Diagram Workflow Method
Paste the following prompt into your AI chat to install this skill:
Please install @efficient-technology/diagram-workflow-method following the guide at https://skillhub.cn/install/skillhub.md.
About this skill
Problem: diagrams are not just drawing
Architecture, flow, sequence, and state diagrams look like placing elements on a canvas, but the harder part is making the information structure explicit: which components are required entities, which calls, dependencies, and transitions are real relationships, and which groupings are just logical boundaries. Asking a model to draw a diagram directly can easily produce missing entities, semantically wrong connections, an incorrect diagram type, broken SVG arrow direction, or unrenderable Mermaid code.
Method: structure-driven SVG / Mermaid generation
The skill splits the workflow into three steps: analyze the information structure by identifying entities, relationships, and hierarchy, using the test of whether information is incomplete without an element; choose the diagram type and encoding scheme based on component hierarchy, process branches, message timing, or state transitions; and compute layout and render output as inline SVG or a Mermaid code block for documents.
It also enforces practical constraints: keep each diagram under 20 entities, split larger structures into overview and detail views, keep color, shape, and line-type encodings consistent, and validate SVG arrow markers so paths point in the +x direction and refX/refY stay aligned. Before delivery, the result is checked against completeness, type fit, hierarchy, relationship accuracy, readability, encoding consistency, and renderability.
Boundaries and caveats
This skill fits visualization tasks with explicit entities and relationships, such as system architecture, business processes, data models, network topology, and protocol interaction. It is not a visual design tool; clarity and correctness take priority over aesthetics. Sensitive information should be explicitly marked for masking, and the generated diagram should be treated as a starting point that users refine for context, layout, entity selection, and styling.
Use Cases
- Before a microservice architecture review, turn components, dependencies, message queues, and databases into a renderable SVG or Mermaid architecture diagram.
- When designing an order state machine, map states and transition events into a state diagram and check completeness with the validation checklist.
- When documenting an API call chain, generate a sequence diagram that labels service messages, return paths, sync/async calls, and alt blocks.
- When reviewing a data model, organize entities, primary keys, 1:N and M:N relationships into an ER diagram for design discussion.
Best For
- Architects preparing architecture reviews who need accurate SVG diagrams for gateways, services, queues, and databases.
- Product managers documenting approval flows who need swimlane and exception-path flowcharts as Mermaid blocks.
- Engineers writing API docs who need sequence diagrams for sync, async, and return-message call chains.
- Data engineers reviewing schema designs who need ER diagrams with primary keys and relationship cardinalities.
Related Skills
Excalidraw Wrap is an Excalidraw-focused wrapper, with tags for TypeScript, GitHub, and automation.
Calibrate vague brand inputs, expose contradictions, distill a brand core and positioning boundaries, then stress-test the result into an executable brand skeleton.
Generate localized Chinese brand names, naming directions, slogans, and risk checklists with reusable templates and trademark search reminders.
A beginner-friendly photo analysis tool that infers shooting parameters from visual features and suggests post-processing, optimization, and learning keywords.