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

82%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

64%

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

This is a highly actionable skill with excellent executable examples and comprehensive API documentation. Its main weaknesses are that it's too long for a SKILL.md file - the detailed API reference, styling configuration, and color tables should be in separate reference files. The workflow could benefit from basic validation steps (e.g., confirming file was created, checking file size).

Suggestions

Move the detailed API reference (Diagram, Flowchart, AutoLayoutFlowchart, ArchitectureDiagram classes), color tables, and configuration/styling sections into separate reference files (e.g., API_REFERENCE.md, STYLING.md) and link to them from the main skill

Add a brief validation step after diagram generation, e.g., checking the file exists and has reasonable size, or opening it to verify JSON validity

Trim the Quick Start to just one method (Method 1) and move Method 2 to a tips or alternatives section to reduce initial cognitive load

Dimension	Reasoning	Score
Conciseness	The skill is fairly comprehensive but includes some unnecessary verbosity - the color reference tables, roughness level descriptions ('Architect', 'Artist', 'Cartoonist'), and viewing instructions are somewhat padded. The token cost note is useful but the overall document is quite long (~400 lines) with content that could be split into reference files.	2 / 3
Actionability	Excellent actionability with fully executable Python code examples throughout, specific import paths, concrete method signatures with parameter details, and complete end-to-end examples for multiple diagram types. All code is copy-paste ready with proper sys.path setup.	3 / 3
Workflow Clarity	The quick start methods are clear, and the export workflow has sequential steps. However, there are no validation checkpoints - no guidance on what to do if the generated file is malformed, if the import path is wrong, or if the save fails. For a file-generation skill this is acceptable but not ideal.	2 / 3
Progressive Disclosure	The document is a monolithic wall of content (~400 lines) with the full API reference, all configuration options, color tables, and three complete examples inline. The API reference, color schemes, and complete examples should be split into separate reference files with clear links from the main skill. The 'See Also' section at the end is good but insufficient to offset the inline bloat.	2 / 3
	Total	9 / 12 Passed

Description

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 clearly communicates what the skill does, when to use it, and how it differs from alternatives. It uses concrete trigger terms users would naturally say, specifies the output format, and explicitly distinguishes itself from Mermaid-based diagramming. The description is concise yet comprehensive.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions and outputs: 'Create Excalidraw diagrams programmatically', 'Outputs editable .excalidraw JSON files', and specifies diagram types like architecture diagrams, system designs, flowcharts. Also differentiates from Mermaid's text-only approach.	3 / 3
Completeness	Clearly answers both 'what' (create Excalidraw diagrams programmatically, output .excalidraw JSON files) and 'when' (explicit 'Use when the user wants architecture diagrams, system designs, flowcharts, or any visual diagram with a hand-drawn aesthetic'). Also includes a 'Best for' clause adding further trigger guidance.	3 / 3
Trigger Term Quality	Includes strong natural trigger terms users would say: 'architecture diagrams', 'system designs', 'flowcharts', 'visual diagram', 'hand-drawn', 'Excalidraw', '.excalidraw', 'presentations'. Also mentions Mermaid as a contrast, which helps with disambiguation.	3 / 3
Distinctiveness Conflict Risk	Highly distinctive by specifying Excalidraw as the tool, .excalidraw JSON as the output format, and explicitly differentiating from Mermaid. This creates a clear niche that is unlikely to conflict with other diagramming skills.	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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: tslateman/duet
Commit: c3b1fc2

Reviewed: 3 months 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.