📊 Publicly benchmarked · 1,161 stars · 108 skills · 73 contributors · 6,187 tests

The first bioinformatics-native
AI agent skill library

ClawBio is where biological AI gets its skills: a curated, reproducible, open repository any agent can call.

        $ pip install clawbio
      

🚀 New in v0.7.0: the library installs as a Claude Code plugin or plain Agent Skills, and the headline skills write SHA-256 reproducibility bundles.

📅 Follow Event Calendar ⭐ View on GitHub 📊 Leaderboard · 161/182 🧬 Submit a Skill 🤖 Try RoboTerri

bioinformaticsgenomicsreproducibilitypopulation-geneticsequityai-agentslocal-firstopenclaw

v0.7.0 · Agent Skills

Genomics skills, in your editor

Every ClawBio skill is a plain Agent Skills folder: a SKILL.md contract, the script that executes it, demo data and tests. Claude Code installs the whole library as a plugin. Cursor, VS Code, Codex, Zed and any other editor that reads Agent Skills load the folders from ~/.agents/skills/. The runnable skills execute on your machine and hand back the report, the structured result, and a commands.sh with SHA-256 checksums, so the analysis can be replayed without the agent that produced it.

            > /plugin marketplace add ClawBio/ClawBio
          

Then /plugin install clawbio. Other editors: copy or symlink the skill folders you need into ~/.agents/skills/.

✅ 108 skills, 101 with a deterministic CLI entry point
🔒 Demo data included, your files only when you pass them
🏠 Local-first. No server, no hosted endpoint, by design

# Claude Code
/plugin marketplace add ClawBio/ClawBio
/plugin install clawbio

# Cursor, VS Code, Codex, Zed: Agent Skills
git clone https://github.com/ClawBio/ClawBio
cp -r ClawBio/skills/pharmgx-reporter ~/.agents/skills/

# Python, any language
pip install clawbio
clawbio run pharmgx --demo

The MCP server introduced in v0.6.0 is deprecated as of v0.7.0 and will be removed in v0.8.0. Existing clawbio mcp configurations keep working until then and print a notice on start. Why, and how to migrate.

🚀 What is new in v0.7.0 🏷️ Release notes 📄 MCP migration guide

The Problem

Reproducing bioinformatics analyses is broken

# Without ClawBio
$ git clone repo && cd repo
# Wrong Python version...
# Reference data link is dead...
# Paths hardcoded to /home/jsmith/data/
# Email first author. Wait 3 weeks.
# Give up.

✗ Dependency hell & broken environments
✗ Dead links to reference data
✗ Hardcoded paths & missing configs
✗ AI hallucinates star alleles & outdated guidelines
✗ No audit trail, no checksums

# With ClawBio
$ python skills/multiqc-reporter/multiqc_reporter.py --demo --output /tmp/multiqc_demo

✓ Demo report regenerated.
✓ Replay command saved alongside outputs.
✓ Checksums available for verification.

# Or with natural language:
$ openclaw "Profile my pharmacogenes"

Many skills write a reproducibility/ bundle with replay commands, environment metadata, and output checksums. Exact files vary by skill, and some replays still require local tools or original inputs.

Why ClawBio

Domain expertise, frozen into code

ChatGPT and Claude are smart generalists. ClawBio skills are domain experts' proven pipelines — executed correctly every time.

🏠

Local-first by default

Your genome is analysed on your machine. Skills that transmit data to external services are clearly labelled and run only when you invoke them.

🔁

Reproducible

Many skills export replay bundles with commands, environment metadata, and output checksums so runs can be rechecked without the original agent session.

🧩

Modular

Each skill is a self-contained directory (SKILL.md + Python scripts) that plugs into the orchestrator — or runs standalone.

⚖️

MIT Licensed

Open-source, free, community-driven. Clone it, run it, build a skill, submit a PR.

