uses it

  • Tasks that involve Bioinformatics
  • Tasks that involve Drug discovery and cheminformatics
  • Tasks that involve Clinical and healthcare research

Example prompts

  • “/tooluniverse”

Requirements

  • Python 3

What it can do on your machine

Read from SKILL.md and the folder at commit ab9aba1. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 4 files in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python3
    • pip

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use pip, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Tooluniverse loads about 950 tokens when it runs. Until then it costs about 36 tokens; SKILL.md has 210 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~36
When it runs · the whole SKILL.md, loaded when a task matches
~950

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from lamm-mit/scienceclaw at commit ab9aba1, republished under its Apache-2.0 licence (© lamm-mit). 210 words, ~950 tokens.

Download SKILL.mdSave it as .claude/skills/tooluniverse/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.
name
tooluniverse
description
Access 1000+ scientific tools from Harvard's ToolUniverse — bioinformatics, drug discovery, genomics, clinical research, and more

ToolUniverse

Gateway to 1000+ machine learning models, databases, APIs, and scientific packages via Harvard's ToolUniverse ecosystem. Covers drug discovery, genomics, proteomics, clinical research, metabolomics, multi-omics, and more.

Overview

ToolUniverse standardizes access to scientific tools through a unified tu.run() interface. This skill wraps that interface so agents can call any ToolUniverse tool and receive JSON output compatible with the scienceclaw artifact system.

Usage

Run any ToolUniverse tool:
bash
python3 {baseDir}/scripts/tooluniverse_run.py --tool UniProt_get_entry_by_accession \
    --args '{"accession": "P05067"}'
Discover available tools:
bash
python3 {baseDir}/scripts/tooluniverse_list.py
python3 {baseDir}/scripts/tooluniverse_list.py --search "compound"
python3 {baseDir}/scripts/tooluniverse_list.py --search "protein" --format json
python3 {baseDir}/scripts/tooluniverse_list.py --info PubChem_get_compound_properties_by_CID

Parameters (tooluniverse_run.py)

ParameterDescriptionDefault
--toolToolUniverse tool name (exact, case-sensitive)Required
--argsTool arguments as a JSON string{}
--formatOutput format: json, summaryjson
--no-cacheDisable result cachingfalse

Available Research Workflows (54+)

Drug Discovery
  • binder-discovery, drug-repurposing, drug-target-validation, drug-drug-interaction
  • chemical-safety, network-pharmacology, pharmacovigilance, adverse-event-detection
Genomics & Variants
  • gwas-trait-to-gene, gwas-snp-interpretation, gwas-fine-mapping, gwas-study-explorer
  • variant-analysis, variant-interpretation, structural-variant-analysis
  • crispr-screen-analysis, cancer-variant-interpretation
Omics & Transcriptomics
  • rnaseq-deseq2, single-cell, epigenomics, spatial-transcriptomics
  • proteomics-analysis, metabolomics, metabolomics-analysis
  • multi-omics-integration, gene-enrichment, expression-data-retrieval
Disease & Clinical
  • disease-research, rare-disease-diagnosis, clinical-trial-matching
  • clinical-trial-design, clinical-guidelines, precision-oncology
  • precision-medicine-stratification, immunotherapy-response-prediction, infectious-disease
Proteins & Sequences
  • sequence-retrieval, protein-structure-retrieval, protein-interactions
  • protein-therapeutic-design, antibody-engineering, phylogenetics
Systems Biology
  • systems-biology, immune-repertoire-analysis, polygenic-risk-score
  • gwas-drug-discovery, multiomic-disease-characterization, statistical-modeling
Data Retrieval
  • chemical-compound-retrieval, target-research, literature-deep-research

Examples

bash
# Retrieve protein entry
python3 {baseDir}/scripts/tooluniverse_run.py \
    --tool UniProt_get_entry_by_accession --args '{"accession": "P05067"}'

# Get compound properties
python3 {baseDir}/scripts/tooluniverse_run.py \
    --tool PubChem_get_compound_properties_by_CID --args '{"cid": 1983}'

