📊 Publicly benchmarked · 1,136 stars · 98 skills · 50 contributors · 5,040 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/.

✅ 98 skills, 91 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✗ AI hallucinates star alleles & outdated guidelines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

98 skills · 92 with runnable demo data · 5,040 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

+ 93 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

Repo	OpenClaw	Stars	Forks	Skills
ClawBio	✓	1,136	266	97
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

🧬

fix(dnasp): name the CLI flag each metadata input maps to. The dnasp skill now correctly names the CLI flag for each metadata input in its argument parser, fixing a registration error that prevented the flags from being recognised on the command line. Contributed by @drdaviddelorenzo.

PR #448 · merged · 17 September 2026

🌿

phylogenetics-builder: protect a rerun's input from being overwritten. The phylogenetics-builder skill now guards its input file from being overwritten during a rerun, preventing a race condition that could silently corrupt the alignment before IQ-TREE processes it. Contributed by @drdaviddelorenzo.

PR #446 · merged · 17 September 2026

🔍

fix: honour GWAS Catalog association max_hits. The gwas-lookup skill now correctly passes the max_hits parameter through to the GWAS Catalog query, preventing the result set from being silently capped at the default page size. Contributed by @krudo-taco.

PR #443 · merged · 17 September 2026

🔬

refactor(fine-mapping): delegate the SuSiE engine to sushie 0.20. The fine-mapping skill now delegates its SuSiE engine to the sushie 0.20 package, removing an internal implementation that had diverged from upstream and picking up improved numerical stability and credible-set diagnostics. Contributed by @camlloyd.

PR #423 · merged · 17 September 2026

🏥

fix: preserve EUCTR trial registry identifiers. The clinical-trial-finder skill now preserves EUCTR identifiers exactly as returned by the registry, fixing a normalisation step that was stripping required hyphens and causing downstream lookup failures. Contributed by @krudo-taco.

PR #444 · merged · 16 September 2026

🧬

fix: treat partial VCF GT calls as no-calls. Partial genotype calls (e.g. ./1 or 1/.) in VCF input are now treated as missing rather than being silently mis-parsed, preventing incorrect allele counts in downstream skill analyses. Contributed by @krudo-taco.

PR #442 · merged · 16 September 2026

🧬

fix: parse BOM-prefixed genetic exports. Genetic export files with a UTF-8 BOM prefix (common in Windows-generated 23andMe and AncestryDNA exports) are now correctly parsed, removing a silent data-loss bug that caused the first variant to be dropped or misread. Contributed by @krudo-taco.

PR #441 · merged · 16 September 2026

🌿

phylogenetics-builder: keep the alignments produced by the pipeline. The phylogenetics-builder skill now retains the intermediate alignment files in the output directory, allowing users to inspect and reuse the multiple sequence alignment that IQ-TREE processed. Contributed by @drdaviddelorenzo.

PR #439 · merged · 16 September 2026

🧬

bio-orchestrator: route population-genetics statistics and alignment NEXUS files to dnasp. The bio-orchestrator now routes population-genetics statistics queries and NEXUS alignment files to the dnasp skill, expanding its vocabulary for evolutionary and sequence-analysis requests. Contributed by @drdaviddelorenzo.

PR #438 · merged · 16 September 2026

🧬

dnasp: v0.5.2 - DnaSP 6.12.03 validation fixes and result.json envelope. The dnasp skill received targeted validation fixes matching DnaSP 6.12.03 outputs and now wraps all results in a structured result.json envelope for downstream consumption. Contributed by @drdaviddelorenzo.

PR #437 · merged · 16 September 2026

View all merged pull requests on GitHub →

The first bioinformatics-native
AI agent skill library

Build agentic bioinformatics with us

Genomics skills, in your editor

Get started in 30 seconds

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