Item detail
github.com

google-deepmind/science-skills

google-deepmind/science-skills is an agent project in RepoRadar's Radar section, holding Gold tier and a 'try now' verdict. Its strongest signal is workflow potential, scored 9.5 out of 10.

Score8.4
Popularity100.0
Risklow
TierGold
Score breakdown
Usefulness8.0
Novelty8.0
Momentum7.0
Maturity9.1
Open-source/build8.4
Evidence7.2
Workflow potential9.5
Setup ease6.4

Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.

Why it matters

Useful for AI research and engineering teams working on agentic scientific workflows: google-deepmind/science-skills is the official Google DeepMind collection of 30+ agent skills covering genomics, structural biology, cheminformatics, literature search, and clinical / pharmacological / regulatory databases, with every skill grounded in a primary scientific database

Where this stands now

google-deepmind/science-skills ranks #209 of 2143 tracked Radar items by composite score (8.4 against a section median of 6.7). The section currently carries 1038 Bronze, 646 Gold, 459 Silver. RepoRadar has retained observations for this record since 2026-06-25 (91 days in the current window). Signal extremes versus the section: novelty at the 78th percentile.

Who should use it

AI research and engineering teams working on agentic scientific workflows: google-deepmind/science-skills is the official Google DeepMind collection of 30+ agent skills covering genomics, structural biology, cheminformatics, literature search, and clinical / pharmacological / regulatory databases, with every skill grounded in a primary scientific database (AlphaGenome, AFDB, UniProt, PubMed, ChEMBL, OpenAlex, PDB) Biology and chemistry research labs that need an AI agent that can query AlphaGenome for variant pathogenicity, AFDB for protein structures, ChEMBL for compound bioactivity, PubMed for literature search, and PDB for 3D structures — the same agent can do all of these without the user switching tools AI safety / drug-discovery / clinical-research engineering teams that need grounded answers (the skills return data from primary databases with source URLs, not summaries) AI coding-agent users (Claude Code, Codex, Cursor, Gemini CLI, Antigravity, OpenCode, Hermes) who want to add scientific-research skills to their existing agent workflow — the skills follow the standard Agent Skills convention (SKILL.md + scripts + references) and install via npx skills add google-deepmind/science-skills/ Users who want a Google-curated scientific-research surface (Antigravity is the canonical deployment target, the README links to the Antigravity 'Build with Google' Science plugin) Open-source maintainers that want a verifiable project (Google DeepMind as the maintainer, Apache-2.0 license, integration with 30+ primary scientific databases, the Science Skills page on skills.sh) AI agents that need source citation (every skill returns source URLs to the primary database, the verifiable claim surface is the database itself)

Who should skip it

Move on from google-deepmind/science-skills if the licensing terms, language support, or platform requirements do not fit your project.

About this signal

google-deepmind/science-skills is tracked by RepoRadar as an agent project in the Radar section. First seen 2026-06-25; the source record was last checked on 2026-06-25. The current verdict is 'try now' with a Gold tier and moderate setup difficulty. The standout signals for google-deepmind/science-skills are workflow potential (9.5) and maturity (9.1), while setup ease (6.4) trails — that balance shapes where it fits best. This page summarizes the public evidence on the linked source page and states where additional review is still needed.

How this item is evaluated

The google-deepmind/science-skills record combines a 8.4/10 composite score with separate popularity (100.0), risk (low), and setup (moderate) signals. See the scoring methodology for the current weights and evidence definitions.

Putting this into practice? Read How to vet an AI agent or MCP server before you wire it in for the checklist behind this score.

Risk explanation

Some skills require API keys. The README explicitly notes 'Some skills, such as AlphaGenome and OpenAlex, require an API key to function' — users must obtain the relevant API key before triggering those skills, and the API key has to be configured in the agent's environment or skill-specific config file; First-time install requires uv package manager and approval prompt. The README says 'The first time you trigger a Science Skill, the agent will ask for approval and install uv, and then proceed to respond to your scientific query / task. We recommend restarting Antigravity after this first time installation.' — users should expect the first invocation to trigger a package-manager install and an approval prompt; Primary databases can change schemas, rate limits, or terms of service. The skills are grounded in 30+ primary scientific databases (AlphaGenome, AFDB, UniProt, PubMed, ChEMBL, OpenAlex, PDB, etc.), and any of those databases can change their API schema, rate limits, or terms of service without notice; users running the skills in production should pin to a tested commit and monitor the upstream database status pages.

Evidence links
Closest alternatives / related signals
google-deepmind deepmind gdm google science scientific-research agentic-science agent-skills
Verification record

What RepoRadar actually verified

Discovered

Automated discovery and source capture. Last checked 2026-09-24T21:49:16.463298Z.

No editorial or hands-on review is claimed. This record remains at Discovered.

Verification sources

Longitudinal intelligence

How this decision record is moving

Raw history JSON →

70 dated snapshots retained from 2026-06-25 through 2026-09-24; see the snapshot index for explicit coverage gaps. Stars, version, release, pricing, integration, risk, maintenance, verdict, score, and momentum fields remain explicit even when a source has not reported them. Repository momentum is a normalized 0–10 RepoRadar signal; GitHub stars appear only where the popularity monitor retained exact timestamped observations.

RepoRadar score8.4 current · +0.0 net
Repository momentum7.8 current · +0.8 net
GitHub stars (observed)3,137 current · +784 net
GitHub stars3,137 exact observation
Versionv1.2.0
Last release2026-09-08T16:25:20Z
Maintenanceactive
Current risklow
Current verdicttry now
Pricing baselineNo structured commercial pricing baseline
Pricing checkedNot applicable or not recorded
Pricing freshnessNo dated commercial pricing review
Integrations baselineNo structured integrations recorded

Recent dated points

DateScoreMomentumStarsRiskVerdictMaintenance
2026-09-248.47.83,137lowtry nowactive
2026-09-238.47.83,131lowtry nowactive
2026-09-228.47.53,121lowtry nowactive
2026-09-218.49.03,116lowtry nowactive
2026-09-208.49.33,105lowtry nowactive
2026-09-198.49.03,100lowtry nowactive
2026-09-178.49.03,074lowtry nowactive
2026-09-158.49.63,041lowtry nowactive
2026-09-138.49.03,016lowtry nowactive
2026-09-128.49.03,012lowtry nowactive
2026-09-118.49.62,998lowtry nowactive
2026-09-088.45.52,861lowtry nowmaintained

Why the record changed

stars changed

Stars changed: 3132 → 3137.

stars changed

Stars changed: 3131 → 3132.

stars changed

Stars changed: 3121 → 3131.

stars changed

Stars changed: 3116 → 3121.

stars changed

Stars changed: 3111 → 3116.

stars changed

Stars changed: 3105 → 3111.

stars changed

Stars changed: 3102 → 3105.

stars changed

Stars changed: 3100 → 3102.

stars changed

Stars changed: 3093 → 3100.

stars changed

Stars changed: 3074 → 3093.

stars changed

Stars changed: 3067 → 3074.

stars changed

Stars changed: 3041 → 3067.