From aws-dev-toolkit
Guided migration assessment and planning — discover source environment, map services, estimate effort, and plan migration waves. Orchestrates gcp-to-aws, azure-to-aws, and the migration-advisor agent.
npx claudepluginhub aws-samples/sample-claude-code-plugins-for-startups --plugin aws-dev-toolkitThis skill uses the workspace's default tool permissions.
You are running a guided cloud migration workflow. This orchestrates discovery, mapping, and planning into one cohesive flow.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Checks Next.js compilation errors using a running Turbopack dev server after code edits. Fixes actionable issues before reporting complete. Replaces `next build`.
Guides code writing, review, and refactoring with Karpathy-inspired rules to avoid overcomplication, ensure simplicity, surgical changes, and verifiable success criteria.
Share bugs, ideas, or general feedback.
You are running a guided cloud migration workflow. This orchestrates discovery, mapping, and planning into one cohesive flow.
DISCOVER SOURCE → MAP SERVICES → ASSESS COMPLEXITY → PLAN WAVES → ESTIMATE COST
Determine the source cloud from $ARGUMENTS or by detecting installed CLIs:
# Auto-detect source cloud
which gcloud >/dev/null 2>&1 && echo "GCP detected"
which az >/dev/null 2>&1 && echo "Azure detected"
which oci >/dev/null 2>&1 && echo "OCI detected"
which doctl >/dev/null 2>&1 && echo "DigitalOcean detected"
Then delegate to the appropriate skill:
gcp-to-aws skill for service mappingazure-to-aws skill for service mappingmigration-advisor agent directlyAlso spawn the migration-advisor agent (subagent_type: "aws-dev-toolkit:migration-advisor") for the detailed discovery commands.
Ask progressively (2-3 at a time):
First round:
Based on answers, follow up with:
Use the source-specific skill (gcp-to-aws or azure-to-aws) to produce a mapping table. For each service:
| Source Service | AWS Equivalent | Migration Strategy | Complexity | Notes |
|---|---|---|---|---|
| ... | ... | Rehost/Replatform/Refactor | Low/Med/High | Gotchas |
Group workloads into migration waves:
## Wave 0: Foundation (Week 1-2)
- Landing zone setup (Control Tower or manual)
- Networking (VPC, Transit Gateway, VPN/Direct Connect)
- Identity (IAM Identity Center, federation)
- Logging/monitoring baseline
## Wave 1: Quick Wins (Week 3-4)
- Stateless services, low-risk
- Proves the migration pipeline works
- Builds team confidence
## Wave 2: Core Services (Week 5-8)
- Databases, stateful workloads
- Requires cutover planning and rollback
## Wave 3: Complex/Critical (Week 9-12+)
- High-risk or high-complexity workloads
- May need refactoring
- Extended parallel-run period
Mandatory — spawn the iac-reviewer agent or invoke security-review to validate the proposed AWS landing zone against:
Use the cost-check skill or aws-pricing MCP tools to estimate:
# Migration Plan: [Source] → AWS
## Executive Summary
[2-3 sentences: what, why, when, how much]
## Source Environment
[Inventory summary from discovery]
## Service Mapping
[Table from Phase 3]
## Migration Strategy
| Strategy | Count | Examples |
|----------|-------|---------|
| Rehost (lift & shift) | X | ... |
| Replatform | X | ... |
| Refactor | X | ... |
| Retire | X | ... |
## Wave Plan
[From Phase 4]
## Security & Compliance
[Findings from Phase 5]
## Cost Projection
| Period | Source Cloud | AWS Projected | Delta |
|--------|------------|---------------|-------|
| Current monthly | $X | — | — |
| Post-migration monthly | — | $X | +/-$X |
| 12-month total (incl. migration costs) | $X | $X | +/-$X |
## Risks
[Top 5 risks with mitigation plans]
## Next Steps
1. [Immediate action]
2. [...]
gcp-to-aws — GCP-to-AWS service mapping and migration patternsazure-to-aws — Azure-to-AWS service mapping and migration patternsnetworking — VPC design, Transit Gateway, VPN, and Direct Connect for landing zonessecurity-review — Security validation for the target AWS environmentcost-check — Cost comparison between source cloud and projected AWS spend