OpenClaw-Medical-Skills

Installation

Install to your workspace skills directory

cp -r skills/* /skills/

Or install globally (available to all agents)

cp -r skills/* ~/.openclaw/skills/

Note: Some skills bundle large data files (databases, datasets). The sparse-checkout method above avoids downloading them. If you need the full repo including all data, install Git LFS first, then run git clone https://github.com/FreedomIntelligence/OpenClaw-Medical-Skills.git.

Skills are picked up automatically on the next session. No restart needed.

Method 4 — Install Selected Skills Only

Pick skills relevant to your domain:

## Skills Overview

| Category | Count | Highlights |
|---|---|---|
| General & Core | 10 | Browser/search, document tools, and developer workflow utilities |
| Medical & Clinical | 119 | Clinical reports, CDS, oncology, imaging, and healthcare AI |
| Scientific Databases | 43 | Genomics/protein/drug databases and biomedical knowledge retrieval |
| Bioinformatics (gptomics) | 239 | Variant analysis, sequencing QC, DE, pathways, single-cell, and epigenomics |
| Omics & Computational Biology | 59 | Single-cell/spatial, proteomics, cheminformatics, and protein design tools |
| ClawBio Pipelines | 21 | Orchestration pipelines for scRNA, GWAS, ancestry, and structural workflows |
| BioOS Extended Suite | 285 | Extended agent suite for oncology, immunology, clinical AI, and infrastructure |
| Data Science & Tools | 93 | Statistics, visualization, automation, simulation, and scientific tooling |
| **Total** | **869** | |

When to Use This Skill

This skill should be used when:

• Working with Benchling's Python SDK or REST API
• Managing biological sequences (DNA, RNA, proteins) and registry entities
• Automating inventory operations (samples, containers, locations, transfers)
• Creating or querying electronic lab notebook entries
• Building workflow automations or Benchling Apps
• Syncing data between Benchling and external systems
• Querying the Benchling Data Warehouse for analytics
• Setting up event-driven integrations with AWS EventBridge

1. Authentication & Setup

Python SDK Installation:

# or with Poetry
poetry add benchling-sdk

Authentication Methods:

API Key Authentication (recommended for scripts):

from benchling_sdk.benchling import Benchling
from benchling_sdk.auth.api_key_auth import ApiKeyAuth

benchling = Benchling(
 url="https://your-tenant.benchling.com",
 auth_method=ApiKeyAuth("your_api_key")
)

OAuth Client Credentials (for apps):

from benchling_sdk.auth.client_credentials_oauth2 import ClientCredentialsOAuth2

auth_method = ClientCredentialsOAuth2(
 client_id="your_client_id",
 client_secret="your_client_secret"
)
benchling = Benchling(
 url="https://your-tenant.benchling.com",
 auth_method=auth_method
)

Key Points:

• API keys are obtained from Profile Settings in Benchling
• Store credentials securely (use environment variables or password managers)
• All API requests require HTTPS
• Authentication permissions mirror user permissions in the UI

For detailed authentication information including OIDC and security best practices, refer to references/authentication.md.

5. Workflows & Automation

Automate laboratory processes using Benchling's workflow system.

Creating Workflow Tasks:

from benchling_sdk.models import WorkflowTaskCreate

task = benchling.workflow_tasks.create(
    WorkflowTaskCreate(
        name="PCR Amplification",
        workflow_id="wf_abc123",
        assignee_id="user_abc123",
        fields=benchling.models.fields({"template": "seq_abc123"})
    )
)

Updating Task Status:

from benchling_sdk.models import WorkflowTaskUpdate

updated_task = benchling.workflow_tasks.update(
    task_id="task_abc123",
    workflow_task=WorkflowTaskUpdate(
        status_id="status_complete_abc123"
    )
)

Asynchronous Operations:

Some operations are asynchronous and return tasks:

# Update all pending tasks for a workflow
tasks = benchling.workflow_tasks.list(
 workflow_id="wf_abc123",
 status="pending"
)

for page in tasks:
 for task in page:
 # Perform automated checks
 if auto_validate(task):
 benchling.workflow_tasks.update(
 task_id=task.id,
 workflow_task=WorkflowTaskUpdate(
 status_id="status_complete"
 )
 )

4. Data Export: