Uv
Automate repetitive workflows and reduce manual effort
Example: Generate reports, summarize documents, draft communications
Save 3-5 hours per week on routine tasks
Learn new skills, understand complex topics, get expert guidance
Example: Explain concepts, provide examples, suggest learning resources
Accelerate learning and skill development by 2x
Enhance output quality through reviews, suggestions, and refinements
Example: Review drafts, suggest improvements, catch errors
Improve work quality by 30-40% with less effort
Time estimate: 15-45 minutes depending on use case complexity
Prerequisites
Submit your Claude Code skill and start earning
epx add google-deepmind/science-skills --skill uvCompatible with
Supported agents
name: "uv"
description: "Checks whether the uv Python package manager is installed and installs it if missing. Ensures uv is on PATH. Use when another skill requires uv as a prerequisite."
| name | uv |
| description | >- Checks whether the uv Python package manager is installed and installs it if missing. Ensures uv is on PATH. Use when another skill requires uv as a prerequisite. |
uv is a fast Python package manager used by Science Skills to run their Python
CLI scripts. Many skills depend on uv being installed and on PATH.
Ensure uv is available before running any skill that depends on it.
uv is already available: uv --version If this succeeds, uv is
ready — skip the remaining steps.uv is installed at its default location but not on PATH:
"$HOME/.local/bin/uv" --version If this succeeds, skip to step 4.uv: curl -LsSf https://astral.sh/uv/install.sh | shuv to PATH and verify (run as a single command): export PATH="$HOME/.local/bin:$PATH" && uv --versionAfter setup, bare uv commands should work without repeating the export.
AI-first code editor with Composer
Before installing skills in Cursor, ensure your development environment meets these requirements:
node --versionuvExecute the skills CLI command in your project's root directory to begin installation:
epx add google-deepmind/science-skills --skill uvFetches uv from google-deepmind/science-skills and configures it for Cursor.
The CLI shows a list of agents. Use arrow keys and space to select Cursor:
Confirm successful installation by checking the skill directory location:
.cursor/skills/uv
Restart Cursor to activate uv. Access via /uvin your agent's command palette.
Learn more:View source on GitHubSkills CLI docsAbout CursorWhat are agent skills?
Steps
Common Pitfalls
✓ Do
✗ Don't
💡 Pro Tips
✓ Use when
Use when skill capabilities match your task, clear ROI on time saved, and you can validate outputs. Best for repetitive tasks, learning, and quality improvement.
✗ Avoid when
Avoid when task requires deep expertise you can't validate, involves sensitive decisions, or when learning process is more valuable than speed of completion.
literature-search-openalex
google-deepmind/science-skills · Science · same repo
opentargets-database
google-deepmind/science-skills · Science · same repo
pymol
google-deepmind/science-skills · Science · same repo
human-protein-atlas-database
google-deepmind/science-skills · Science · same repo
literature-search-biorxiv
google-deepmind/science-skills · Science · same repo
infographics
K-Dense-AI/scientific-agent-skills · Science · 2 shared tags
Solid pick for teams standardizing on skills: uv is focused, and the summary matches what you get after install.
Useful defaults in uv — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows.
uv has been reliable in day-to-day use. Documentation quality is above average for community skills.
Keeps context tight: uv is the kind of skill you can hand to a new teammate without a long onboarding doc.
Useful defaults in uv — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows.
Registry listing for uv matched our evaluation — installs cleanly and behaves as described in the markdown.
uv fits our agent workflows well — practical, well scoped, and easy to wire into existing repos.
I recommend uv for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.
uv has been reliable in day-to-day use. Documentation quality is above average for community skills.
Solid pick for teams standardizing on skills: uv is focused, and the summary matches what you get after install.
showing 1-10 of 65