Scientific Agent Skills: Open-Source Skills for AI-Driven Science

RepositoryK-Dense-AI/scientific-agent-skillsTool

Scientific Agent Skills (formerly Claude Scientific Skills) is an open-source library providing 177 validated skills and access to over 100 scientific databases, enabling AI agents to handle workflows across biology, chemistry, medicine, and drug discovery.

Key points

  1. Includes 177 validated scientific skills and integration with 100+ domain databases.
  2. Built on the open Agent Skills and Agent Plugins specifications.
  3. Compatible with platforms such as Cursor, Claude Code, Codex, Pi, and Google Antigravity.
  4. Offers K-Dense BYOK, an open-source local desktop workspace supporting 40+ models and optional Modal cloud compute.
  5. Released under the MIT licence alongside an arXiv research paper (2609.00065).

Why it matters

Standard AI agents often lack native integration with scientific databases and domain-specific computation pipelines. A unified, open-standard library allows researchers to turn off-the-shelf agents into capable scientific assistants without rebuilding integration layers from scratch.

Analysis

The project addresses the gap between general-purpose code assistants and domain-heavy scientific research. Implemented primarily in Python, it integrates automated skill testing and security scanning workflows to maintain reliability. The transition from Claude-specific tooling to the open Agent Skills specification broadens interoperability across multiple agent frameworks. With version 2.72.0, extensive star counts, and a peer-reviewed preprint, the library demonstrates high maturity. It primarily serves bioinformaticians, medicinal chemists, and researchers seeking local or cloud-backed agentic workflows.

Found in

Summary generated by AI (Gemini 3.8 Flash, 18 October 2026). It may contain errors – the original source is authoritative.

Similar in content, found by the AI search.

  • Repository:mohitagw15856/pm-claude-skills

    PM Skills: Agent Framework Collection for AI Assistants

    PM Skills is an MIT-licensed repository providing over 1,100 structured agent skills in plain Markdown. It equips models across Claude, ChatGPT, Gemini, Cursor, and Codex with step-by-step frameworks for professional duties and critical life events.

    1.3kstarsHTML

    AI & LLMs· Resource

  • Repository:anthropics/skills

    Anthropic Skills: Reference Repository and Specification for Claude Agent Skills

    Anthropic provides a public repository containing example skills, templates, and specifications for Claude's Agent Skills standard. Skills package instructions, scripts, and resources inside folders with a central SKILL.md file to enable repeatable workflows ranging from document generation to technical testing.

    174.3kstarsPython

    AI & LLMs· Resource

  • Repository:davidondrej/skills

    davidondrej/skills: Reusable Skills for AI Agents

    An open-source repository by David Ondrej containing modular instructions and workflows for AI coding, research, and orchestration agents.

    3.9kstarsPython

    AI & LLMs· Resource

  • Repository:kepano/obsidian-skills

    obsidian-skills: Agent Skills for Obsidian and Open Formats

    The open-source repository kepano/obsidian-skills equips AI coding agents with capabilities to interact with Obsidian vaults. Built on the Agent Skills specification, it works with agents like Claude Code, Codex, and OpenCode.

    47.9kstars

    AI & LLMs· Tool

  • Link:Anthropic

    Agent Skills: An Open Standard for Modular AI Agent Capabilities

    Agent Skills is an open format designed to equip AI agents with specialised domain knowledge and repeatable workflows. Centred around a directory containing a SKILL.md file, it relies on progressive disclosure to keep context overhead minimal.

    AI & LLMs· Resource

Let's talk about your project

Locations

  • Mattersburg
    Johann Nepomuk Bergerstraße 7/2/14
    7210 Mattersburg, Austria
  • Vienna
    Ungargasse 64-66/3/404
    1030 Wien, Austria

Parts of this content were created with the assistance of AI.