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.

1.76x

Quality

51%

Does it follow best practices?

Impact

99%

1.76x

Average score across 10 eval scenarios

Securityby

Failed to scan

The risk profile of this skill

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/anthropic-canvas-design/SKILL.md

Quality

Discovery

67%

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 adequately communicates the skill's purpose and includes an explicit 'Use when' clause with some trigger terms. However, it suffers from vague language ('design philosophy', 'beautiful visual art') and could benefit from more specific capability listing and broader trigger term coverage. The copyright disclaimer, while responsible, doesn't aid in skill selection.

Suggestions

Expand trigger terms to include common variations like 'illustration', 'graphic', 'flyer', 'banner', 'infographic', 'image creation' to improve matching.

Replace vague phrases like 'using design philosophy' with specific capabilities such as 'applying color theory, typography, layout composition, and visual hierarchy'.

Use third-person voice consistently ('Creates original visual designs') instead of second person ('You should use this skill') to align with style guidelines.

Dimension	Reasoning	Score
Specificity	Names the domain (visual art/design) and some actions (create posters, art, designs), but 'using design philosophy' is vague and the specific capabilities like file format handling aren't well elaborated beyond mentioning .png and .pdf.	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 like 'poster', 'piece of art', 'design', and file formats '.png' and '.pdf', but misses common variations like 'illustration', 'graphic', 'flyer', 'banner', 'infographic', 'visual', or 'image creation'.	2 / 3
Distinctiveness Conflict Risk	The focus on static visual art/posters provides some distinctiveness, but 'design' is broad and could overlap with UI design, web design, or presentation skills. The 'static piece' qualifier helps but isn't strongly differentiating.	2 / 3
	Total	9 / 12 Passed

Implementation

35%

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

This skill is highly verbose and repetitive, spending excessive tokens on motivational/aspirational language ('masterpiece,' 'museum quality,' 'expert craftsmanship') that Claude doesn't need repeated dozens of times. While the two-step workflow (philosophy creation → visual expression) is a reasonable structure, the skill lacks concrete technical guidance on how to actually generate PDF/PNG files programmatically, and has no validation steps for the output. The philosophy examples are a strength but could be externalized for better progressive disclosure.

Suggestions

Cut repetitive exhortations about craftsmanship and museum quality to a single, concise statement—repeating 'meticulously crafted' 6+ times wastes tokens without adding information.

Add concrete, executable code examples showing how to generate PDF/PNG output (e.g., specific Python libraries like reportlab, PIL/Pillow, or cairo with actual code snippets).

Add a validation checkpoint after canvas creation—e.g., verify the output file opens correctly, check dimensions, confirm text doesn't overlap by reviewing coordinates programmatically.

Move the philosophy examples into a separate EXAMPLES.md file and reference it from the main skill to improve progressive disclosure and reduce the monolithic feel.

Dimension	Reasoning	Score
Conciseness	Extremely verbose and repetitive. The instruction to emphasize 'expert craftsmanship' is itself repeated at least 5-6 times across different sections. Concepts like 'minimal text,' 'visual expression,' and 'museum quality' are restated redundantly throughout. The skill could be cut by 60%+ without losing actionable content.	1 / 3
Actionability	Provides some concrete guidance (philosophy examples, output format expectations, font directory reference), but lacks executable code or specific tool commands for generating PDFs/PNGs. The instructions are heavily philosophical/aspirational rather than technically precise—Claude is told to 'create a masterpiece' but not given specific libraries, code patterns, or rendering approaches.	2 / 3
Workflow Clarity	There is a discernible multi-step sequence (create philosophy → deduce reference → create canvas → refine), but validation checkpoints are absent. The 'final step' refinement pass is mentioned but has no concrete criteria for what 'pristine' means or how to verify quality. No feedback loops for error recovery in the PDF/PNG generation process.	2 / 3
Progressive Disclosure	Content is structured with headers and sections, but it's a monolithic wall of text that could benefit from splitting detailed philosophy examples and canvas creation guidelines into separate reference files. The font directory is referenced but no other external resources are linked. The inline philosophy examples are lengthy and could be in a separate EXAMPLES.md.	2 / 3
	Total	7 / 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: boisenoise/skills-collections
Commit: 636b862

Reviewed: 3 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.