Scientific Agent Skills
166 skills for scientific work: bioinformatics, cheminformatics, clinical data, geospatial analysis and 100+ databases
- 55,262 ★ on the repository
- Last commit
- MIT
Extended access
Why this level
- Skills run Python scripts and install packages via uv
- They call external APIs and scientific databases
- Some community skills are not exhaustively reviewed
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/scientific-agent-skillsDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- Skills run Python scripts and install packages via uv
- They call external APIs and scientific databases
- Some community skills are not exhaustively reviewed
This is third-party code. Review the repository files before installing.
What it does
A collection of Agent Skills that gives an agent curated workflows for scientific Python packages and databases. It includes skills for RDKit, Scanpy, BioPython, PyTorch Lightning, Qiskit and pymatgen, a unified database-lookup skill for 78 public databases (PubChem, UniProt, ClinicalTrials.gov and others), and integrations such as Benchling, Opentrons and LabArchives. Every skill that ships scripts has a test suite in CI.
Who it is for. Scientists, bioinformaticians, data analysts and labs that use an agent for research computing.
Good fit when
- Analyzing single-cell RNA-seq, sequences or variants
- Querying scientific databases such as PubChem, ChEMBL or UniProt
- Cheminformatics and virtual screening
- Drafting literature reviews, hypotheses or experimental protocols
Not a fit when
- You need patient-specific diagnosis or treatment decisions
- You cannot review skill scripts before installing them
Example request
Load my h5ad file, run QC and cell clustering in Scanpy and plot a UMAPLimitations
The authors warn that skills can run code, install packages and make network requests, and community contributions may be less thoroughly reviewed. Installing the full collection adds a lot of standing context, so a topical subset is recommended. Requires Python and uv; Windows only via WSL2. Clinical skills are for research, not patient decisions.
How to disable. Remove unneeded skill folders from your agent's skills directory or disable the plugin in your client. If you used gh skill, manage installed skills through gh skill.
FAQ
Is it Claude-only?
No. It follows the open Agent Skills standard and works with Cursor, Claude Code, Codex, Gemini CLI, Google Antigravity and others.
Can I pin a version?
Yes, use gh skill install with --pin and a release tag or commit SHA.
Discussion
No questions or reviews yet.
Related
SkillsA library of agent skills for medical research: literature search and appraisal, study design, data analysis and academic writing
A Google DeepMind skill collection for science tasks: access to biology and chemistry databases, literature search and structural biology
16 research methodology skills for agents: from a testable question and pre-registered hypotheses to reproducible analysis
High-Stakes Analytics Lab
High-Stakes Analytics & Decision Lab
An evidence-gated analytics skill for high-stakes decisions: profiles data, picks a method the evidence supports, can answer with a data request
A Claude Code plugin and MCP server: over 1000 scientific tools for biology, chemistry and medicine, data-check commands and routing skills
dbt Agent Skills
dbt-agent-skills
Official dbt Labs skills: the agent understands dbt projects, runs workflows and helps with migration
Comparison with similar tools
Entries that share the main search query, and how they differ.
| Entry | Official | Repository stars | Main difference |
|---|---|---|---|
| Scientific Agent Skills (this entry) | no | 55,262 | |
| Life Sciences: Anthropic's marketplace for Claude Code | yes | 632 | anthropic's official plugin marketplace for biology and medicine |
| ClaudePrism: LaTeX editor with Claude Code | no | 1,830 | a desktop editor for scientific writing in LaTeX with Claude Code |
| K-Dense BYOK: AI research assistant on your computer | no | 1,412 | a free open-source app where the AI assistant Kady handles research |
README in short
Scientific Agent Skills (formerly Claude Scientific Skills) is K-Dense's collection of 166 skills for scientific and research tasks. They span genomics, drug discovery, proteomics, clinical research, medical imaging, materials science, astronomy, geospatial work and scientific communication. The repository is also an Agent Plugins package. Install via npx skills, gh skill, Cursor or Codex plugins, or a manual clone. The project is described in arXiv:2609.00065 and includes a dedicated security section.
README badge
Original SKILL.md
---
name: biopython
description: Comprehensive molecular biology toolkit. Use for sequence manipulation, file parsing (FASTA/GenBank/PDB), phylogenetics, and programmatic NCBI/PubMed access (Bio.Entrez). Best for batch processing, custom bioinformatics pipelines, BLAST automation. For quick lookups use gget; for multi-service integration use bioservices.
allowed-tools: Read Write Edit Bash
compatibility: Requires Python 3.10+, NumPy, and Biopython. Entrez and web BLAST examples require network access; local BLAST/MUSCLE examples require those command-line tools installed separately.
license: Biopython License Agreement
metadata:
version: "1.3"
skill-author: K-Dense Inc.
openclaw:
envVars:
- name: NCBI_EMAIL
required: false
description: Email for NCBI Entrez identification (required by NCBI policy for Entrez calls).
- name: NCBI_API_KEY
required: false
description: NCBI API key to raise Entrez rate limits.
---
# Biopython: Computational Molecular Biology in Python
## Overview
Biopython is a comprehensive set of freely available Python tools for biological computation. It provides functionality for sequence manipulation, file I/O, database access, structural bioinformatics, phylogenetics, and many other bioinformatics tasks. The current version is **Biopython 1.87** (released 30 March 2026). It supports **Python 3.10-3.14** and PyPy3.10, and requires NumPy. Biopython 1.87 also addresses **CVE-2025-68463** in `Bio.Entrez.Parser` when parsing untrusted files, so prefer 1.87+ for workflows that parse externally supplied Entrez XML.
## When to Use This Skill
Use this skill when:
- Working with biological sequences (DNA, RNA, or protein)
- Reading, writing, or converting biological file formats (FASTA, GenBank, FASTQ, PDB, mmCIF, etc.)
- Accessing NCBI databases (GenBank, PubMed, Protein, Gene, etc.) via Entrez
- Running BLAST searches or parsing BLAST results
- Performing sequence alignments (pairwise or multiple sequence alignments)
- Analyzing protein structures from PDB files
- Creating, manipulating, or visualizing phylogenetic trees
- Finding sequence motifs or analyzing motif patterns
- Calculating sequence statistics (GC content, molecular weight, melting temperature, etc.)
- Performing structural bioinformatics tasks
- Working with population genetics data
- Any other computational molecular biology task
## Core Capabilities
Biopython is organized into modular sub-packages, each addressing specific bioinformatics domains:
1. **Sequence Handling** - Bio.Seq and Bio.SeqIO for sequence manipulation and file I/O
2. **Alignment Analysis** - Bio.Align and Bio.AlignIO for pairwise and multiple sequence alignments
3. **Database Access** - Bio.Entrez for programmatic access to NCBI databases
4. **BLAST Operations** - Bio.Blast for running and parsing BLAST searches
5. **Structural Bioinformatics** - Bio.PDB for working with 3D protein structures
6. **Phylogenetics** - Bio.Phylo for phylogenetic tree manipulation and visualization
7. **Advanced Features** - Motifs, population genetics, sequence utilities, and more
## Installation and Setup
Install the current stable Biopython release with an explicit version pin for reproducibility:
```bash
uv pip install "biopython==1.87"