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.

Quality

50%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./SKILLs/canvas-design/SKILL.md

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

Quality

Content

35%

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

The skill communicates a coherent two-phase design workflow with good examples, but it is padded with repeated craftsmanship rhetoric, lacks concrete rendering tooling or validation checkpoints, and references a non-existent fonts directory.

Suggestions

Collapse the repeated craftsmanship emphasis into a single statement; remove the duplicated 'EXPERT CRAFTSMANSHIP' principle to recover token budget.

Provide concrete rendering guidance (specific tool/code for producing .pdf/.png) and a verification checkpoint confirming the file rendered with no overlapping or off-canvas elements.

Fix or remove the ./canvas-fonts reference, or actually ship the fonts directory and point to it cleanly.

Dimension	Reasoning	Score
Conciseness	The craftsmanship framing ('meticulously crafted', 'countless hours', 'master-level execution', 'top of their field', 'expert-level craftsmanship') is restated across at least five sections, and 'EXPERT CRAFTSMANSHIP' repeats the earlier guideline verbatim — heavy redundant padding rather than lean instruction.	1 / 3
Actionability	Gives concrete structural guidance (name the movement in 1-2 words, 4-6 paragraphs, named examples) but the canvas step is abstract ('create museum or magazine quality work') with no concrete rendering tool or code, and it points to a ./canvas-fonts directory that does not exist.	2 / 3
Workflow Clarity	The sequence (philosophy .md -> deduce reference -> canvas .pdf/.png -> final refinement) is clearly laid out, but there are no explicit validation or verification checkpoints and the 'FINAL STEP' is framed as a fabricated user quote rather than a verify-fix-retry loop.	2 / 3
Progressive Disclosure	Sections are well organized, but the body is a monolithic ~123-line single file with no split reference files, and it references ./canvas-fonts which is not present in the bundle, so the one external reference is broken.	2 / 3
	Total	7 / 12 Passed

Description

65%

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 clearly answers both what and when with an explicit trigger clause and a distinct niche, but it is written in second person and its named actions are repetitive rather than comprehensive, capping specificity.

Suggestions

Rewrite in third person ('Creates visual art...') to avoid the voice penalty on specificity.

Broaden trigger terms to cover common variations such as 'illustration', 'graphic', 'flyer', 'image', and 'artwork'.

Replace the repetitive 'Create beautiful visual art' / 'Create original visual designs' with a few more distinct concrete actions (e.g., compose layouts, apply color palettes, render to .png/.pdf).

Dimension	Reasoning	Score
Specificity	Names the domain ('visual art in .png and .pdf documents') and the action 'Create original visual designs', but the two named actions are near-synonymous rather than a comprehensive set; the second-person phrasing 'You should use this skill' triggers the -1 voice penalty.	1 / 3
Completeness	Explicitly states what it does ('Create beautiful visual art in .png and .pdf documents') and when to use it ('You should use this skill when the user asks to create a poster, piece of art, design, or other static piece').	3 / 3
Trigger Term Quality	Includes natural user terms ('poster', 'piece of art', 'design', 'static piece') but omits common variations like illustration, graphic, flyer, image, or artwork that a user would equally likely say.	2 / 3
Distinctiveness Conflict Risk	The niche of static visual art / design-philosophy output in .png and .pdf with 'never copying existing artists' work' is distinct from document, code, and general image skills.	3 / 3
	Total	9 / 12 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: netease-youdao/LobsterAI
Path: SKILLs/canvas-design/SKILL.md
Commit: 2921c1e

Reviewed: about 11 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.