Generate Excalidraw diagrams from natural language descriptions. Outputs .excalidraw JSON files openable in Excalidraw. Use when asked to "create a diagram", "make a flowchart", "visualize a process", "draw a system architecture", "create a mind map", "generate an Excalidraw file", "draw an ER diagram", "create a sequence diagram", or "make a class diagram". Supports flowcharts, relationship diagrams, mind maps, architecture, DFD, swimlane, class, sequence, and ER diagrams. Can use icon libraries (AWS, GCP, etc.) when set up. Do NOT use for code architecture analysis (use the architecture skills), Mermaid diagram rendering (use mermaid-studio), or non-visual documentation (use docs-writer).
94
92%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is an excellent skill description that hits all the marks. It provides specific capabilities, extensive natural trigger terms, clear 'what' and 'when' guidance, and explicit negative boundaries to prevent conflicts with related skills. The description is comprehensive yet well-organized, making it easy for Claude to select appropriately from a large skill set.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: generating Excalidraw JSON files, supporting flowcharts, relationship diagrams, mind maps, architecture diagrams, DFD, swimlane, class, sequence, and ER diagrams. Also mentions icon library support (AWS, GCP). | 3 / 3 |
Completeness | Clearly answers both 'what' (generates Excalidraw JSON diagrams from natural language, supports many diagram types) and 'when' (explicit 'Use when asked to...' clause with extensive trigger phrases). Also includes explicit 'Do NOT use' guidance for disambiguation, which goes above and beyond. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say: 'create a diagram', 'make a flowchart', 'visualize a process', 'draw a system architecture', 'create a mind map', 'generate an Excalidraw file', 'draw an ER diagram', 'create a sequence diagram', 'make a class diagram'. These are highly natural phrases. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with clear niche (Excalidraw-specific output format) and explicit negative boundaries distinguishing it from architecture analysis skills, Mermaid rendering (mermaid-studio), and non-visual documentation (docs-writer). Very unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a high-quality, comprehensive skill that provides actionable, executable guidance for generating Excalidraw diagrams. Its main strength is the concrete JSON examples and detailed validation checklist that prevent common errors. The primary weakness is some redundancy across sections (element ordering, spacing, and binding rules appear in multiple places), which could be consolidated to save tokens.
Suggestions
Consolidate repeated guidance (element ordering, spacing rules, binding patterns) that appears in Step 4, Best Practices, Common Mistakes, and Validation Checklist into fewer locations to reduce redundancy and save ~50 lines.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is quite long (~300 lines) with some redundancy — spacing guidelines, element ordering rules, and common mistakes are repeated across multiple sections (Step 4, Best Practices, Common Mistakes, Validation Checklist). However, most content is genuinely necessary given the complexity of the Excalidraw JSON format, which Claude wouldn't inherently know. | 2 / 3 |
Actionability | Provides fully executable JSON examples for text containers, arrow bindings, and arrow labels. Includes specific hex color codes, pixel spacing values, font family numbers, and concrete property names. The guidance is copy-paste ready and leaves no ambiguity about the exact JSON structure required. | 3 / 3 |
Workflow Clarity | The 5-step workflow (Understand → Choose Type → Extract → Generate → Save) is clearly sequenced with explicit validation via the comprehensive checklist before delivery. The checklist serves as a strong verification checkpoint, and the troubleshooting table provides error recovery guidance. The element count recommendations include a feedback loop suggesting diagram splitting. | 3 / 3 |
Progressive Disclosure | Appropriately references external files for detailed content: `references/excalidraw-schema.md` for the full schema, `references/element-types.md` for extraction guidelines, `references/icon-libraries.md` for icons, and `assets/` templates for each diagram type. All references are one level deep and clearly signaled with context about when to read them. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
906a57d
Table of Contents
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.