aws-cloud-watch
Query AWS CloudWatch metrics for ECS/EC2/RDS and return charts.
Why use this skill?
Easily query ECS, EC2, and RDS metrics directly in your agent. Lightweight, secure, and built for fast cloud infrastructure insights.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/delbertheihei/aws-cloud-watchWhat This Skill Does
The aws-cloud-watch skill is a specialized utility designed for OpenClaw AI agents to interface directly with AWS CloudWatch without relying on the bulky AWS SDK. It enables the agent to query, retrieve, and summarize critical infrastructure metrics for AWS ECS, EC2, and RDS services. By implementing custom SigV4 signing using native cryptographic modules, it offers a lightweight and secure way to monitor your cloud resource health. The skill provides text-based summaries of metric performance, allowing the agent to interpret and communicate resource utilization trends, such as CPU spikes or memory pressure, directly within your chat interface.
Installation
To integrate this skill into your environment, use the OpenClaw hub command:
clawhub install openclaw/skills/skills/delbertheihei/aws-cloud-watch
Ensure that you have your AWS credentials properly configured in your agent environment. You must set the AWS_ACCESS_KEY_ID and AWS_SECRET_ACCESS_KEY environment variables. Optionally, specify your AWS_REGION to override the default us-west-2 setting. The skill runs locally using Node.js and requires no external heavy dependencies, making it ideal for streamlined agent deployments.
Use Cases
This skill is highly effective for DevOps teams and cloud engineers who need real-time operational insights without navigating the complex AWS Management Console. Common scenarios include:
- Monitoring production cluster health: Quickly verifying if an ECS cluster is overloaded during high-traffic events.
- Database performance analysis: Checking RDS latency or CPU utilization to troubleshoot slow query performance.
- Infrastructure auditing: Fetching historical metric data to correlate performance issues with recent deployments.
- Automated incident response: Having the agent fetch specific resource logs when an alert is triggered, providing context before a human even checks the system.
Example Prompts
- "Check the CPU utilization for my production-cluster in ECS for the last 3 hours."
- "What is the current CPU load on the database instance rds-prod-01?"
- "Summarize the performance metrics for my ec2 instance i-0abcdef123456789 over the last hour."
Tips & Limitations
The aws-cloud-watch skill is currently optimized for text-based summaries rather than visual chart rendering. While it provides accurate numerical data, complex performance analysis may require supplementary tools. Note that ECS metrics are strictly cluster-level unless you have explicitly enabled Container Insights in your AWS configuration. If a requested metric is unavailable, the skill is designed to return a clear notification rather than failing silently, which helps in debugging agent interactions. Always ensure your IAM user or role has cloudwatch:GetMetricStatistics permissions to ensure smooth operation.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-delbertheihei-aws-cloud-watch": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: network-access, external-api