tooluniverse-cs-setup
This skill automates ToolUniverse setup for Claude Science by creating a conda environment, installing the pip package, and bundling the workflow library into a native skill. It replaces the plugin-based approach with direct kernel integration, handling first-time installation, version upgrades, and workflow refreshes from GitHub.
tooluniverse-cs-setup installs the ToolUniverse pip package and research workflows natively in Claude Science.
AI-generated summary based on this skill's SKILL.md
Decision gist · record as of 2026-07-27
tooluniverse-cs-setup installs the ToolUniverse pip package and research workflows natively in Claude Science. This skill automates ToolUniverse setup for Claude Science by creating a conda environment, installing the pip package, and bundling the workflow library into a native skill. It replaces the plugin-based approach with direct kernel integration, handling first-time installation, version upgrades, and workflow refreshes from GitHub.
Use it when
- tooluniverse-cs-setup handles first-time setup by automating environment creation and package installation.
- Yes.
Verify before relying
Read SKILL.md below before installing (4 files). Open directory: indexed for reading, not audited.
Install
mims-harvard/ToolUniverse/tooluniverse-cs-setup · repository language: Python
Open directory. Skills are indexed for reading, not audited. Review a skill's body before installing it.
Frequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
How to install tooluniverse in Claude Science?
tooluniverse-cs-setup automates the complete installation process. The skill creates a dedicated conda environment, installs the ToolUniverse pip package, and bundles your workflow library into a native Claude Science skill. This replaces the plugin approach with direct kernel integration, giving you access to 2500+ tools without external dependencies.
How do I set up tooluniverse for the first time?
tooluniverse-cs-setup handles first-time setup by automating environment creation and package installation. The skill sets up a conda environment (typically Python 3.11), installs the ToolUniverse pip package, configures your cache directory, and publishes the tooluniverse-research skill bundle to your Claude Science catalog. No manual configuration needed.
Can tooluniverse-cs-setup update my existing installation?
Yes. tooluniverse-cs-setup supports version upgrades by reinstalling the pip package and refreshing your workflow library from GitHub. When upstream releases new tools or updates, the skill pulls changes directly from the repository and rebundles them into your skill, keeping your installation current.
What does the tooluniverse-research skill bundle do?
tooluniverse-cs-setup builds and publishes the tooluniverse-research skill bundle, which packages your ToolUniverse workflows as a native Claude Science skill. This bundle integrates directly into your kernel, enabling seamless access to all configured tools without plugin overhead or external process management.
How does tooluniverse-cs-setup differ from the VS Code plugin?
tooluniverse-cs-setup replaces the plugin-based approach with direct kernel integration. Instead of running ToolUniverse as an external service, the skill bundles workflows natively into Claude Science, eliminating plugin dependencies and simplifying setup while maintaining full access to your tool library.
Can I refresh my ToolUniverse workflows after a GitHub release?
Yes. tooluniverse-cs-setup includes workflow library refresh functionality that pulls the latest updates from GitHub and rebundles them into your skill. This lets you stay synchronized with upstream releases without reinstalling the entire package.
SKILL.md
Rendered from the published skill. Quoted content, verbatim.
Set up ToolUniverse for Claude Science
The upstream ToolUniverse ships a Claude Code plugin (MCP server + uvx + slash commands). Claude Science loads capabilities differently, so this skill installs the equivalent natively: the tooluniverse pip package supplies the 2500+ tools, and the workflow library is packaged into a single dynamically-loaded skill, tooluniverse-research. No uv, no MCP server, no plugin marketplace.
Loading this skill defines tu_build_research_bundle() in the kernel (run cells in the tooluniverse conda env).
Full install / update — four steps
1. Create the conda env (skip if it already exists):
manage_environments(mode="create", name="tooluniverse", python_version="3.11", packages=["pip"])
**2. Install
(truncated - see the full file via the links below)
File tree — 4 files
skills/tooluniverse-cs-setup/SKILL.md
skills/tooluniverse-cs-setup/kernel.py
skills/tooluniverse-cs-setup/templates/research_kernel.py
skills/tooluniverse-cs-setup/templates/router_SKILL.md
Let your AI agent find skills like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 56,283 agent skills by what they can do, searchable in plain language.
wish › “Install or upgrade ToolUniverse pip package in Claude Science”
Give your agent the search over MCP, or paste the wish link into any chat. No install? Search from any chat →
Related skills
ToolUniverse setup guides you through installing and configuring the platform across three access modes: chat-based MCP for AI assistants, command-line interface with nine subcommands, or Python SDK for automation. The skill covers uv installation, MCP configuration for 12+ AI clients, full CLI reference, Coding API patterns, API key setup, and troubleshooting.
ToolUniverse SDK provides a Python interface to compose and execute scientific research pipelines across protein analysis, drug discovery, genomics, and disease databases. Call tools via portable dict API, function methods, or direct instantiation, with batch execution and caching for reproducible workflows.
This skill audits ToolUniverse documentation for technical errors, outdated information, and unnecessary duplication. It runs five phases—static method scanning, live code execution, automated validation, ToolUniverse audit, and simplification—to ensure every concept appears exactly once and all code is correct. Use it before releases, after API changes, or when asked to review, fix, or streamline documentation.
This skill systematically discovers drug repurposing opportunities by analyzing disease-target associations, drug mechanisms, and pathway overlap. It guides you through target-based, compound-based, and disease-driven workflows, then scores candidates by genetic evidence, safety profile, literature support, and drug properties to prioritize the most viable options.
ToolUniverse unifies over 1000 scientific tools into a single sandbox environment for biomedical research. It covers drug discovery, protein structure analysis, genomics, clinical data, literature search, and molecular modeling through a three-step workflow: search for tools, check specifications, then execute. Chain multiple tools to combine data from different sources for comprehensive research.
Access histone ChIP-seq data, chromatin accessibility maps, and regulatory element annotations from ENCODE and Roadmap Epigenomics to investigate chromatin state by tissue, transcription factor binding patterns, and cis-regulatory landscapes. Interpret histone marks, eQTL associations, and variant regulatory impact through multi-layer evidence synthesis.