openscientist-ioOfficial·9 Agent Skills Included

openscientist

Autonomous hypothesis generation and scientific data analysis

Runs autonomous discovery loops that generate hypotheses, test them against uploaded data, and search PubMed for mechanistic evidence. Covers metabolomics, genomics, structural biology, and statistics while eliminating manual analysis scripting and literature digging. Includes workflow skills for prioritization, result interpretation, and stopping criteria to produce rigorous final reports faster.

44|13

↗

npx skills add openscientist-io/openscientist --all -g -y

All Skills in This Repository (9)

Pure Emerald Level Indicators

📦 In Repo

openscientist-io

result-interpretation

Interpret statistical results and generate follow-up actions or hypotheses.

prioritization

Rank hypotheses by impact, feasibility, and novelty to select the next research action.

stopping-criteria

Evaluate iteration state and budget constraints to decide whether to continue or synthesize.

hypothesis-generation

Generate testable hypotheses from data patterns and literature findings.

metabolomics

Analyze metabolomics datasets with pathway-context reasoning and hypothesis generation.

genomics

Identify differential gene expression patterns from RNA-seq and transcriptomics data.

data-science

Analyze scientific datasets with statistical tests and Python code examples.

kbase-query

Query and explore KBase BERDL Datalake databases and tables via MCP REST.

jgi-lakehouse

Query JGI GOLD and IMG genomic metadata via the Dremio Lakehouse using SQL.

Official

Intermediate

Frequently Asked Questions

FAQPage Schema

How to install OpenScientist?▼

Run `npx skills add openscientist-io/openscientist --all -g -y` in your terminal to install all skills in this suite globally.

What does OpenScientist do?▼

It autonomously analyzes scientific data by generating hypotheses, running statistical tests, searching PubMed, and producing a final report with mechanistic findings.

What data types does OpenScientist support?▼

It works with metabolomics, genomics, transcriptomics, and structural biology data, accepting files like CSV, Excel, Parquet, PDB, mmCIF, and FASTA.

Can OpenScientist query KBase or JGI databases?▼

Yes. It includes skills for running SQL queries against the KBase/BERDL datalake and the JGI GOLD and IMG genomics lakehouses.

Do I need coding experience to use OpenScientist?▼

No. You upload data, state your research question, and the agent handles the statistical analysis and literature search automatically.