From mighty-powers
Living Architecture Map — auto-generate Mermaid diagrams of your codebase. Use when user wants to visualize architecture, understand code structure, generate diagrams, or document system design.
How this skill is triggered — by the user, by Claude, or both
Slash command
/mighty-powers:architecture-mapThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Auto-generates and maintains architecture diagrams from your actual code. Always up-to-date.
Auto-generates and maintains architecture diagrams from your actual code. Always up-to-date.
node ${CLAUDE_PLUGIN_ROOT}/tools/architecture-mapper.mjs <project-directory>
Parse the JSON output for architecture data and diagrams.
Display each Mermaid diagram with context:
System Architecture: High-level view of all components and how they connect.
[system diagram from tool output]
API Route Map: All endpoints organized by resource.
[routes diagram from tool output]
Database Schema: Entity-relationship diagram of all tables and relations.
[database ER diagram from tool output]
Data Flow: Sequence diagram showing how a typical request flows through the system.
[data flow diagram from tool output]
Based on the scanned data, provide analysis:
Strengths:
Concerns:
Service Dependencies: List all external services and how they're used. Flag any that are single points of failure.
Save architecture documentation:
docs/architecture/ directorydocs/architecture/ARCHITECTURE.md with all diagramsThe document should be self-contained and renderable in GitHub (GitHub supports Mermaid in markdown).
Based on architecture analysis:
Recommend running /architecture-map after any significant structural change:
The diagrams are generated from code, so they're always accurate when re-run.
The map IS the territory. Architecture diagrams that drift from reality are worse than no diagrams. Because these are auto-generated from code, they're always truthful.
npx claudepluginhub anderson-0/mighty-powers --plugin mighty-powersGuides creation, editing, and verification of skills for AI coding agents using test-driven development with subagent scenarios. Use when authoring or debugging skills.