canvas-design

tessl i github:ComposioHQ/awesome-claude-skills --skill canvas-design

Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.

54%

Overall

Validation — 88%

Implementation — 27%

Activation — 67%

SKILL.md

Review

Evals

Validation

88%

Warnings & errors only

Criteria	Description	Result
description_voice	'description' should use third person voice; found second person: 'You should'	Warning
metadata_version	'metadata' field is not a dictionary	Warning

	Total	14 / 16 Passed

Implementation

27%

This skill is overly verbose and philosophical rather than actionable. It spends significant tokens on abstract design concepts and repeated emphasis on 'craftsmanship' and 'masterpiece quality' that don't provide concrete guidance. The core technical task—actually generating PDF/PNG files—lacks any executable code or specific tool usage instructions.

Suggestions

Add concrete code examples showing how to generate PDF/PNG files using specific libraries or tools available to Claude

Remove redundant philosophical language and repeated emphasis on 'craftsmanship'—state it once clearly instead of 5+ times

Split content into separate files: keep SKILL.md as a concise overview, move philosophy examples to EXAMPLES.md and detailed canvas instructions to CANVAS.md

Add specific validation steps with concrete criteria (e.g., 'verify all elements have minimum 20px margin from edges') rather than vague 'double-check' instructions

Dimension	Reasoning	Score
Conciseness	Extremely verbose with extensive repetition of concepts like 'craftsmanship' and 'masterpiece' throughout. Contains philosophical padding and redundant explanations that Claude doesn't need (e.g., explaining what a design philosophy is multiple times, repeating the same principles in different sections).	1 / 3
Actionability	Provides conceptual guidance and examples of design philosophies, but lacks concrete executable code or specific tool commands. References './canvas-fonts' directory but doesn't show how to use it. No actual code for PDF/PNG generation despite being the core output.	2 / 3
Workflow Clarity	Has a two-step structure (philosophy creation then canvas creation) but validation checkpoints are vague ('double-check that nothing overlaps'). The 'FINAL STEP' refinement pass is mentioned but lacks specific criteria for when work is complete. No error recovery guidance.	2 / 3
Progressive Disclosure	Monolithic wall of text with no references to external files for detailed guidance. All content is inline despite being lengthy. Could benefit from separating philosophy examples, canvas creation details, and multi-page instructions into separate referenced documents.	1 / 3
	Total	6 / 12 Passed

Activation

67%

The description adequately covers both what the skill does and when to use it, which is its main strength. However, it lacks specificity in concrete actions and could benefit from more comprehensive trigger terms. The use of second person ('You should use') violates the third-person voice guideline.

Suggestions

Add more specific concrete actions like 'generate layouts, compose typography, apply color schemes, create illustrations'

Expand trigger terms to include common variations: 'graphic', 'illustration', 'banner', 'flyer', 'infographic', 'artwork'

Rewrite to third person voice: 'Use this skill when...' instead of 'You should use this skill when...'

Dimension	Reasoning	Score
Specificity	Names the domain (visual art, .png/.pdf) and some actions (create poster, art, design), but lacks comprehensive specific actions like 'generate layouts', 'apply color palettes', or 'compose typography'.	2 / 3
Completeness	Clearly answers both what ('Create beautiful visual art in .png and .pdf documents') and when ('when the user asks to create a poster, piece of art, design, or other static piece') with explicit trigger guidance.	3 / 3
Trigger Term Quality	Includes some natural terms users would say ('poster', 'piece of art', 'design') but missing common variations like 'graphic', 'illustration', 'banner', 'flyer', 'infographic', or 'visual'.	2 / 3
Distinctiveness Conflict Risk	The focus on 'static piece' and visual art helps distinguish it, but 'design' is quite broad and could overlap with UI design, presentation design, or document formatting skills.	2 / 3
	Total	9 / 12 Passed

Reviewed

17 days ago

Table of Contents

Validation Implementation Activation

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.