Skip to content
OpenAgentSkill
Browsing is open · Catalog captured 2026-11-21 · Automatic updates and account services are paused.
Design & UI

ln-25-architecture-diagram-builder

Creates evidence-backed current or target architecture diagrams; not UI design.

levnikolaevich · Static checks on file

Installation

Read the source and dependencies before running a command. Copying does not install or execute anything.

npx skills add levnikolaevich/claude-code-skills --skill ln-25-architecture-diagram-builder

About this skill


name: ln-25-architecture-diagram-builder description: "Creates evidence-backed current or target architecture diagrams; not UI design."

Architecture Diagram Builder

Goal: Create the smallest set of understandable, evidence-backed diagrams needed to communicate current or proposed architecture. Change only approved architecture documentation; do not invent relationships, perform visual product design, replace prose evidence, audit fitness, or edit implementation.

Execution contract: The ordered checkboxes are the Definition of Done. Track every item internally as PENDING, PROVEN with concrete evidence, CLEARED with evidence that its condition is absent, or UNPROVEN with a gap; reading, delegation, or tool failure is not proof. Reconcile items after each section. Before returning, resolve all PENDING and count only PROVEN and CLEARED; apply the skill's verdict and approval rules to every gap. Preserve user intent, scope, and existing authorization. Continue authorized work; ask only for consequential unresolved choices or required external approval. Scale depth to material risk without silently skipping checks. Preserve dependency and safety ordering; otherwise choose the verification method appropriate to each obligation. Treat equivalent user or repository evidence as valid input; another skill, named artifact, or complete lifecycle is not a prerequisite. Preserve source requirement and decision identifiers when available. Bind reused evidence to the relevant source version, dirty changes, configuration, and environment; invalidate only affected claims after a change. On continuation, reconcile the task, existing authorization, current state, and unresolved evidence before resuming. For long work, return a compact continuation record or update an already authorized task artifact; read-only skills do not persist it. Distinguish artifact readiness, verified behavior, and authority to perform an external action. Prepare authorized work before any required approval. If an instruction prevents progress, identify its exact source and explain the unresolved boundary; do not invent an approval gate from general caution.

Tool Routing

NeedPreferred capabilityFallback
Architecture evidenceRepository files, runtime wiring, IaC, contracts, and approved artifactsUser-provided model with UNVERIFIED labels
Relationship tracingLanguage intelligence, dependency tools, and focused searchDirect inspection of producers, consumers, and registrations
Diagram formatExisting repository convention and rendererMermaid in Markdown, then plain ASCII
Syntax verificationRepository renderer, parser, or previewManual fence, identifier, and relationship inspection
Document mutationMinimal patch to approved diagram artifactsReturn BLOCKED if path or evidence boundary is unsafe

Diagrams communicate a model; executable behavior remains authoritative for current state. Keep current, target, and transition views visibly distinct.

Artifact Rules

  • Reuse an existing diagram convention or use docs/architecture/diagrams/<view>.md.
  • Prefer Markdown with Mermaid for text-reviewable source; use ASCII when Mermaid is unsupported.
  • For static structure, choose the context, container, or component level that answers the requested question; do not create prerequisite overview diagrams when existing context suffices.
  • Keep diagram source reviewable in version control.
  • Split views when one diagram needs multiple unrelated stories.
  • Never use color as the only carrier of meaning.
  • Use stable element identifiers and concise display labels so revisions produce reviewable diffs.
  • Keep detailed evidence beside the diagram rather than crowding nodes and relationships.
  • Preserve an understandable existing notation; introduce a new notation only when it answers the audience question better.

Checklist

1. Establish the Diagram Contract

  • Resolve audience, question, current or target state, scope, approved destination, and required notation.
  • Read repository instructions, relevant architecture artifacts, and existing diagram conventions.
  • Select the minimum useful view or views; reject diagrams that add no relationship clarity.
  • Define the evidence boundary and label user-supplied or proposed elements separately.
  • Keep the run read-only except for approved architecture diagram documentation.

2. Build the Architecture Model

  • Identify relevant people, systems, applications/data stores (C4 containers when using C4), components, queues, and external dependencies; distinguish logical containers from OS/container-runtime deployment units.
  • Record responsibility, type, technology when decision-relevant, owner when known, and current/target status for each element.
  • Resolve relationship direction, label, protocol or data, synchronicity, and trust or network boundary where relevant.
  • Trace runtime discovery and registration before including current-state routes, handlers, jobs, plugins, or consumers.
  • Mark uncertain elements or relationships UNKNOWN rather than completing the picture aesthetically.

3. Select and Draw Views

  • Create a system-context view when readers need system scope and external actors.
  • Create a container or deployment view for responsibilities, deployability, stores, or operational topology; include nodes, regions, networks, scaling, and failover when relevant to the audience question.
  • Create a component view only for a complex area whose internal boundaries change understanding.
  • Create sequence or dynamic views for critical success, failure, retry, timeout, recovery, or migration interactions.
  • Create data-flow or trust-boundary views when security, privacy, residency, or system-of-record questions require them.
  • Avoid mixing abstraction levels in one view unless the exception is explicit and necessary
Read the complete source ↗