tooluniverse

# 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) | Parameter | Description | Default | |-----------|-------------|---------| | `--tool` | ToolUniverse tool name (exact, case-sensitive) | Required | | `--args` | Tool arguments as a JSON string | `{}` | | `--format` | Output format: json, summary | json | | `--no-cache` | Disable result caching | false | ## Available Research Workflows (54+) ### Drug Discovery - binder-discovery, drug-repurposing, drug-target-validation, drug-drug-interaction - chemical-safe...