cc-polymath

🥈Silver

cc-polymath enables Claude Code to automate complex tasks across cloud infrastructure, design, and advanced maths. Operations teams can streamline workflows, reduce manual effort, and improve accuracy. It connects to Claude Code plugins and integrates with existing Python-based tools.

9470Updated 2w ago

Intermediate30min to implementautomation

Saves ~90 min per use

Quick InstallView Source

git clone https://github.com/rand/cc-polymath.git

Works with:

Claude

Overview

About This Skill

How to Use

[{"step":"Define the scope of automation","action":"Identify the specific task or workflow you want to automate (e.g., 'deploy a Kubernetes cluster', 'scale cloud resources', or 'solve a complex mathematical optimization problem'). Use [PLACEHOLDERS] in the prompt to specify cloud providers, tools, and configurations.","tip":"Start with a single, well-defined task. For example, 'automate the deployment of a serverless function on AWS Lambda' is clearer than 'automate cloud stuff'."},{"step":"Specify integration requirements","action":"List the tools, APIs, or existing pipelines that the automation must connect to (e.g., Terraform, GitHub Actions, Kubernetes, or Python libraries like NumPy/PyTorch). Include these in the prompt template under [EXISTING_TOOLS/PIPELINES].","tip":"If you're unsure about integration points, ask the AI to suggest compatible tools or libraries. For example, 'What Python libraries integrate well with AWS CDK for infrastructure automation?'"},{"step":"Set error handling and validation rules","action":"Define what the automation should do if it encounters common failure points (e.g., permission errors, resource limits, or API timeouts). Include these in the prompt under [COMMON_FAILURE_POINTS].","tip":"For cloud infrastructure, always include IAM permission checks. For math problems, specify fallback methods if numerical methods fail to converge."},{"step":"Execute and validate the output","action":"Run the generated automation code in your environment (e.g., Claude Code, AWS CloudShell, or a local Python environment). Review the output for correctness and test the deliverables (e.g., deployed infrastructure or mathematical results).","tip":"For infrastructure automation, use Terraform's `plan` command before `apply` to preview changes. For math problems, verify results with known test cases."},{"step":"Iterate and extend","action":"Refine the automation by adding more features or handling edge cases. For example, extend a Kubernetes deployment script to include monitoring or logging integrations.","tip":"Document the automation's behavior and limitations. For example, 'This script assumes the AWS region is us-east-1 and will fail if the region is not supported.'"}]

Setup & Installation

Quick Install

No install command available. Check the GitHub repository for manual installation instructions.

Alternative Install (Git Clone)

git clone https://github.com/rand/cc-polymath

Requirements

Claude Code or compatible AI agent
Works with: Claude

Quick Start Guide

Install the Skill

Copy the install command above and run it in your terminal.

Open Your AI Agent

Launch Claude Code, Cursor, or your preferred AI coding agent.

Try It Out

Use the prompt template or examples below to test the skill.

Customize

Adapt the skill to your specific use case and workflow.

Usage Examples

Prompt Template

Use cc-polymath to automate [TASK] across [CLOUD_PROVIDER/INFRASTRUCTURE_AREA] with [SPECIFIC_METHOD]. Ensure the solution integrates with [EXISTING_TOOLS/PIPELINES] and includes error handling for [COMMON_FAILURE_POINTS]. Provide the final deliverable as [OUTPUT_FORMAT]. Example: 'Use cc-polymath to automate the deployment of a Kubernetes cluster on AWS with Terraform. Integrate the solution with GitHub Actions for CI/CD and include error handling for IAM permission failures. Provide the final deliverable as a Terraform module with a README.'

Example Output

```python
# Automated Kubernetes Cluster Deployment on AWS using cc-polymath
# Generated: 2024-05-20 | Version: 1.2.0

import boto3
from cc_polymath.terraform import TerraformAutomation
from cc_polymath.kubernetes import K8sClusterConfig

# Initialize AWS and Terraform clients
aws_client = boto3.client('ec2')
terraform = TerraformAutomation(
    backend_config={
        'bucket': 'my-terraform-state-bucket',
        'key': 'k8s-cluster/terraform.tfstate',
        'region': 'us-east-1'
    }
)

# Define cluster configuration
cluster_config = K8sClusterConfig(
    cluster_name="prod-ai-platform",
    node_groups=[
        {
            'name': 'gpu-nodes',
            'instance_type': 'g4dn.xlarge',
            'min_size': 2,
            'max_size': 5,
            'labels': {'gpu': 'true', 'workload': 'ai-training'}
        },
        {
            'name': 'cpu-nodes',
            'instance_type': 'm5.xlarge',
            'min_size': 3,
            'max_size': 10,
            'labels': {'workload': 'general'}
        }
    ],
    vpc_config={
        'cidr_block': '10.0.0.0/16',
        'subnets': ['10.0.1.0/24', '10.0.2.0/24'],
        'nat_gateway': True
    },
    addons=[
        'aws-load-balancer-controller',
        'cluster-autoscaler',
        'metrics-server'
    ]
)

# Generate Terraform files
terraform.generate_infrastructure(
    config=cluster_config,
    output_dir="./terraform/k8s-cluster"
)

# Validate IAM permissions before deployment
required_permissions = [
    'ec2:DescribeVpcs',
    'eks:CreateCluster',
    'iam:PassRole',
    's3:GetObject'
]
permission_check = terraform.validate_iam_permissions(required_permissions)

if not permission_check['all_permissions_granted']:
    print("ERROR: Missing IAM permissions:")
    for perm in permission_check['missing_permissions']:
        print(f"- {perm}")
    raise PermissionError("Insufficient IAM permissions for cluster deployment")

# Deploy the cluster
print("Deploying Kubernetes cluster...")
deployment_result = terraform.apply(
    working_dir="./terraform/k8s-cluster",
    auto_approve=False,
    var_file="terraform.tfvars"
)

# Post-deployment verification
if deployment_result['success']:
    print("Cluster deployed successfully!")
    print(f"Cluster endpoint: {deployment_result['cluster_endpoint']}")
    print(f"Kubeconfig path: {deployment_result['kubeconfig_path']}")
    
    # Configure kubectl
    kubectl_config = f"""
apiVersion: v1
clusters:
- cluster:
    certificate-authority-data: {deployment_result['cluster_ca_cert']}
    server: {deployment_result['cluster_endpoint']}
  name: {cluster_config.cluster_name}
contexts:
- context:
    cluster: {cluster_config.cluster_name}
    user: {cluster_config.cluster_name}-admin
  name: {cluster_config.cluster_name}
current-context: {cluster_config.cluster_name}
kind: Config
preferences: {{}}
users:
- name: {cluster_config.cluster_name}-admin
  user:
    exec:
      apiVersion: client.authentication.k8s.io/v1beta1
      command: aws
      args:
        - --region
        - us-east-1
        - eks
        - get-token
        - --cluster-name
        - {cluster_config.cluster_name}
"""
    with open("~/.kube/config", "w") as f:
        f.write(kubectl_config)
    
    print("kubectl configuration updated successfully.")
else:
    print("Deployment failed. Error:")
    print(deployment_result['error'])
```