This repository provides a comprehensive set of Markdown-based document templates designed to aid in the architectural design and construction of systems on AWS. Targeting cloud engineers and architects, it streamlines the creation of essential documentation, including infrastructure design, non-functional requirements gathering, and best practice workshops, by leveraging established frameworks and AI assistance.

How It Works

The project organizes templates into distinct categories: cloud design sheets, non-functional requirements checklists, and AWS best practice workshop materials. Documents are authored in Markdown within doc_source/ directories and can be converted to MS Word using pandoc. A key differentiator is the integration with Claude Code, an AI assistant, which is configured via CLAUDE.md and .mcp.json to help manage, review, and update documentation, including specialized skills for AWS Well-Architected Framework reviews and checking for outdated non-functional requirements against current AWS specifications.

Quick Start & Requirements

• Prerequisites: Claude Code CLI, Python package manager uvx.
• Setup: Requires configuration of Claude Code and MCP servers as detailed in .claude/, CLAUDE.md, and .mcp.json. Specific setup time and resource footprint are not detailed.

Highlighted Details

• Comprehensive infrastructure design templates aligned with the AWS Well-Architected Framework.
• Non-functional requirements checklist integrating IPA Non-Functional Requirements Grade and AWS Well-Architected Framework, covering categories like reliability, security, cost optimization, and generative AI.
• AI-assisted document management using Claude Code with custom skills for automated reviews and updates.
• Markdown source files convertible to MS Word via pandoc.

Maintenance & Community

The steering/ directory contains update plans and outdated check results, indicating active maintenance. No community links (e.g., Discord, Slack) are provided.

Licensing & Compatibility

Licensing information is not specified in the provided README.

Limitations & Caveats

The README does not explicitly state limitations, alpha status, or known bugs. The reliance on Claude Code implies a dependency on Anthropic's AI services and associated costs or access requirements. Conversion to MS Word via pandoc requires its installation and correct configuration.