Traction scoreGitHub stars can be faked, so popularity alone can be misleading. Traction Score looks for broader signs of recent attention, adoption, and active maintenance.
ClawBio provides bioinformaticians with a structured set of tools for processing complex biological data. The repository streamlines the transition from raw sequence files to actionable reports, enabling more precise genome assessment and protein analysis.
By integrating utilities for FASTA metrics and unified proteomics pipelines, the library helps researchers automate the detection of sequence-level characteristics and manage data from platforms like Olink and SomaLogic.
WHO IT'S FOR
Bioinformaticians
automate sequence analysis and proteomics pipelines
Compatible AgentsThe repository documents support for these agents. The skills may also work with other agents that can load SKILL.md files, but they may need some setup or small changes.
Installs: Complete ClawBio source checkout with all skills and full demo data; skillPaths is a bounded selection, not the checkout's complete inventory.
Before you start
Python 3.11+
Git
uv installed
Run from: The parent directory where the new ClawBio checkout should be created
Run this complete block in a terminal. It clones the repository into ClawBio, enters that directory, synchronizes the locked environment, and runs the documented demo.
git clone https://github.com/ClawBio/ClawBio.git
cd ClawBio
uv sync # installs from pyproject.toml + uv.lock
uv run python clawbio.py run pharmgx --demo
Installs: Only the clinpgx skill folder in the user's shared Agent Skills directory. · Cursor, VS Code, Codex, Zed
Before you start
Python 3.11+
A local ClawBio source checkout
requests >= 2.28.0
Platform: darwin or linux
Run from: ClawBio repository root
Manually copy or symlink the repository folder skills/clinpgx/ into ~/.agents/skills/. This is a filesystem action performed outside an agent session; the author supplies no exact terminal command.
Installs: Only the gwas-lookup skill folder in the user's shared Agent Skills directory. · Cursor, VS Code, Codex, Zed
Before you start
Python 3.11+
A local ClawBio source checkout
requests >= 2.28
Platform: darwin or linux
Run from: ClawBio repository root
Manually copy or symlink the repository folder skills/gwas-lookup/ into ~/.agents/skills/. This is a filesystem action performed outside an agent session; the author supplies no exact terminal command.
Installs: Only the ukb-navigator skill folder in the user's shared Agent Skills directory. · Cursor, VS Code, Codex, Zed
Before you start
Python 3.11+
A local ClawBio source checkout
chromadb >= 0.4
Platform: darwin or linux
Run from: ClawBio repository root
Manually copy or symlink the repository folder skills/ukb-navigator/ into ~/.agents/skills/. This is a filesystem action performed outside an agent session; the author supplies no exact terminal command.
Gene symbol: CYP2D6 (replace with another standard HGNC pharmacogene symbol if desired)
Python 3.11+
requests >= 2.28.0
Access to the ClinPGx REST API
Using the clinpgx skill, look up CYP2D6 on ClinPGx and produce a concise report covering known alleles, function annotations, associated gene-drug pairs, and available CPIC evidence. Cite ClinPGx/PharmGKB and clearly label this as research and educational information.
Public dbSNP identifier: rs429358 (replace with another valid rsID if desired)
Python 3.11+
requests >= 2.28
Network access to the documented public genomic APIs
Using the gwas-lookup skill, find the GWAS associations for rs429358. Resolve its coordinates and alleles, then provide a concise unified summary of its strongest GWAS, PheWAS, eQTL, and fine-mapping results, noting any source that fails.
Research question: UK Biobank fields that measure kidney function
Python 3.11+
chromadb >= 0.4
The documented UK Biobank schema source; first use requires indexing it into ChromaDB
voyageai is optional because the skill documents a fallback to ChromaDB defaults
Using the ukb-navigator skill, identify the most relevant UK Biobank fields that measure kidney function. Return a small ranked table with field IDs, descriptions, categories, and relevance scores.