Code UML Diagram Generation
Paste the following prompt into your AI chat to install this skill:
Please install @showapi/code-uml-text-analysis-showapi according to https://skillhub.cn/install/skillhub.md.
About this skill
Problem
During code review, onboarding, or documentation, reading line by line often hides module boundaries, call paths, and key logic. Text-only analysis can be precise but lacks a visual model for the architecture.
How It Works
The skill separates code analysis from UML generation. It first extracts language type, intent, and code segments, then creates a PlantUML prompt and diagram focus. It also produces core findings, an architecture summary, and a sectioned analysis report. Real calls are asynchronous: execute_task.py submits a task and returns a task_id, while query_task.py polls the result and syncs the key payload from each round to the user. The final output combines the UML image, consistency-check result, and structured text into an HTML preview.
Boundaries
code is required and should contain the full code text; synchronous mode is not supported. Without showapi_appkey, the system runs a mock call and the result is preview-only, not a real generated output. Use analysis_points to focus the report, such as permission checks or ignoring Getter/Setter methods.
Screenshots
Use Cases
- Take over an unfamiliar Java module and generate a class-structure UML diagram with key-logic notes.
- Before code review, convert core business code into a UML diagram and highlight permission checks.
- Draft architecture documentation using sectioned code analysis, consistency checks, and UML output.
- Preview code UML generation without an appKey, then decide whether to run a real call.
Best For
- Engineers taking over a legacy codebase and needing module structure diagrams
- Engineering leads preparing code review reports with UML architecture views
- Technical writers turning complex code structure into image-and-text sections
- Engineers previewing code UML output without an appKey before integrating real calls
Related Skills
Automatically indexes Gradle-cached AAR/JAR dependency classes and returns library coordinates, versions, and public APIs by fully qualified name, using only the Python standard library.
Codifies AMT and YourMT3 training conventions, script patterns, hyperparameters, precision, checkpoints, and NaN safeguards.
Retrieve relevant chunks from a customer-managed PKM dataset by dataset_id and return concise, source-annotated answers.
Convert PRDs, user stories, or functional specs into prioritized test-point checklists covering functional, business-rule, boundary, exception, and non-functional dimensions.