excalidraw-diagram

Create Excalidraw diagram JSON files that make visual arguments. Use when the user wants to visualize workflows, architectures, or concepts.

Quality

68%

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

Fix and improve this skill with Tessl

tessl review fix ./SKILL.md

Quality

Content

62%Scale 1-3

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 and well-structured skill with excellent workflow clarity, including a mandatory render-validate-fix loop with explicit checkpoints and stopping conditions. However, it suffers significantly from verbosity — the file is far too long, with extensive philosophical explanations, redundant comparison tables, and design principles that Claude already understands. The content would benefit greatly from aggressive condensation and splitting detailed reference material (pattern library, shape meaning tables, comparison tables) into separate reference files.

Suggestions

Move the Visual Pattern Library, Shape Meaning table, and Bad vs Good comparison tables into separate reference files (e.g., references/patterns.md, references/shape-guide.md) and link to them from SKILL.md — this alone would cut the file roughly in half.

Remove philosophical explanations Claude already knows (e.g., 'A diagram isn't formatted text. It's a visual argument...') and replace with terse rules like 'Structure must communicate meaning without text labels (isomorphism test).'

Consolidate the multiple overlapping sections about containers vs free-floating text, typography hierarchy, and shape meaning into a single concise decision table.

Dimension	Reasoning	Score
Conciseness	The skill is extremely verbose at ~400+ lines. It extensively explains design philosophy, visual argumentation concepts, and pattern libraries that Claude already understands. Sections like 'Core Philosophy', 'Bad vs Good' comparison tables, and lengthy explanations of when to use containers vs free-floating text are padded with unnecessary conceptual teaching. Much of this could be condensed to terse rules and examples.	1 / 3
Actionability	The skill provides highly concrete, executable guidance: specific bash commands for rendering, exact JSON structure templates, precise CSS-like property values (roughness: 0, fontFamily: 3, opacity: 100), specific pixel dimensions for hierarchy (300×150 hero, 180×90 primary), and a clear section-by-section build workflow with namespace conventions for IDs and seeds.	3 / 3
Workflow Clarity	The multi-step workflow is exceptionally well-sequenced: Step 0 (assess depth) → Step 1-4 (design) → Step 5 (generate JSON section-by-section) → Step 6 (mandatory render-view-fix loop). The render & validate section includes explicit validation checkpoints, a feedback loop with specific audit criteria, clear stopping conditions, and error recovery guidance. Destructive operations are properly gated.	3 / 3
Progressive Disclosure	The skill references external files well (references/color-palette.md, references/element-templates.md, README.md, render_excalidraw.py), but the SKILL.md itself is monolithic — it inlines extensive content about visual patterns, design philosophy, container discipline, and comparison tables that could be split into reference files. The main file tries to be both overview and comprehensive reference simultaneously.	2 / 3
	Total	9 / 12 Passed

Description

75%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.

The description is well-structured with a clear 'Use when' clause and a distinctive niche around Excalidraw JSON files. However, it could benefit from listing more specific actions beyond 'create' and including additional trigger terms that users might naturally use when requesting diagrams or visual content.

Suggestions

Add more specific concrete actions such as 'create, edit, and update Excalidraw diagram JSON files with shapes, arrows, and text elements'.

Expand trigger terms to include common variations like 'diagram', 'flowchart', 'whiteboard', 'sketch', '.excalidraw', or 'draw'.

Dimension	Reasoning	Score
Specificity	It names the domain (Excalidraw diagram JSON files) and one action (create), but doesn't list multiple specific concrete actions like editing, exporting, or adding specific elements. 'Make visual arguments' is somewhat vague.	2 / 3
Completeness	Clearly answers both 'what' (create Excalidraw diagram JSON files that make visual arguments) and 'when' (use when the user wants to visualize workflows, architectures, or concepts) with an explicit 'Use when' clause.	3 / 3
Trigger Term Quality	Includes some relevant terms like 'Excalidraw', 'workflows', 'architectures', 'concepts', and 'visualize', but misses common variations users might say such as 'diagram', 'flowchart', 'whiteboard', 'sketch', or '.excalidraw'.	2 / 3
Distinctiveness Conflict Risk	The mention of 'Excalidraw diagram JSON files' is highly specific and creates a clear niche that is unlikely to conflict with other diagramming or visualization skills. The format specificity (JSON files for Excalidraw) makes it very distinct.	3 / 3
	Total	10 / 12 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (553 lines); consider splitting into references/ and linking	Warning

	Total	10 / 11 Passed

Repository: coleam00/excalidraw-diagram-skill
Path: SKILL.md
Commit: 8646fcc

Reviewed: 4 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.