CreateOS provides a platform for AI agents, APIs, backends, and more to be shipped directly to production. It is designed for developers looking to streamline their deployment processes across various services.
$ npx skills add https://github.com/nodeops-app/skills --skill createosThe CreateOS skill enables AI agents to deploy applications, APIs, and backends directly to the CreateOS cloud platform. It supports two authentication modes: MCP mode (preferred, requiring no API key) and REST/script mode (using CREATEOS_API_KEY environment variable). The skill integrates with Claude Code, Cursor, Windsurf, and 40+ other AI coding agents through the skills.sh CLI. It simplifies deployment workflows by allowing agents to ship production-ready code without manual platform configuration. Developers can install the skill via npm and use it alongside complementary migration tools like vercel-to-createos.
Install using the provided npx command and authenticate using MCP.
Deploy AI agents using MCP without needing an API key
Upload deployment files directly to CreateOS
List projects hosted on CreateOS
Migrate applications from Vercel to CreateOS
$ npx skills add https://github.com/nodeops-app/skills --skill createosgit clone https://github.com/nodeops-app/skillsCopy the install command above and run it in your terminal.
Launch Claude Code, Cursor, or your preferred AI coding agent.
Use the prompt template or examples below to test the skill.
Adapt the skill to your specific use case and workflow.
Generate a production-ready deployment configuration for a [TYPE] service for [COMPANY] in the [INDUSTRY] industry. Include infrastructure requirements, environment variables, and scaling parameters based on this data: [DATA]. Ensure the output is optimized for [SERVICE_PLATFORM] and includes best practices for security and performance.
# Production Deployment Configuration for Acme Corp's Payment Processing API ## Service Overview - **Service Type**: RESTful API - **Company**: Acme Corp - **Industry**: Fintech - **Target Platform**: AWS ECS with Fargate ## Infrastructure Requirements ### Compute - **CPU**: 2 vCPUs (baseline) - **Memory**: 4GB (adjustable to 8GB during peak loads) - **Concurrency**: 100 requests per container - **Auto Scaling**: Min 2, Max 10 containers based on CPU >70% for 5 minutes ### Storage - **Database**: Amazon RDS (PostgreSQL) with 100GB SSD storage - **Cache**: Amazon ElastiCache (Redis) with 5GB memory - **Logs**: Amazon CloudWatch with 30-day retention ### Networking - **VPC**: Dedicated VPC with private subnets for containers - **Load Balancer**: Application Load Balancer with HTTPS termination - **Security Groups**: Restrict access to database and cache to API containers only ## Environment Variables ``` NODE_ENV=production DATABASE_URL=postgres://user:[email protected]:5432/payments REDIS_URL=redis://acme-cache.cluster-xyz.cache.amazonaws.com:6379 JWT_SECRET=xxxxxxxxxxxxxxxxxxxxxxxxxxxx STRIPE_API_KEY=sk_live_xxxxxxxxxxxxxxxx ``` ## Security Best Practices - Enable AWS WAF for DDoS protection - Rotate database credentials every 90 days using AWS Secrets Manager - Implement mutual TLS for internal service-to-service communication - Set up CloudTrail logging for all API calls ## Monitoring & Alerts - CloudWatch Alarms for: - CPU >80% for 5 minutes - Memory >90% for 1 minute - 5xx errors >1% in 5 minutes - SNS notifications to #devops-alerts Slack channel ## Deployment Pipeline 1. **Build**: Docker image built and pushed to ECR 2. **Test**: Run integration tests in staging environment 3. **Deploy**: Blue-green deployment with 10% traffic to new version 4. **Verify**: Automated health checks and performance benchmarks 5. **Promote**: Full traffic shift after 30 minutes of stable operation
Take a free 3-minute scan and get personalized AI skill recommendations.
Take free scan