AWS cloud operations for CloudWatch, S3, Lambda, EC2, and IAM
The English summary is being prepared. Showing the original description.
Review the instructions the agent will receive before you install.
The skill invokes the AWS CLI v2. Install and configure:
sudo ./aws/installcurl "https://awscli.amazonaws.com/AWSCLIV2.pkg" -o "AWSCLIV2.pkg" then run the installermsiexec; or install via package managersConfigure: aws configure (access key, secret, region). Verify: aws --version
Identity & config: aws sts get-caller-identity — who am I; aws configure list-profiles — list profiles.
S3: aws s3 ls; aws s3 cp <local> s3://bucket/; aws s3 sync ./dir s3://bucket/; aws s3 rm s3://bucket/key.
Lambda: aws lambda list-functions; aws lambda invoke --function-name X output.json; aws lambda get-function --function-name X.
CloudWatch: aws cloudwatch list-metrics; aws cloudwatch get-metric-statistics; aws cloudwatch describe-alarms; put-metric-alarm for alerts.
EC2: aws ec2 describe-instances; start-instances/stop-instances/terminate-instances with --instance-ids.
Best practices: Use IAM roles over long-lived keys; set AWS_REGION/AWS_PROFILE; use --output json and --query to limit response size; run destructive ops only after describe to confirm resources.
Free: AWS Skill Builder — exam prep, Cloud Quest, Cloud Essentials. Cloud Practitioner (CLF-C02): Cloud concepts, security/compliance, technology/services, billing (~6 months exposure). Solutions Architect Associate: Next step; prep on Skill Builder.
Skill data: Map to S3, Lambda, CloudWatch, EC2, IAM; security best practices; no hardcoded credentials.
Suggested hooks: Pre-deploy: validate credentials (aws sts get-caller-identity). Cost-tracking hook: optional CloudWatch/billing checks. No mandatory hook; use when devops is routed for AWS tasks.
Workflows: Use with devops (contextual: aws_project). Flow: detect AWS project → load aws-cloud-ops → run CLI via skill script. See operations/incident-response if debugging AWS resources.
Provides 90%+ context savings vs raw AWS MCP server. Multi-service support with progressive disclosure by service category.
| Tool | Description | Confirmation |
|---|---|---|
| logs-groups | List log groups | No |
| logs-tail | Tail log stream | No |
| logs-filter | Filter log events | No |
| metrics-list | List metrics | No |
| metrics-get | Get metric data | No |
| alarm-list | List alarms | No |
| alarm-create | Create alarm | Yes |
| Tool | Description | Confirmation |
|---|---|---|
| s3-ls | List buckets/objects | No |
| s3-cp | Copy objects | Yes |
| s3-sync | Sync directories | Yes |
| s3-rm | Delete objects | Yes |
| Tool | Description | Confirmation |
|---|---|---|
| lambda-list | List functions | No |
| lambda-get | Get function details | No |
| lambda-invoke | Invoke function | Yes |
| lambda-logs | Get function logs | No |
| Tool | Description | Confirmation |
|---|---|---|
| ec2-list | List instances | No |
| ec2-describe | Describe instance | No |
| ec2-start | Start instance | Yes |
| ec2-stop | Stop instance | Yes |
| sg-list | List security groups | No |
| Tool | Description | Confirmation |
|---|---|---|
| iam-users | List users | No |
| iam-roles | List roles | No |
| iam-policies | List policies | No |
# List EC2 instances
aws ec2 describe-instances --output table
# Tail CloudWatch logs
aws logs tail /aws/lambda/my-function --follow
# List S3 buckets
aws s3 ls
# Invoke Lambda
aws lambda invoke --function-name my-func output.json
⚠️ Never hardcode credentials ⚠️ Use IAM roles when possible ⚠️ IAM write operations are blocked
| Issue | Solution |
|---|---|
| Access denied | Check IAM permissions |
| Region error | Set AWS_REGION |
| Credentials | Run aws configure |
Before starting:
Read .claude/context/memory/learnings.md
After completing:
.claude/context/memory/learnings.md.claude/context/memory/issues.md.claude/context/memory/decisions.mdASSUME INTERRUPTION: If it's not in memory, it didn't happen.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Ensure accessibility in UI components including semantic HTML, ARIA attributes, keyboard navigation, and WCAG 2.2 AA compliance.
The English summary is being prepared. Showing the original description.
Use when you want to improve response quality through meta-cognitive reasoning. Applies 15+ reasoning methods to reconsider and refine initial outputs.
The English summary is being prepared. Showing the original description.
N-round opposing-stance debates for trade-off analysis. Assigns pro/con roles to agents, runs structured debate rounds with quality scoring, and produces a moderator synthesis with confidence-rated recommendation. Generalizable to architecture, technology, security, and design decisions.
The English summary is being prepared. Showing the original description.
Force adversarial code review stance that eliminates confirmation bias — reviewer must find issues or re-analyze
The English summary is being prepared. Showing the original description.
Creates specialized AI agents on-demand when no existing agent matches a request. Use when the Router cannot find a suitable agent for a task. Enables self-evolution by generating persistent agents.
The English summary is being prepared. Showing the original description.
LLM-as-judge evaluation framework with 5-dimension rubric (accuracy, groundedness, coherence, completeness, helpfulness) for scoring AI-generated content quality with weighted composite scores and evidence citations
The English summary is being prepared. Showing the original description.