Uv
100TrustedInstructions onlyPython environment management by verifying and configuring the uv package manager.
What it does
Adding Uv to your assistant ensures it has the necessary infrastructure to manage Python project dependencies. It shifts the burden of manual setup onto the agent, allowing it to detect if the package manager is present and configure it for immediate use.
This is a utility skill designed to resolve environment prerequisites before executing specialized Python scripts. By confirming the availability of the tool on the system PATH, the assistant eliminates errors stemming from missing software.
When it earns its place
Reach for it when…
Apply this skill when an assistant identifies that a specific Python-based script or library requires the uv package manager to function correctly. It is appropriate when transitioning into a new environment where the software stack remains unverified.
Look elsewhere when…
Do not install this if you primarily use alternative dependency managers like pip or conda, as this skill specifically addresses uv requirements. It is unnecessary if the target scripts are pre-packaged within containers or cloud environments where the software is already provisioned by an administrator.
What to say to use it
You never invoke a skill directly — the assistant picks it up when your request matches what it covers. These are the kinds of things that do that.
- Check if the python environment is ready to run scripts
- Install the dependencies for this project using uv
- Verify my system has the required package manager
- Ensure the python tooling is correctly configured
Install it
Install for all your projects
Copy the skill directory into your personal skills folder. Claude picks it up on its own the next time your request matches what it does — there is nothing to enable.
git clone --depth 1 --branch main https://github.com/google-deepmind/science-skills.git /tmp/science-skills
mkdir -p ~/.claude/skills
cp -r /tmp/science-skills/skills/uv ~/.claude/skills/uvInstall for one project only
Put it in the project's own skills folder instead, so it can be committed and shared with everyone working on that repository.
cp -r /tmp/science-skills/skills/uv .claude/skills/uvIf a skill of the same name exists in both places, the personal one wins.
Installing on Claude.ai or through the API instead? The full guide covers every surface.
Pair it with an MCP server
Uv changes how the work is done. These servers change what Claude can reach while doing it.
- GitHub MCP Server53The skill sets the conventions the code should follow; GitHub MCP Server is what lets Claude read the repository it is writing into.
- Context Forge MCP Server86Context Forge MCP Server gives the code somewhere to actually run, so the skill's guidance can be checked instead of assumed.
- Supabase MCP Server100Pair with Supabase MCP Server when the code being written has to match a real schema rather than a described one.