excalidraw-studio

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).

Quality

93%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

86%Weight 40%Scale 1-5

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

A strong, highly actionable skill body with executable JSON examples, clean progressive disclosure, and a clear workflow. The main drag is length: the Common Mistakes and Validation Checklist sections overlap and could be consolidated to improve token efficiency.

Suggestions

Merge the 'Common Mistakes to Avoid' list and the 'Validation Checklist' into a single section — they cover the same properties (boundElements/containerId, startBinding/endBinding, required base props, element order) and the duplication inflates token cost.

Add an explicit validate→fix→retry feedback loop (e.g., 'If a shape's text is missing, fix containerId/originalText and regenerate') to lift workflow clarity to the score-5 anchor, since the current checklist is one-shot rather than iterative.

Consider moving one of the two full inline JSON code blocks (arrow-label or binding example) into references/excalidraw-schema.md, keeping only the canonical text-in-shape example inline.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and assumes Claude's competence, but the body is long — two full JSON code blocks plus a ~15-item 'Common Mistakes' list that substantially overlaps the 'Validation Checklist', which could be tightened.	4 / 5
Actionability	Fully executable, copy-paste-ready JSON examples cover the common cases (text-in-shape, arrow labels, bindings) alongside concrete palette, spacing, and font-size tables.	5 / 5
Workflow Clarity	Clear 5-step sequence (UNDERSTAND→CHOOSE→EXTRACT→GENERATE→SAVE) with a pre-delivery validation checklist, but the validation is a checklist rather than an explicit validate→fix→retry feedback loop, leaving minor checkpoint gaps versus the score-5 anchor.	4 / 5
Progressive Disclosure	SKILL.md is a clear overview with well-signaled one-level-deep references (references/element-types.md, references/excalidraw-schema.md, references/icon-libraries.md, assets/*-template.json), all of which are real files, with content appropriately split out.	5 / 5
	Total	18 / 20 Passed

Description

100%Weight 40%Scale 1-5

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

An exemplary description: specific actions, comprehensive natural trigger phrases, explicit what-and-when completeness, and strong boundary guidance that prevents mis-routing to neighboring skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Generate Excalidraw diagrams from natural language descriptions', 'Outputs .excalidraw JSON files', supports 9 named diagram types and icon libraries — with comprehensive coverage.	5 / 5
Completeness	Explicitly answers both 'what' (generate Excalidraw-format diagrams, output JSON files) and 'when' (concrete 'Use when asked to...' trigger phrases), matching the score-5 anchor.	5 / 5
Trigger Term Quality	Comprehensive natural trigger phrases ('create a diagram', 'make a flowchart', 'visualize a process', 'draw an ER diagram', etc.) plus the .excalidraw file extension, covering synonyms and variations users would actually say.	5 / 5
Distinctiveness Conflict Risk	Clear Excalidraw-specific niche with explicit 'Do NOT use for...' boundary guidance (architecture skills, mermaid-studio, docs-writer), giving minimal conflict risk.	5 / 5
	Total	20 / 20 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: tech-leads-club/agent-skills
Path: packages/skills-catalog/skills/(tooling)/excalidraw-studio/SKILL.md
Commit: fc886b7

Reviewed: 5 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.