AWS Agent Skills enable Claude agents to interact with AWS services. Operations teams use it to automate cloud infrastructure tasks. It connects to AWS APIs for managing resources, monitoring, and deployment.
git clone https://github.com/itsmostafa/aws-agent-skills.githttps://github.com/itsmostafa/aws-agent-skills
["1. Identify the specific AWS service and task you want to automate. Common services include EC2, S3, Lambda, and RDS.","2. Determine the authentication method. Use IAM roles for EC2 instances or access keys for external applications. Ensure the IAM role has the necessary permissions.","3. Write the AWS Agent Skill using the AWS SDK (boto3 for Python). Include error handling for common issues like API throttling, invalid parameters, and permission errors.","4. Test the skill in a non-production environment. Use AWS CloudWatch Logs to monitor the skill's performance and troubleshoot any issues.","5. Deploy the skill to your production environment. Monitor its performance and make adjustments as needed. Use AWS CloudTrail to track API calls made by the skill."]
Automate the creation of IAM policies for various AWS services.
Develop and debug serverless Lambda functions triggered by S3 events.
Generate Infrastructure as Code templates for deploying AWS resources.
Set up monitoring and alerting using CloudWatch for critical applications.
No install command available. Check the GitHub repository for manual installation instructions.
git clone https://github.com/itsmostafa/aws-agent-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.
Create an AWS Agent Skill to [SPECIFIC_TASK] in our AWS environment. The skill should connect to our [AWS_SERVICE] using [AUTHENTICATION_METHOD]. Ensure it follows our [SECURITY_POLICY] guidelines. Provide the necessary IAM permissions and error handling for [COMMON_ISSUES].
Here's an AWS Agent Skill to automate EC2 instance scaling based on CPU utilization:
```python
import boto3
class ScaleEC2Instances:
def __init__(self):
self.cloudwatch = boto3.client('cloudwatch')
self.autoscaling = boto3.client('autoscaling')
def check_cpu_utilization(self, auto_scaling_group_name):
# Get CPU utilization metrics for the past 5 minutes
response = self.cloudwatch.get_metric_statistics(
Namespace='AWS/EC2',
MetricName='CPUUtilization',
Dimensions=[{'Name': 'AutoScalingGroupName', 'Value': auto_scaling_group_name}],
StartTime=datetime.utcnow() - timedelta(minutes=5),
EndTime=datetime.utcnow(),
Period=300,
Statistics=['Average']
)
return response['Datapoints'][0]['Average'] if response['Datapoints'] else 0
def scale_instances(self, auto_scaling_group_name, desired_capacity):
self.autoscaling.set_desired_capacity(
AutoScalingGroupName=auto_scaling_group_name,
DesiredCapacity=desired_capacity
)
def execute(self, auto_scaling_group_name):
cpu_utilization = self.check_cpu_utilization(auto_scaling_group_name)
current_capacity = self.autoscaling.describe_auto_scaling_groups(
AutoScalingGroupNames=[auto_scaling_group_name]
)['AutoScalingGroups'][0]['DesiredCapacity']
if cpu_utilization > 70 and current_capacity < 10:
self.scale_instances(auto_scaling_group_name, current_capacity + 1)
elif cpu_utilization < 30 and current_capacity > 2:
self.scale_instances(auto_scaling_group_name, current_capacity - 1)
```
This skill monitors CPU utilization and scales instances up or down based on predefined thresholds. It requires IAM permissions for CloudWatch and AutoScaling services. Error handling includes checking for valid metrics and capacity limits.Cloud computing platform with 200+ services
IronCalc is a spreadsheet engine and ecosystem
ITIL-aligned IT service management platform
Customer feedback management made simple
Enterprise workflow automation and service management platform
Automate your spreadsheet tasks with AI power
Take a free 3-minute scan and get personalized AI skill recommendations.
Take free scan