# Search PubMed
python3 {baseDir}/scripts/tooluniverse_run.py \
    --tool PubMed_search_articles --args '{"query": "Alzheimer amyloid", "max_results": 10}'

# List tools related to GWAS
python3 {baseDir}/scripts/tooluniverse_list.py --search "gwas"

Installation

bash
pip install tooluniverse

Notes

  • Tool names are exact and case-sensitive — use tooluniverse_list.py to discover
  • Results are cached by default; use --no-cache for fresh data
  • All outputs are JSON for downstream tool chaining
  • Set API keys via environment variables as required by individual tools

© lamm-mit, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 5 other files (scripts) in skills/tooluniverse of lamm-mit/scienceclaw.

  • SKILL.md
  • scripts/__pycache__/tooluniverse_run.cpython-313.pyc
  • scripts/__pycache__/tooluniverse_search.cpython-313.pyc
  • scripts/tooluniverse_run.py
  • scripts/tooluniverse_search.py
  • setup_tu_skills.py

Open the folder on GitHubat commit ab9aba1

Compare with similar skills

Tooluniverse next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Tooluniverse compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Tooluniverse this skilllamm-mit/scienceclaw244—~950Automated safety check: PassApache-2.0
Biomedical Analysis Dispatchxjtulyc/MedgeClaw6171 repos~2kAutomated safety check: PassNone
Hcls Build Agentaws-samples/amazon-bedrock-agents-healthcare-lifesciences274—~885Automated safety check: PassMIT-0
Hcls Get Startedaws-samples/amazon-bedrock-agents-healthcare-lifesciences274—~607Automated safety check: PassMIT-0
Genomics Variant Interpretationaws-samples/amazon-bedrock-agents-healthcare-lifesciences274—~1.5kAutomated safety check: PassMIT-0
Biomnidavila7/claude-code-templates32k8 repos~2.4kAutomated safety check: NotesMIT

Similar skills

  • Routes bioinformatics, drug discovery, clinical and multi-omics tasks from a chat interface to Claude Code sessions running K-Dense scientific skills, with a live dashboard per task.

    617 GitHub starsUsed in 1 repo~2k tokens
    Research & ScienceAuto-check passed
  • Hcls Build Agent

    aws-samples/amazon-bedrock-agents-healthcare-lifesciences

    Official

    A skill your agent uses when a developer wants to build a new healthcare or life sciences agent, structure tools and system prompts for an HCLS workflow, or create a Strands agent with…

    274 GitHub stars~885 tokensUpdated 7 days ago
    Research & ScienceAuto-check passed
  • Hcls Get Started

    aws-samples/amazon-bedrock-agents-healthcare-lifesciences

    Official

    A skill your agent uses when a developer asks how to get started building healthcare or life sciences agents, wants to understand the HCLS Agents Toolkit, or asks what's available in this repository.

    274 GitHub stars~607 tokensUpdated 7 days ago
    Research & ScienceAuto-check passed
  • Genomics Variant Interpretation

    aws-samples/amazon-bedrock-agents-healthcare-lifesciences

    Official

    A skill your agent uses when interpreting genomic variants from VCF files, performing clinical variant classification using ClinVar/VEP annotations, analyzing allele frequencies against population…

    274 GitHub stars~1.5k tokensUpdated 7 days ago
    Research & ScienceAuto-check passed
  • Biomni

    davila7/claude-code-templates

    Autonomous biomedical AI agent framework for executing complex research tasks across genomics, drug discovery, molecular biology, and clinical analysis.

    32k GitHub starsUsed in 8 repos~2.4k tokens
    Research & ScienceAuto-check: notes
  • Tooluniverse

    AgentTeam-TaichuAI/ScienceClaw

    Access 1000+ scientific tools through ToolUniverse for drug discovery, protein analysis, genomics, literature search, clinical data, ADMET prediction, molecular docking, and more.

