🦖 ClawBio — Bioinformatics AI Agent Skills

New in v0.6.1 · Model Context Protocol

Genomics skills, in your editor

ClawBio speaks MCP, so the skill library is callable from Cursor, Zed, VS Code agent mode and Claude Desktop, not just Claude Code. Most bioinformatics MCP servers retrieve records. This one executes: it runs the real skill on your machine and hands 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.

            $ uvx --from 'clawbio[mcp]' clawbio mcp
          

No install required. Add the same three lines to your client's config and restart it.

✅ 97 skills, each flagged runnable or spec-only
🔒 Demo data only until you opt in explicitly
🏠 Local stdio. No hosted endpoint, by design

// Cursor, Claude Desktop, VS Code, Zed
{
  "mcpServers": {
    "clawbio": {
      "command": "uvx",
      "args": ["--from", "clawbio[mcp]",
               "clawbio", "mcp"]
    }
  }
}

📄 MCP setup guide 🏷️ Release notes

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✗ AI hallucinates star alleles & outdated guidelines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

97 skills · 91 with runnable demo data · 4,039 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

+ 92 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	✓	1,118	256	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

🔧

Refactor: SHA-256 helpers delegated to clawbio.common.checksums. Checksum utilities previously duplicated across skills are now centralised in a shared module, reducing maintenance burden and ensuring consistent hashing behaviour. Contributed by @camlloyd.

PR #351 · merged · 26 August 2026

📄

Docs: CI false claim about #329 environment.yml corrected. A documentation fix removing an inaccurate statement that PR #329 included a committed environment.yml alongside the CI scripts, which it did not.

PR #363 · merged · 23 August 2026

⚙️

CI: auto-approve queued runs for PRs that touch only skills/. CI workflows now automatically approve queued workflow runs for pull requests that exclusively modify files under skills/, reducing manual intervention for skill-only contributions.

PR #362 · merged · 23 August 2026

🐛

Fix: catalog and CI no longer assume every skill is Python. The catalog generator and CI test-scoping scripts previously treated all skills as Python-backed, causing incorrect maturity tier detection and false CI failures for skills implemented in other languages or as spec-only entries.

PR #361 · merged · 22 August 2026

🐛

Fix: claw-semantic-sim drops the false "works out of the box" demo claim. The skill's SKILL.md falsely stated that a runnable demo was available out of the box. The claim has been removed to accurately reflect the current implementation status.

PR #358 · merged · 22 August 2026

🐛

Fix: gwas-prs panel citations corrected; demo panels no longer shadow real PGS Catalog scores. Demo PGS panels were being prioritised over live PGS Catalog lookups for matching traits, causing real scores to be silently skipped. Panel citations now correctly reference the originating PGS Catalog study.

PR #357 · merged · 21 August 2026

🐛

Fix: correct strand guidance and stale expression values in the gi-* skills. The gi-promoter, gi-splice, gi-enhancer, gi-chromatin, gi-expression, and gi-annotation skills contained stale expression values and incorrect strand orientation guidance. All six skills have been updated with validated guidance. Contributed by @boldakov.

PR #354 · merged · 21 August 2026

🔬

New skill: deepspot-m — transcriptome-wide virtual spatial transcriptomics from H&E histology tiles. Predicts spatial gene expression across the full transcriptome from standard haematoxylin and eosin images using the DeepSpot-M model, without needing spatial sequencing. Contributed by @KalinNonchev. Total: 97 skills.

PR #331 · merged · 21 August 2026

📄

Docs: audit.py updated to point to the relocated GenAI semantic conventions repository. The audit script was referencing an old repository path for the GenAI OpenTelemetry semantic conventions, causing 404 errors during CI audits. The reference is now updated to the current location.

PR #349 · merged · 21 August 2026

🔬

Scientific audit can now fail: gate on a committed bench baseline. The scientific-audit workflow now compares benchmark results against a committed baseline rather than always reporting pass. A benchmark regression blocks the pull request, preventing inflated pass-rate headlines on the public leaderboard.

PR #343 · merged · 13 August 2026

View all merged pull requests on GitHub →

The first bioinformatics-native
AI agent skill library

Genomics skills, in your editor

Get started in 30 seconds

The first bioinformatics-nativeAI agent skill library

Genomics skills, in your editor

Get started in 30 seconds

The first bioinformatics-native
AI agent skill library