Install
$ agentstack add skill-google-deepmind-science-skills-uv Open-source listing, not yet scanned by AgentStack. Follow the source repository for install instructions.
Security review
⚠ Flagged1 finding(s); flagged for manual review. · v0.1.0 How review works →
- • Prompt-injection patterns
- • Secret / credential exfiltration
- • Dangerous shell & filesystem operations
- • Untrusted network calls
- • Known-malicious package signatures
- high Pipes remote content directly into a shell (remote code execution).
What it can access
- ● Network access Used
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
uv (Python Package Manager)
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.
Setup
- Check if
uvis already available:uv --versionIf this succeeds,uvis
ready — skip the remaining steps.
- Check whether
uvis installed at its default location but not on PATH:
"$HOME/.local/bin/uv" --version If this succeeds, skip to step 4.
- If uv is not installed do both these steps in order:
(a) Tell the user that uv is a tool for creating a consistent and reliable Python environment used for running the Science Skills, and that you need to install it now. (b) Install uv: curl -LsSf https://astral.sh/uv/install.sh | sh
- Add
uvto PATH and verify (run as a single command): `export
PATH="$HOME/.local/bin:$PATH" && uv --version`
After setup, bare uv commands should work without repeating the export.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: google-deepmind
- Source: google-deepmind/science-skills
- License: Apache-2.0
- Homepage: https://antigravity.google/use-cases/science
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.