    671 GitHub stars~1.2k tokensUpdated 5 mo ago
    Research & ScienceAuto-check passed

More from lamm-mit/scienceclaw

All 86 skills in this repo
  • Fred Economic Data

    lamm-mit/scienceclaw

    Query FRED (Federal Reserve Economic Data) API for 800,000+ economic time series from 100+ sources.

    244 GitHub starsUsed in 4 repos~3k tokens
    Auto-check passed
  • Drug Research

    lamm-mit/scienceclaw

    Generates comprehensive drug research reports with compound disambiguation, evidence grading, and mandatory completeness sections.

    244 GitHub starsUsed in 3 repos~1.7k tokens
    Auto-check passed
  • Imaging Data Commons

    lamm-mit/scienceclaw

    Query and download public cancer imaging data from NCI Imaging Data Commons using idc-index.

    244 GitHub starsUsed in 5 repos~11k tokens
    Auto-check passed
  • Rowan

    lamm-mit/scienceclaw

    Cloud-based quantum chemistry platform with Python API. An agent skill from lamm-mit/scienceclaw.

    244 GitHub starsUsed in 4 repos~3.1k tokens
    Auto-check: warnings
  • Infographics

    lamm-mit/scienceclaw

    Create professional infographics using Nano Banana Pro AI with smart iterative refinement.

    244 GitHub starsUsed in 6 repos~4.4k tokens
    Auto-check: notes
  • Disease Research

    lamm-mit/scienceclaw

    Generate comprehensive disease research reports using 100+ ToolUniverse tools.

    244 GitHub stars~946 tokensUpdated 1 mo ago
    Auto-check passed

Questions about Tooluniverse

What does Tooluniverse do?

Access 1000+ scientific tools from Harvard's ToolUniverse — bioinformatics, drug discovery, genomics, clinical research, and more. Tooluniverse is an agent skill from lamm-mit/scienceclaw.

When should I use Tooluniverse?

Tooluniverse fits situations like: tasks that involve Bioinformatics; tasks that involve Drug discovery and cheminformatics; tasks that involve Clinical and healthcare research.

How do I install Tooluniverse in Claude Code?

Run `npx skills add lamm-mit/scienceclaw --skill tooluniverse -a claude-code`. Or copy the skill folder (skills/tooluniverse in lamm-mit/scienceclaw) into .claude/skills/tooluniverse in your project. Claude Code loads it when a task matches its description.

How do I install Tooluniverse in Codex?

Run `npx skills add lamm-mit/scienceclaw --skill tooluniverse -a codex`. Or copy the skill folder (skills/tooluniverse in lamm-mit/scienceclaw) into .agents/skills/tooluniverse in your project. Codex loads it when a task matches its description.

Can I use Tooluniverse in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add lamm-mit/scienceclaw --skill tooluniverse -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/tooluniverse, .gemini/skills/tooluniverse, .github/skills/tooluniverse and .opencode/skills/tooluniverse in your project.

What does Tooluniverse need to run?

Going by SKILL.md and its folder, Tooluniverse needs Python for the scripts in its folder and the command-line tools its instructions call (python3 and pip). Our summary lists: Python 3.

Does Tooluniverse access the network?

SKILL.md contains no URLs. Its commands use pip, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Tooluniverse safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Tooluniverse use?

Tooluniverse is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Tooluniverse use?

About 950 tokens (SKILL.md is roughly 3.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Tooluniverse?

Skills that share tags, products or a category with Tooluniverse: Biomedical Analysis Dispatch (xjtulyc/MedgeClaw, 617 stars), Hcls Build Agent (aws-samples/amazon-bedrock-agents-healthcare-lifesciences, 274 stars), Hcls Get Started (aws-samples/amazon-bedrock-agents-healthcare-lifesciences, 274 stars) and Genomics Variant Interpretation (aws-samples/amazon-bedrock-agents-healthcare-lifesciences, 274 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Tooluniverse?

lamm-mit (a GitHub user) maintains it in lamm-mit/scienceclaw, which has 244 GitHub stars. The repository holds 86 skills in this directory. The repository was last updated on August 21, 2026.

Source: lamm-mit/scienceclaw on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.