A comprehensive API and toolset for biological data access, literature search, and advanced computational biology workflows.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install openbio
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install openbio using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is OpenBio?
OpenBio is a powerful integration for Openclaw Skills that bridges the gap between AI agents and the complex world of biological sciences. It provides a unified interface to query major biological databases like PDB, UniProt, and ChEMBL, alongside tools for scientific literature discovery via PubMed and bioRxiv. Beyond data retrieval, it enables agents to perform sophisticated computational tasks such as protein structure prediction using Boltz or Chai, molecular biology experiment design, and pathway enrichment analysis.
By leveraging this skill, developers can build agents capable of assisting in drug discovery, genomic research, and synthetic biology. The skill ensures high-quality results by incorporating domain-specific quality thresholds, such as AlphaFold pLDDT scores and experimental resolution metrics, making it an essential asset for any bio-focused Openclaw Skills deployment.
OpenBio Use Cases
- Automating scientific literature reviews and data extraction from PubMed or bioRxiv.
- Predicting protein structures and binding affinities using state-of-the-art ML models like Boltz-2 and Chai-1.
- Designing molecular biology experiments, including primer design, Gibson assembly, and restriction digests.
- Analyzing genomic variants, clinical trial data, and GWAS associations for medical research.
- Parsing and editing plasmid files for synthetic biology and cloning workflows.
How OpenBio Works
- The agent performs a version check to ensure the local skill matches the latest OpenBio API specifications.
- Users authenticate via an environment variable to access secure endpoints.
- The agent retrieves the specific tool schema to identify required parameters and data types.
- For heavy computational tasks, the agent submits a job and receives a unique job ID for asynchronous processing.
- The agent polls the status endpoint and retrieves the final results, including download URLs for structural data or analysis reports.
OpenBio Setup
To get started with OpenBio, install the skill using the following command:
bunx skills add https://github.com/openbio-ai/skills --skill openbio
Next, set your API key as an environment variable. You can generate a key at the OpenBio profile page:
export OPENBIO_API_KEY=your_key_here
Verify the installation by performing a health check:
curl -X GET "https://api.openbio.tech/api/v1/tools/health"
OpenBio Data Schema & Taxonomy
OpenBio organizes its data through a structured API response system. Metadata and results are categorized by biological entity type.
| Data Type | Description | Key Metadata |
|---|---|---|
| Protein Structures | PDB/AlphaFold data | pLDDT scores, resolution, chain IDs |
| Literature | Citations and abstracts | DOI, PMID, publication date |
| Genomics | Variants and genes | p-values, chromosome location, VEP predictions |
| Jobs | Asynchronous tasks | job_id, status, result_url |
All tools follow a strict schema-first approach, where the validation endpoint can be used to verify payloads before execution within Openclaw Skills.
OpenBio Advanced Features
- Support for long-running asynchronous jobs with automated polling for structure prediction and BLAST searches.
- Multi-modal structure prediction involving proteins, ligands, RNA, and glycans via Chai-1.
- De novo protein design from text descriptions using Pinal.
- Deep integration with cheminformatics tools for Tanimoto similarity and molecular property calculation.
- Domain-specific decision trees to guide the AI agent to the most appropriate biological tool for a specific task.
SKILL.md
Loading
Related Openclaw Skills
Learning Coach
A production-grade AI learning assistant that facilitates a plan-learn-practice-assess loop with proactive automation and deep subject isolation.
Intercom
A secure, opt-in communication bridge for routing messages between different AI agent sessions via internal session keys.
Xiaomi Outbound Bot (Alibaba Cloud)
A specialized automation skill for triggering and managing batch outbound telephone tasks via the Alibaba Cloud Xiaomi platform.
Business Claw ERPNext Skills
A powerful collection of pre-defined business workflows that integrate MCP tools with ERPNext to automate complex enterprise tasks.
hey.lol AI Creator Skill
Enable your AI agent to build a social media presence, engage with humans, and earn money through paywalled content.
Host Ping
A reliable networking skill designed to detect host availability and measure latency for specific IP addresses via ICMP.
METADATA
Featured*
