Comprehensive AI Architecture Review with HTML Reports

Comprehensive AI Architecture Review with HTML Reports

This AI agent skill facilitates a thorough review of an application's architecture by exploring its codebase structure and generating detailed, self-contained HTML reports. The reports include Mermaid diagrams and propose candidate improvements, ideal for use before significant refactoring, onboarding to new codebases, or undertaking major architectural changes.

What this skill does

• Phase 1: Explore
  • Reads a CONTEXT.md file if available, or indicates absence.
  • Utilises `CBM_PROJECT` for an architecture overview, identifying layers, boundaries, clusters, and hotspots, with options to call shared contract recipes for hubs, bridges, cross-boundary, and test-gaps.
  • Deploys the Serena structure for an additional symbols overview for deeper insights.
  • Analyses key "hub" nodes to comprehend structure, naming conventions, and patterns.
• Phase 2: Generate HTML Report
  • Produces an HTML report located at `docs/supergraph/architecture-review-.html` with TailwindCSS and Mermaid for styling and visuals.
  • Includes architecture `graph TD` and detailed cards for each proposal (Problem/Proposal/Before/After Mermaid/Impact/Trade-offs).
  • Summarises results in tables that highlight Test Gaps and Unexpected Coupling.
• Phase 3: Grilling Loop
  • Allows iterative review and refinement of the findings to converge on optimal architectural recommendations.

Who it is for

• Software developers and architects planning large codebase refactoring.
• Development teams onboarding onto unfamiliar codebases.
• Teams considering significant architectural shifts to improve codebase efficiency and maintainability.

Use cases

• Preparation for a substantial system refactoring to streamline the architecture.
• Comprehensive understanding of existing codebase structure during onboarding to shorten learning curves.
• Proactively identifying and addressing potential architectural weaknesses before implementing changes.

Technical details

• Compatible with AI coding agents like Claude Code, Cursor, and Codex.
• Involves the use of tools such as antigravity-plugin, aiapplication, and architecture for analysis and reporting.
• Generates visualizations using Mermaid diagrams included in the HTML reports.

Source & Licence

This package is built on open-source work published by datit309 (datit309/supergraph) and distributed under MIT. The original licence text and copyright notice are included in your download.

Personal and commercial use, modification and redistribution are permitted, provided the original copyright and licence notice are retained.

Your purchase covers curation, licence verification, packaging, documentation and instant delivery. It does not grant exclusive rights to the underlying open-source code, which remains available under its original licence.

Delivery & Support

• Delivery: instant — a secure download link is emailed to you as soon as payment is confirmed.
• Format: ZIP archive containing the skill files, documentation and the original licence.
• Support: support@mcpcart.com — we aim to reply within 2 business days.
• Updates: updates are included only where stated on this page.

Refunds

This is a digital product delivered immediately after purchase. By completing your order you request immediate delivery and acknowledge that, once the download has been accessed, the statutory right to cancel no longer applies to the extent permitted by law. Refund requests are handled in accordance with our published Refund Policy.

Claude, Codex, Gemini and Cursor are trademarks of their respective owners. MCP Cart is an independent marketplace and is not affiliated with, endorsed by, or sponsored by any of them. Compatibility references describe interoperability only.