🌍

Equity-aware

Built-in support for underrepresented populations. HEIM diversity metrics baked into the roadmap.

🎯

Benchmark Validated

Public scientific-correctness leaderboard: 161/182 tests passing (88.5%) as of 26 Jul 2026, across 10 of 95 skills, every failure tagged. The suite currently reports an overall FAIL: nutrigx-advisor regressed from 10/10 to 0/10. AD ground truth (34 genes, 3 evidence tiers), mock API server for offline CI, swappable fine-mapping (ABF vs SuSiE), benchmark scorer with precision/recall/F1. View leaderboard · DOI

🦞

Built on OpenClaw

Powered by OpenClaw, the open agent platform that routes natural language to the right specialist skill. ClawBio is the bioinformatics catalogue any OpenClaw-compatible agent can call.

🔌

Claude Code Plugin

Install with two commands: /plugin marketplace add ClawBio/ClawBio then /plugin install clawbio. All skills instantly available.

Skills Library

108 skills · 102 with runnable demo data · 6,187 tests · 161 / 182 publicly benchmarked passing

Each skill includes demo data so you can try it immediately without your own files.

💊 PharmGx Reporter

Pharmacogenomic report from 23andMe/AncestryDNA: 12 genes, 31 SNPs, 51 drugs, CPIC guidelines.

MVP

🥦 NutriGx Advisor

Personalised nutrition report from consumer genetic data: MTHFR, folate, vitamin D, caffeine, lactose, omega-3, and more.

MVP

🔍 GWAS Lookup

Federated variant lookup across 9 genomic databases: GWAS Catalog, Open Targets, PheWeb (UKB, FinnGen, BBJ), GTEx, eQTL Catalogue, and more.

MVP

📊 GWAS Polygenic Risk

Calculate polygenic risk scores from DTC genetic data using curated PGS Catalog scores across 6 traits.

MVP

⚖️ Equity Scorer

Compute HEIM diversity and equity metrics from VCF or ancestry data: heterozygosity, FST, and population representation scores.

MVP

+ 103 more skills on GitHub · see which ones are publicly benchmarked →

In Production

ClawBio skills, running in conversation

ClawBio skills aren't just CLI tools — they power live AI agents that talk to real users every day.

RoboTerri

Telegram AI Agent

A bioinformatics intelligence agent on Telegram — inspired by Professor Teresa K. Attwood, a pioneer of bioinformatics education and research. Run pharmacogenomics reports from your own genetic data. Snap a photo of your medication, get personalised dosage guidance. Local-first, with reproducibility support where the underlying skill writes a replay bundle.

PharmGx Reporter Drug Photo Lookup NutriGx Advisor Genome Compare Equity Scorer Metagenomics GWAS Lookup scRNA Orchestrator

Community

Wanted: skills from the community

If you work with genomics, proteomics, metabolomics, imaging, or clinical data — wrap your pipeline as a skill.

claw-gwas

PLINK/REGENIE automation — Statistical genetics

claw-acmg

Clinical variant classification — Clinical genomics

claw-pathway

GO/KEGG enrichment — Functional genomics

claw-phylogenetics

IQ-TREE/RAxML automation — Evolutionary biology

claw-spatial

Visium/MERFISH — Spatial transcriptomics

claw-long-reads

ONT/PacBio QC and assembly — Long-read sequencing

Your skill here

🎮 Join the Discord 💬 Join the Telegram 📖 Read the contribution guide

Repo	OpenClaw	Stars	Forks	Skills
ClawBio	✓	1,161	284	108
OpenClaw-Medical-Skills	✓	1,037	123	869
bioSkills	✓	331	52	425
LabClaw	✓	317	54	211
claude-scientific-skills	~	14.5k	1,585	250
Biomni	—	2,826	508	314

Recent Updates

Latest from the community

🔍

docs(audit): skill_run is a child span under a caller's TRACEPARENT. The skill_run docstring now says it joins the caller's trace when TRACEPARENT is set, rather than always starting a root trace, matching the behaviour added in #653. Contributed by @camlloyd.

