bedrock-migration-assessment
This aws-startup-advisor skill assesses how a codebase uses AI models before a move to Amazon Bedrock, whatever cloud it comes from.
What the skill teaches
This aws-startup-advisor skill assesses how a codebase uses AI models before a move to Amazon Bedrock, whatever cloud it comes from. It scans code for calls to OpenAI (direct or through Azure), Anthropic, Google Gemini and OpenRouter, or validates an existing ai-workload-profile.json, and, if the user agrees and supplies an admin key, it can measure usage from OpenAI, Anthropic and OpenRouter read-only. After a short preview it runs the clarify step. The current release stops there: it does not design, estimate costs, generate artifacts or rewrite code, which llm-to-bedrock and the infrastructure migration skills handle. It includes Python scripts.
Capabilities
- Find AI provider calls in a codebase
- Measure OpenAI, Anthropic and OpenRouter usage with consent
- Answer migration questions for a move to Bedrock
About
- Publisher
- Amazon Web Services
Install
What's inside
- references/contracts/ai-workload-profile.schema.json
- references/phases/clarify/clarify-ai-only.md
- references/phases/discover/discover-app-code.md
- references/phases/discover/discover-openai-api.md
- references/phases/discover/discover.md
- references/shared/schema-preferences.md
- references/vendored/README.md
- references/vendored/state/phase-status.schema.json
- scripts/migration-preview.py
- scripts/openai-usage.py
- scripts/validate-ai-profile.py
MCP servers and skills can run code on your computer and act on your data. Review the source before installing.
This skill includes scripts that your agent may run.
Details
| Fact | Value | Source |
|---|---|---|
| Type | Skill | |
| Tool | Amazon Web Services | |
| Publisher | Amazon Web Services | source |
| Official status | Officialpublished in AWS's own GitHub organisation (github.com/aws) as part of the Agent Toolkit for AWS | source |
| Needs an API key or sign-in | Not stated in its documentation | |
| Includes scripts | Yes | source |
| Platforms | Not stated in its documentation | |
| AI clients | Not stated in its documentation | |
| Licence | Apache-2.0 | source |
| Pricing | Not stated in its documentation | |
| Activity | Last commit Nov 11, 20263,464 GitHub starsDownload data not available (not on npm or PyPI) | source |
| Links | Repository |
More from Amazon Web Services
4 servers · 169 skills
- analyzing-release-readiness (Skill)
- Amazon ECS MCP Server (MCP server)
- Agent Toolkit for AWS (MCP server)
- chatting-with-aws-devops-agent (Skill)
- coordinating-multi-space-devops-agent (Skill)
- diff-scanning-with-aws-security-agent (Skill)
Sources
- Skill file (SKILL.md)github.com/aws/agent-toolkit-for-awsNov 10, 2026
- README (README.md)github.com/aws/agent-toolkit-for-aws · Backs: Official status, PublisherNov 13, 2026
- Licence file (LICENSE)github.com/aws/agent-toolkit-for-aws · Backs: LicenceNov 13, 2026
- Folder in the repository (bedrock-migration-assessment)github.com/aws/agent-toolkit-for-aws · Backs: Includes scriptsNov 10, 2026
- GitHub repositorygithub.com/aws/agent-toolkit-for-aws · Backs: Activity, LicenceNov 11, 2026
Other MCP servers and skills for Amazon Web Services
- AWS Documentation MCP Server(MCP server)
- awslabs.amazon-mq-mcp-server(MCP server)
- awslabs.amazon-sns-sqs-mcp-server(MCP server)
- awslabs.amazon-translate-mcp-server(MCP server)
- awslabs.aws-iac-mcp-server(MCP server)
- awslabs.aws-location-mcp-server(MCP server)
- awslabs.aws-pricing-mcp-server(MCP server)
- analyzing-release-readiness(Skill)
- View all →