Scientific Agent Skills
AIAn open library of 163 validated Agent Skills that turn Cursor, Claude Code, Codex or Antigravity into a working AI scientist across 100+ databases.
Scientific Agent Skills
An open library of 163 validated Agent Skills that turn Cursor, Claude Code, Codex or Antigravity into a working AI scientist across 100+ databases.
About Scientific Agent Skills
Scientific Agent Skills is an MIT-licensed library of 163 tested, domain-specific skills that give a general coding agent real scientific capability. Each skill packages the procedure, tool calls and database access for a concrete research task, and the collection reaches more than 100 scientific databases so an agent can look up, retrieve and reason over primary sources instead of relying on recall. Originally released as Claude Scientific Skills, the project was renamed after adopting the open Agent Skills standard, so it now works with any agent that supports it — Cursor, Claude Code, Codex and Google Antigravity are listed explicitly. Continuous integration runs both a security scan and a skill test suite on every change, which is unusual for a skills collection and is what lets the maintainers describe the set as validated. The same team also publishes K-Dense BYOK, a free open-source desktop AI co-scientist that bundles these skills with web search, file handling and a choice of 40+ models under your own API keys, keeping data local with optional cloud scale-out via Modal.
Screenshots
Key Features
Use Cases
Frequently asked questions about Scientific Agent Skills
What is Scientific Agent Skills?
An open library of 163 validated Agent Skills that turn Cursor, Claude Code, Codex or Antigravity into a working AI scientist across 100+ databases.
How does Scientific Agent Skills work?
Scientific Agent Skills works by combining 163 Validated Skills: A tested library of domain skills covering concrete scientific procedures rather than generic prompt snippets., 100+ Scientific Databases: Skills wire agents into over a hundred research databases so answers are grounded in retrieved primary data., Agent-agnostic Standard: Built on the open Agent Skills standard, so it runs on Cursor, Claude Code, Codex and Google Antigravity rather than a single vendor., CI Skill Testing: A GitHub Actions skill-test workflow runs against the collection, so regressions in individual skills are caught in the repository., Automated Security Scanning: A dedicated security-scan workflow checks the skill set on every change, important when skills execute tools on a researcher's machine. to help users with Literature and Database Retrieval: Have an agent pull and cross-reference records from specialised scientific databases during a literature review., Reproducible Analysis Pipelines: Use validated skills so the same analytical procedure runs identically across projects and lab members., Local Co-scientist Workspace: Run K-Dense BYOK on a laptop with your own API keys to keep unpublished data off third-party servers., Extending an Existing Coding Agent: Add scientific capability to Cursor or Claude Code without switching to a separate research platform., Teaching and Onboarding: Give students or new lab members an agent that already knows the standard procedures and data sources for the field..
What are the main features of Scientific Agent Skills?
Key features include 163 Validated Skills: A tested library of domain skills covering concrete scientific procedures rather than generic prompt snippets., 100+ Scientific Databases: Skills wire agents into over a hundred research databases so answers are grounded in retrieved primary data., Agent-agnostic Standard: Built on the open Agent Skills standard, so it runs on Cursor, Claude Code, Codex and Google Antigravity rather than a single vendor., CI Skill Testing: A GitHub Actions skill-test workflow runs against the collection, so regressions in individual skills are caught in the repository., Automated Security Scanning: A dedicated security-scan workflow checks the skill set on every change, important when skills execute tools on a researcher's machine..
Who is Scientific Agent Skills for?
Scientific Agent Skills is useful for anyone interested in Literature and Database Retrieval: Have an agent pull and cross-reference records from specialised scientific databases during a literature review., Reproducible Analysis Pipelines: Use validated skills so the same analytical procedure runs identically across projects and lab members., Local Co-scientist Workspace: Run K-Dense BYOK on a laptop with your own API keys to keep unpublished data off third-party servers., Extending an Existing Coding Agent: Add scientific capability to Cursor or Claude Code without switching to a separate research platform., Teaching and Onboarding: Give students or new lab members an agent that already knows the standard procedures and data sources for the field..
How much does Scientific Agent Skills cost?
Scientific Agent Skills is free to use.
How do I get started with Scientific Agent Skills?
Visit https://github.com/K-Dense-AI/scientific-agent-skills to sign up and explore Scientific Agent Skills.
Explore more AI Ai Agents tools
Browse all Ai Agents tools →Browse by use case: Automation & Productivity
Compare Scientific Agent Skills: vs Superagent · vs Topview · vs OpenTag · vs Caddi