excalidraw

Create Excalidraw diagrams programmatically. Use when the user wants architecture diagrams, system designs, flowcharts, or any visual diagram with a hand-drawn aesthetic. Outputs editable .excalidraw JSON files. Best for architecture overviews and presentations where the hand-drawn style and drag-and-drop editing add value over Mermaid's text-only approach.

Quality

88%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Securityby

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 key criteria. It provides specific capabilities, includes natural trigger terms users would actually say, explicitly states both what it does and when to use it, and clearly differentiates itself from similar tools like Mermaid. The description uses proper third-person voice throughout.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions: 'Create Excalidraw diagrams programmatically', 'Outputs editable .excalidraw JSON files', and specifies use cases like 'architecture diagrams, system designs, flowcharts'. Also differentiates from Mermaid's approach.	3 / 3
Completeness	Clearly answers both what ('Create Excalidraw diagrams programmatically', 'Outputs editable .excalidraw JSON files') and when ('Use when the user wants architecture diagrams, system designs, flowcharts, or any visual diagram with a hand-drawn aesthetic'). Explicit 'Use when...' clause present.	3 / 3
Trigger Term Quality	Includes natural keywords users would say: 'architecture diagrams', 'system designs', 'flowcharts', 'visual diagram', 'hand-drawn', 'presentations', '.excalidraw'. Good coverage of terms a user might naturally use when requesting this type of work.	3 / 3
Distinctiveness Conflict Risk	Clearly distinguishes itself from other diagramming tools by explicitly mentioning 'hand-drawn aesthetic', 'Excalidraw', '.excalidraw JSON files', and contrasting with 'Mermaid's text-only approach'. This creates a clear niche unlikely to conflict with other diagram skills.	3 / 3
	Total	12 / 12 Passed

Implementation

77%

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

This is a strong, highly actionable skill with excellent executable examples and clear workflows. The main weakness is verbosity - the comprehensive API reference and color tables inflate the token cost significantly when a leaner overview with links to detailed docs would serve better. The content successfully teaches Claude how to generate Excalidraw diagrams but could be more token-efficient.

Suggestions

Move the detailed API Reference section to a separate REFERENCE.md file, keeping only essential methods in the main skill

Remove the color hex table - Claude can reference colors by name without needing the hex values

Condense the Configuration & Styling section by removing explanatory text like 'Roughness levels:' descriptions that Claude can infer

Dimension	Reasoning	Score
Conciseness	The content is mostly efficient but includes some unnecessary verbosity. The API reference section is comprehensive but could be more condensed - Claude doesn't need explanations like 'The base class for all diagrams' or detailed color hex values in a table. The token cost note is valuable but the overall document is longer than necessary.	2 / 3
Actionability	Excellent actionability with fully executable, copy-paste ready code examples throughout. Every method is demonstrated with concrete Python code, complete with imports and the sys.path setup needed to run. The examples are complete and immediately usable.	3 / 3
Workflow Clarity	Clear workflows for diagram generation with explicit steps. The Quick Start provides two methods with exact commands. The export workflow includes setup steps and execution commands. For a diagram generation skill, the single-action workflows (write script → run → view output) are unambiguous.	3 / 3
Progressive Disclosure	The document is well-structured with clear sections (Quick Start, API Reference, Examples, Tips), but it's monolithic - the full API reference (150+ lines) could be in a separate REFERENCE.md file. The 'See Also' section shows good cross-referencing, but the main content could benefit from splitting detailed API docs from the overview.	2 / 3
	Total	10 / 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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: tslateman/duet
Commit: 96a72fa

Reviewed: about 8 hours 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.