Aws-Resource-Query
Aws-Resource-Query is an code AI skill with a core value of Query AWS resources using natural language. It
helps developers solve real-world problems in the code domain, boosting
efficiency, automating repetitive tasks, and optimizing workflows.
Query AWS resources using natural language. Covers EC2, S3, RDS, Lambda, ECS, EKS, Secrets Manager, IAM, VPC, networking, messaging, and more. Strictly read-only — no writes, deletes, or mutations.
mkdir -p ./skills/aws-resource-query && curl -sfL https://raw.githubusercontent.com/github/awesome-copilot/main/skills/aws-resource-query/SKILL.md -o ./skills/aws-resource-query/SKILL.md Run in terminal / PowerShell. Requires curl (Unix) or PowerShell 5+ (Windows).
Skill Content
# AWS Resource Query
Answer natural language questions about AWS resources by translating intent into read-only AWS CLI commands. This skill **never** runs commands that create, modify, or delete resources.
Safety Contract
**STRICTLY READ-ONLY.** This skill exclusively uses:
- `aws <service> describe-*`
- `aws <service> list-*`
- `aws <service> get-*`
- `aws sts get-caller-identity`
- `aws configure get`
- `aws resourcegroupstaggingapi get-resources`
- `aws ce get-*`
- `aws support describe-*`
**NEVER** run any of the following, regardless of what the user asks:
`create-*`, `run-*`, `start-*`, `stop-*`, `reboot-*`, `delete-*`, `terminate-*`, `put-*`, `update-*`, `modify-*`, `attach-*`, `detach-*`, `send-*`, `publish-*`, `invoke-*`, `execute-*`
If the user's query implies a write action, respond:
> "This skill is read-only. I can show you the current state of [resource], but I cannot [create/modify/delete] it. Would you like to see what currently exists?"
Workflow
Step 1: Parse Intent
Identify: target service(s), scope (all / filtered / specific), detail level, and region.
Step 2: Confirm Account & Region
aws sts get-caller-identity --query '{Account:Account,UserId:UserId}'
aws configure get regionAppend `--region <region>` to all commands when the user specifies one.
Step 3: Execute & Format
Run the matched read-only command(s) below and format results as a readable table. For large result sets show a count first and offer to filter further.
---
Intent → Command Mapping
COMPUTE
#### EC2 Instances
# "list EC2 instances" / "show my VMs" / "what instances are running"
aws ec2 describe-instances \
--query 'Reservations[].Instances[].[InstanceId,InstanceType,State.Name,Tags[?Key==`Name`].Value|[0],PrivateIpAddress,PublicIpAddress]' \
--output table
# "running instances only"
aws ec2 describe-instances --filters Name=instance-state-name,Values=running \
--query 'Reservations[].Instances[].[InstanceId,InstanceType,Tags[?Key==`Name`].Value|[0],PrivateIpAddress]' \
--output table
# "stopped instances"
aws ec2 describe-instances --filters Name=instance-state-name,Values=stopped \
--query 'Reservations[].Instances[].[InstanceId,InstanceType,Tags[?Key==`Name`].Value|[0]]' \
--output table
# "instance types in use"
aws ec2 describe-instances --query 'Reservations[].Instances[].InstanceType' --output text | sort | uniq -c | sort -rn
# "auto scaling groups" / "ASGs"
aws autoscaling describe-auto-scaling-groups \
--query 'AutoScalingGroups[].[AutoScalingGroupName,MinSize,MaxSize,DesiredCapacity]' --output table
# "elastic IPs" / "EIPs"
aws ec2 describe-addresses \
--query 'Addresses[].[PublicIp,InstanceId,AllocationId,AssociationId]' --output table
# "key pairs"
aws ec2 describe-key-pairs \
--query 'KeyPairs[].[KeyName,CreateTime]' --output table
# "AMIs I own"
aws ec2 describe-images --owners self \
--query 'Images[].[ImageId,Name,CreationDate,State]' --output table
# "spot instances"
aws ec2 describe-spot-instance-requests \
--query 'SpotInstanceRequests[].[SpotInstanceRequestId,State,InstanceId,LaunchSpecification.InstanceType]' --output table#### Lambda Functions
# "list Lambda functions" / "show serverless functions"
aws lambda list-functions \
--query 'Functions[].[FunctionName,Runtime,MemorySize,Timeout,LastModified]' --output table
# "Lambda function details for <name>"
aws lambda get-function-configuration --function-name <name>
# "Lambda event source mappings" / "Lambda triggers"
aws lambda list-event-source-mappings \
--query 'EventSourceMappings[].[FunctionArn,EventSourceArn,State,BatchSize]' --output table
# "Lambda layers"
aws lambda list-layers \
--query 'Layers[].[LayerName,LatestMatchingVersion.LayerVersionArn]' --output table
# "Lambda concurrency for <name>"
aws lambda get-function-concurrency --function-name <name>#### ECS
# "ECS clusters"
aws ecs list-clusters --query 'clusterArns' --output table
🎯 Best For
- Claude users
- GitHub Copilot users
- Software engineers
- Development teams
- Tech leads
💡 Use Cases
- Code quality improvement
- Best practice enforcement
📖 How to Use This Skill
- 1
Install the Skill
Copy the install command from the Terminal tab and run it. The SKILL.md file downloads to your local skills directory.
- 2
Load into Your AI Assistant
Open Claude or GitHub Copilot and reference the skill. Paste the SKILL.md content or use the system prompt tab.
- 3
Apply Aws-Resource-Query to Your Work
Open your project in the AI assistant and ask it to apply the skill. Start with a small module to verify the output quality.
- 4
Review and Refine
Review AI suggestions before committing. Run tests, check for regressions, and iterate on the skill output.
❓ Frequently Asked Questions
Is Aws-Resource-Query compatible with Cursor and VS Code?
Yes — this skill works with any AI coding assistant including Cursor, VS Code with Copilot, and JetBrains IDEs.
Do I need specific dependencies for Aws-Resource-Query?
Check the install command and Works With section. Most code skills only require the AI assistant and your codebase.
How do I install Aws-Resource-Query?
Copy the install command from the Terminal tab and run it. The skill downloads to ./skills/aws-resource-query/SKILL.md, ready to use.
Can I customize this skill for my team?
Absolutely. Edit the SKILL.md file to add team-specific instructions, examples, or workflows.
⚠️ Common Mistakes to Avoid
Skipping validation
Always test AI-generated code changes, even for simple refactors.
Missing dependency updates
Check if the skill requires updated dependencies or new packages.