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.

1.48x

Quality

63%

Does it follow best practices?

Impact

89%

1.48x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/all-skills/skills/canvas-design/SKILL.md

The canonical home for this skill is canvas-design in anthropics/skills

Quality

Content

45%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.

The content has a clear high-level workflow with a built-in refinement loop, but it is held back by notable verbosity and repetitive motivational padding, abstract rather than executable canvas guidance, and a monolithic structure with a missing canvas-fonts reference. It reads more as creative brief than as tight, actionable instruction.

Suggestions

Remove the repeated craftsmanship emphasis (it appears 4+ times: lines 49, 84, 107, 115) and the poetic padding (e.g. "as if it were a scientific bible", "This is true art.") — state the craft bar once and trust it.

Add concrete execution guidance for producing output: name a tool/library or give a runnable snippet for generating .png/.pdf, so the canvas section is actionable rather than aspirational.

Fix or remove the broken ./canvas-fonts reference (the directory is not in the bundle), and consider splitting the philosophy examples into a separate reference file to reduce the monolithic SKILL.md.

Dimension	Reasoning	Score
Conciseness	The body is noticeably verbose with several padded sections, repeating the craftsmanship/emphasis ("meticulously crafted", "countless hours", "top of their field", "EXPERT CRAFTSMANSHIP") four or more times and including poetic prose ("as if it were a scientific bible", "This is true art.") that does not earn its tokens, fitting the noticeably-verbose anchor rather than the mostly-efficient one.	2 / 5
Actionability	There is some concrete scaffolding (name in 1-2 words, 4-6 paragraphs, five named example philosophies, a real font directory), but the canvas instructions are abstract ("create work that looks like it took countless hours", "use repeating patterns and perfect shapes") with no library, tool, or code for actually producing a .png/.pdf, leaving key execution details missing.	3 / 5
Workflow Clarity	A clear two-step sequence is stated up front (Design Philosophy Creation, then Canvas Creation) and the sections follow it, including a FINAL STEP refinement pass with a self-check prompt ("If the instinct is to call a new function... STOP and instead ask..."); only minor validation gaps (no explicit output-render verification) keep it from a 5.	4 / 5
Progressive Disclosure	All content is inlined into a single ~124-line SKILL.md with the philosophy examples and canvas guidance that could live in separate files, and the one external reference ("Search the ./canvas-fonts directory") points to a directory that does not exist in the bundle, matching the minimal-structure / broken-reference anchor.	2 / 5
	Total	11 / 20 Passed

Description

82%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.

The description is strong: it explicitly answers both what the skill does and when to use it, with concrete trigger terms and a distinct niche. Its only real weakness is specificity of capabilities, which stay at a generic level rather than enumerating concrete design actions.

Dimension	Reasoning	Score
Specificity	Names the domain (visual art in .png/.pdf) and a couple concrete actions ("Create beautiful visual art", "Create original visual designs, never copying"), but the actions are generic with no specifics on layout, typography, or color systems, matching the 1-2 concrete actions anchor rather than the several-actions anchor.	3 / 5
Completeness	Both halves are explicit: "what" is stated ("Create beautiful visual art in .png and .pdf documents using design philosophy") and "when" is concrete with multiple trigger phrases ("You should use this skill when the user asks to create a poster, piece of art, design, or other static piece"), matching the anchor for clear and explicit answers to both.	5 / 5
Trigger Term Quality	Natural trigger terms users would say ("poster, piece of art, design, or other static piece") plus file extensions (.png, .pdf) give good coverage, though synonyms like "artwork", "graphic", or "flyer" are missing, so it falls just below the comprehensive anchor.	4 / 5
Distinctiveness Conflict Risk	It carves a clear niche (original art/design generation in image and PDF formats) with distinct triggers (poster, art, design) that few other skills would match, giving minimal conflict risk.	5 / 5
	Total	17 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: davepoon/buildwithclaude
Path: plugins/all-skills/skills/canvas-design/SKILL.md
Commit: a9fa86d

Reviewed: about 20 hours 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.