ln-75-architecture-diagram-builder

Creates evidence-backed current or target architecture diagrams from repository evidence.

556|83|Updated Oct 24, 2025
One-click install
npx skills add https://github.com/levnikolaevich/claude-code-skills --skill ln-75-architecture-diagram-builder
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ln-75-architecture-diagram-builder
Source: https://github.com/levnikolaevich/claude-code-skills/tree/main/plugins/architecture-suite/skills/ln-75-architecture-diagram-builder
Command: npx skills add https://github.com/levnikolaevich/claude-code-skills --skill ln-75-architecture-diagram-builder

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Architecture diagrams are often drawn from memory or assumptions, producing visuals that misrepresent the real system. This Skill builds diagrams strictly from repository evidence—code, runtime wiring, IaC, and contracts—so every element and relationship is traceable and trustworthy.

Core Features & Use Cases

  • Evidence-Backed Modeling: Traces components, containers, stores, queues, and dependencies from actual repository artifacts, marking uncertain relationships as UNKNOWN instead of guessing.
  • Multiple View Types: Produces system-context, container, component, sequence, data-flow, and deployment views, selecting only the minimum views that answer a named audience question.
  • Verifiable Output: Validates Mermaid or ASCII syntax, keeps diagram source reviewable in version control, and reports a READY, INCONCLUSIVE, or BLOCKED verdict with a completion checklist.
  • Use Case: When onboarding engineers to a microservices system, generate a current-state container diagram with labeled relationships and evidence notes so the team can verify each claim against the codebase.

Quick Start

Ask the agent to create an evidence-backed architecture diagram of the current system for a specific audience and question, saving it under docs/architecture/diagrams.

Frequently Asked Questions about ln-75-architecture-diagram-builder

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I create an architecture diagram from an existing codebase?

Define the audience, question, and current or target state first, then trace elements and relationships from repository files, runtime wiring, and contracts. The Skill builds the model from evidence and renders it as Mermaid in Markdown or ASCII, validating syntax before reporting.

What diagram types should I use for software architecture documentation?

Use system-context views for scope and external actors, container or deployment views for responsibilities and topology, component views only for complex areas, sequence views for critical runtime interactions, and data-flow views for stores and trust boundaries.

Does it support Mermaid diagrams in Markdown?

Yes, Mermaid in Markdown is the preferred format because it stays reviewable in version control. ASCII is the fallback when Mermaid is unsupported, and existing repository diagram conventions take priority over both.

Can it generate diagrams for a proposed target architecture?

Yes, it handles both current and target states, keeping them visibly distinct. Proposed or user-supplied elements are labeled separately from evidence-backed current-state elements so reviewers can tell observation from proposal.

What are the limitations of evidence-based architecture diagramming?

It does not perform UI design, architecture audits, or code changes, and it will not invent relationships to complete a picture. When material relationships cannot be verified, it marks them UNKNOWN and returns an INCONCLUSIVE or BLOCKED verdict.