bio-orchestrator

Route bioinformatics requests to specialized skills for automated analysis orchestration.

1.1k|238|Updated Feb 25, 2026
One-click install
npx skills add https://github.com/ClawBio/ClawBio --skill bio-orchestrator
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: bio-orchestrator
Source: https://github.com/ClawBio/ClawBio/tree/main/skills/bio-orchestrator
Command: npx skills add https://github.com/ClawBio/ClawBio --skill bio-orchestrator

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

The Bio Orchestrator routes diverse bioinformatics requests to specialised sub-skills, removing the burden of manual skill selection, file-format detection, and multi-step workflow assembly so users can focus on scientific questions instead of tooling logistics.

Core Features & Use Cases

  • File Type Detection & Routing: Detects common bioinformatics file types (VCF, FASTQ, BAM, PDB, h5ad, CSV) and routes them to the appropriate specialised skill.
  • Multi-Step Analysis Planning: Plans and chains multiple skills for complex workflows (e.g., annotate VCF then compute diversity metrics) with dependency checks and human checkpoints.
  • Report Generation & Reproducibility: Produces structured markdown reports with methods, results, figures, citations, reproducibility bundles (conda environment, commands, checksums), and an audit log.
  • Safety & Governance: Enforces local-first policies, explicit consent for uploads, path validation, and audit logging to prevent accidental data exfiltration or destructive actions.

Quick Start

Route sample.vcf for annotation and diversity scoring and produce a reproducible markdown report.

Frequently Asked Questions about bio-orchestrator

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate multi-step bioinformatics workflows with VCF and FASTQ files?

Bioinformatics orchestration routes requests to specialized skills based on file-type detection, applying multi-step analysis planning and dependency checks across genomics and sequencing workflows. It removes manual skill selection and workflow assembly by chaining outputs and logging audits automatically.

Can I chain genomics analyses like VCF annotation and diversity scoring together?

Yes, you can chain genomics analyses like VCF annotation and diversity scoring. The orchestrator plans multi-step workflows, checks dependencies, and dispatches to multiple specialized skills sequentially, passing upstream outputs to downstream tasks automatically.

Does this bioinformatics orchestration support reproducibility bundles with checksums?

Yes, bioinformatics orchestration supports reproducibility by generating structured markdown reports alongside bundles. These bundles include conda environments, exact commands, and checksums to ensure analyses can be validated and reproduced reliably.

What bioinformatics file formats can be automatically detected and routed for analysis?

The bioinformatics orchestration system automatically detects common file formats including VCF, FASTQ, BAM, PDB, h5ad, and CSV. It uses extension and keyword detection to route these files to appropriate specialized skills for targeted analysis.

How do I ensure local data safety when orchestrating single-cell and structural biology workflows?

To ensure local data safety during single-cell and structural biology workflows, the orchestration enforces local-first policies, path validation, and explicit consent for uploads. It maintains audit logs to prevent accidental data exfiltration or destructive actions.