Run research and scientific analysis workflows with Scientific Agent Skills
Give an agent curated scientific workflows, databases, and domain-specific guidance when general prompting is not reliable enough for research-heavy work.
Prerequisites
An Agent Skills compatible harness such as Claude Code, Cursor, or Codex, plus Python and the scientific libraries, databases, model providers, or local environment dependencies required by the selected workflow.
Installation
Use the upstream install or setup path that matches your environment:
- uv pip install cisco-ai-skill-scanner
- The skills use uv as the package manager for installing Python dependencies. Install it using the instructions for your operating system:
- pip install uv
- uv --version
Requirements and caveats from upstream:
- 70+ Optimized Python Package Skills - Explicitly defined skills for RDKit, Scanpy, PyTorch Lightning, scikit-learn, BioPython, pyzotero, BioServices, PennyLane, Qiskit, OpenMM, MDAnalysis, scVelo, TimesFM, and oth...
- 70+ Optimized Python Package Skills - RDKit, Scanpy, PyTorch Lightning, scikit-learn, BioServices, PennyLane, Qiskit, OpenMM, scVelo, TimesFM, and others (the agent can use any Python package; these are the pre-do...
⚙️ Prerequisites
Basic usage or getting-started notes:
9 Scientific Integration Skills - Explicitly defined skills for Benchling, DNAnexus, LatchBio, OMERO, Protocols.io, Open Notebook, and more. Again, the agent is not limited to these — any API or platform reachable...
Agent Skills are powerful — they can instruct your AI agent to run arbitrary code, install packages, make network requests, and modify files on your system. A malicious or poorly written skill has the potential to ste...
We take security seriously. All contributions go through a review process, and we run LLM-based security scans (via Cisco AI Defense Skill Scanner) on every skill i...
Source: https://github.com/K-Dense-AI/scientific-agent-skills
Extracted from upstream docs: https://raw.githubusercontent.com/K-Dense-AI/scientific-agent-skills/HEAD/README.md
Documentation
Source
1---2name: run-research-and-scientific-analysis-workflows-with-scientif3description: Give an agent curated scientific workflows, databases, and domain-specific guidance when general prompting is not reliable enough for research-heavy work.4---56# Run research and scientific analysis workflows with Scientific Agent Skills78Give an agent curated scientific workflows, databases, and domain-specific guidance when general prompting is not reliable enough for research-heavy work.910## Prerequisites1112An Agent Skills compatible harness such as Claude Code, Cursor, or Codex, plus Python and the scientific libraries, databases, model providers, or local environment dependencies required by the selected workflow.1314## Installation1516Use the upstream install or setup path that matches your environment:17- uv pip install cisco-ai-skill-scanner18- The skills use uv as the package manager for installing Python dependencies. Install it using the instructions for your operating system:19- pip install uv20- uv --version2122Requirements and caveats from upstream:23- **70+ Optimized Python Package Skills** - Explicitly defined skills for RDKit, Scanpy, PyTorch Lightning, scikit-learn, BioPython, pyzotero, BioServices, PennyLane, Qiskit, OpenMM, MDAnalysis, scVelo, TimesFM, and oth...24- **70+ Optimized Python Package Skills** - RDKit, Scanpy, PyTorch Lightning, scikit-learn, BioServices, PennyLane, Qiskit, OpenMM, scVelo, TimesFM, and others (the agent can use any Python package; these are the pre-do...25- ## ⚙️ Prerequisites2627Basic usage or getting-started notes:28- **9 Scientific Integration Skills** - Explicitly defined skills for Benchling, DNAnexus, LatchBio, OMERO, Protocols.io, Open Notebook, and more. Again, the agent is not limited to these — any API or platform reachable...29- Agent Skills are powerful — they can instruct your AI agent to run arbitrary code, install packages, make network requests, and modify files on your system. A malicious or poorly written skill has the potential to ste...30- We take security seriously. All contributions go through a review process, and we run LLM-based security scans (via [Cisco AI Defense Skill Scanner](https://github.com/cisco-ai-defense/skill-scanner)) on every skill i...3132- Source: https://github.com/K-Dense-AI/scientific-agent-skills33- Extracted from upstream docs: https://raw.githubusercontent.com/K-Dense-AI/scientific-agent-skills/HEAD/README.md3435## Documentation3637- https://github.com/K-Dense-AI/scientific-agent-skills#readme3839## Source4041- [Agent Skill Exchange](https://agentskillexchange.com/skills/run-research-and-scientific-analysis-workflows-with-scientific-agent-skills/)
agentskillexchange