uml-and-software-architecture-visualization

Design, critique, read, write, render, and implement UML and UML-like software diagrams. Use when the user mentions UML, sequence diagrams, class diagrams, activity diagrams, state machines, use case diagrams, component diagrams, deployment diagrams, object diagrams, package diagrams, profile diagrams, timing diagrams, communication diagrams, interaction overview diagrams, composite structure diagrams, ERDs, database schema diagrams, C4, BPMN, swimlanes, flowcharts, network diagrams, application architecture diagrams, software architecture diagrams, diagram-as-code, model-as-code, XMI, UMLDI, PlantUML, Mermaid, Graphviz DOT, D2, Structurizr, DBML, diagrams.net/draw.io, Kroki, or interactive diagram editors and explorers.

Quality

100%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

100%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A high-signal routing/selection skill: lean for its broad scope, concrete and actionable, with a clear sequenced workflow and exemplary one-level-deep reference structure. Minor redundancy between 'Representative Prompts' and the description does not rise to a conciseness penalty.

Dimension	Reasoning	Score
Conciseness	The body is dense actionable defaults and routing tables with no explanation of concepts Claude already knows; its length is proportional to an unusually broad scope rather than padding. It is not a level-2 because there is no unnecessary conceptual explanation to tighten.	3 / 3
Actionability	Gives concrete, specific, copy-ready recommendations throughout, e.g. 'prefer DBML, SQL-derived ERD tooling, Mermaid ER, or PlantUML IE/ER' and 'use React Flow for editable node-edge UIs, Cytoscape.js for graph analysis', fully actionable for a selection skill.	3 / 3
Workflow Clarity	The Core Workflow is a clearly sequenced 10-step decision process (job → audience → notation → format → layout → renderer → model contract → export/tests → default state) with sub-options at each step; no validation loop is required because this is design selection, not a destructive or batch operation.	3 / 3
Progressive Disclosure	A well-signaled 'Reference Guide' points one level deep to five real files (uml-diagram-types-and-selection, formats-and-interchange, typescript-web-rendering, interactive-diagram-patterns, quality-accessibility-export-testing), all verified present, with the SKILL.md serving as a concise overview — content is appropriately split for easy navigation.	3 / 3
	Total	12 / 12 Passed

Description

100%Weight 40%Scale 1-3

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, specific description that clearly states capabilities and trigger conditions with broad, natural keyword coverage. It is on the long side but every term is a legitimate trigger rather than padding.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Design, critique, read, write, render, and implement UML and UML-like software diagrams' — rather than vague language, matching the level-3 anchor.	3 / 3
Completeness	Explicitly answers both 'what' (the verb list) and 'when' via the 'Use when the user mentions…' clause, satisfying the level-3 anchor for explicit triggers.	3 / 3
Trigger Term Quality	Exhaustive coverage of natural terms users would say, from UML and every diagram type (sequence, class, activity, state machine…) to ERDs, BPMN, C4, PlantUML, Mermaid, D2, DBML, and Kroki.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (UML / software-architecture visualization) with highly specific, distinctive triggers and third-person voice, making conflict with other skills unlikely.	3 / 3
	Total	12 / 12 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: openai/plugins
Path: plugins/build-web-data-visualization/skills/uml-and-software-architecture-visualization/SKILL.md
Commit: 11c74d6

Reviewed: 17 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.