PR #656 · merged · 19 October 2026

🛡️

ci: fix zizmor findings in ci.yml and bench-leaderboard.yml. A skill-name template-injection risk in the CI harness step and two checkouts that kept persisted git credentials unnecessarily are fixed, closing out the zizmor findings those two workflows had open. Contributed by @camlloyd.

PR #658 · merged · 19 October 2026

🧵

feat(audit): nest skill_run under the caller's span from TRACEPARENT. When an agent runs a skill, the shared audit layer's skill_run span now joins the agent's own trace via the W3C TRACEPARENT header, instead of starting a disconnected root trace. Contributed by @camlloyd.

PR #653 · merged · 18 October 2026

🧪

fix(igv-validator): skip its tests without pysam; CI collects with core deps. The igv-validator skill's tests now skip cleanly when pysam isn't installed, and CI collects the whole suite with only core dependencies so any skill importing an optional extra at module level is caught. Contributed by @camlloyd.

PR #621 · merged · 17 October 2026

💊

fix(pharmgx-reporter): use the shared ClawBio disclaimer in report.md. The pharmgx-reporter skill's report.md now carries the exact medical disclaimer sentence required by AGENTS.md instead of its own wording, so the markdown report reads correctly even when sent on its own. Contributed by @camlloyd.

PR #612 · merged · 17 October 2026

📄

docs(unbloat): README.md — drop FAQ duplicating earlier sections. README's FAQ section is removed: each of its eight answers repeated a section already further up the page, and one gave install instructions that contradicted the Quick Start. Contributed by @camlloyd.

PR #627 · merged · 17 October 2026

🗑️

docs: remove one-off event and hackathon files. Four one-off event files — a demo teleprompter script, a hackathon submission doc, and two slide-deck notes — are removed, as none is referenced anywhere else in the repo. Contributed by @sooraj-codes.

PR #649 · merged · 17 October 2026

📦

docs(packaging): move the release runbook to docs/releasing.md. With the stale Bioconda draft gone, packaging/ held only the release runbook, so it moves next to the other docs; the publish workflow's comment is updated to match. Contributed by @camlloyd.

PR #648 · merged · 17 October 2026

🧹

chore(packaging): delete the stale Bioconda recipe. The in-repo Bioconda recipe draft had drifted from the live recipe now maintained in bioconda-recipes, so it's deleted and packaging/README.md links to the live recipe instead. Contributed by @camlloyd.

PR #647 · merged · 17 October 2026

📝

docs(templates): ask new-skill proposers to check for similar skills first. The new-skill issue template now asks proposers to confirm no similar skill already exists, after two pairs of overlapping skills were added without either side noticing the other. Contributed by @camlloyd.

PR #643 · merged · 17 October 2026

View all merged pull requests on GitHub →

Get started in 30 seconds

Install with pip, conda, as a Claude Code plugin, or as Agent Skills in any editor that reads them. Every skill includes demo data.

        # Option 1: pip (recommended)

        pip install clawbio

        clawbio run pharmgx --demo

        # Option 2: conda

        conda install -c bioconda clawbio

        # Option 3: Claude Code plugin

        /plugin marketplace add ClawBio/ClawBio

        /plugin install clawbio

        # Option 4: Agent Skills (Cursor, VS Code, Codex, Zed)

        git clone https://github.com/ClawBio/ClawBio

        cp -r ClawBio/skills/pharmgx-reporter ~/.agents/skills/

📅 Follow Event Calendar ⭐ Star on GitHub 🤖 Try RoboTerri 📄 Documentation

The first bioinformatics-nativeAI agent skill library

Build agentic bioinformatics with us

Genomics skills, in your editor

Get started in 30 seconds

The first bioinformatics-native
AI agent skill library