No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by google-deepmind · Agent Tool · ★ 3.0k
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is science-skills safe to install? View the security audit →
Science Skills A collection of agent skills for scientific research tasks, spanning genomics, structural biology, cheminformatics, literature search, and more. Each skill provides structured instructions, scripts, and resources that extend an AI agent's capabilities for specialized scientific tasks. Skill Structure Each skill directory contains: SKILL.md — Main instruction file with YAML frontmatter and detailed markdown instructions scripts/ — Helper scripts and utilities references/ — Additional documentation and references (optional) Getting started with GDM Science Skills Install the Science Skills bundle via npx using: Using science skills with Google Antigravity If you're a new Google Antigravity user: Launch the application after downloading Google Antigravity and check the box for Science at the 'Build with Google' step - this will install the curated collection of our Science Skills. If you're an existing Google Antigravity user: Update to the latest version then open Settings - Customizations - Build with Google Plugins (click on 'Customize' at the bottom of the page) - Download the plugin Prerequisites We use th
| Stars | 3,044 |
| Forks | 347 |
| Language | Python |
| Category | Agent Tool |
| License | Apache-2.0 |
| Quality Score | 68.6490578975884/100 |
| Last Updated | 2026-09-15 |
| Created | 2026-05-13 |
| Platforms | python |
| Est. Tokens | ~14k |
These tools work well together with science-skills for enhanced workflows:
Looking for a science-skills alternative? If you're comparing science-skills with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Use this skill to enable Claude Code to communicate directly with your Google NotebookLM notebooks. Query your
The secure, validated skill registry for professional AI coding agents. Extend Antigravity, Claude Code, Curso
Skill to give Claude Code (and any coding agent) the ability to generate beautiful and practical Excalidraw di
Raptor turns Claude Code into a general-purpose AI offensive/defensive security agent. By using Claude.md and
General-purpose Playwright automation for coding agents
🎭 AI 写小说：从零生成 10-50 章完整中文小说，三层问答 · 创作记忆 · 悬念钩子 · 自动校验，长篇网文连载皆宜｜开源免费，适配主流 coding agent｜AI novel writing skill
Explore other popular agent tool tools:
science-skills is GDM Science Skills to speed up agentic scientific workflows with better grounding and higher token efficiency. Integrate insights from AlphaGenome, AFDB, UniProt and 30+ other databases and tools.. It is categorized as a Agent Tool with 3.0k GitHub stars.
science-skills is primarily written in Python.
You can find installation instructions and usage details in the science-skills GitHub repository at github.com/google-deepmind/science-skills. The project has 3.0k stars and 347 forks, indicating an active community.
science-skills is released under the Apache-2.0 license, making it free to use and modify according to the license terms.
The top alternatives to science-skills on Agent Skills Hub include notebooklm-skill, agent-skills, excalidraw-diagram-skill. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: