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.

1.75x

Quality

61%

Does it follow best practices?

Impact

98%

1.75x

Average score across 10 eval scenarios

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./claude/skills/canvas-design/SKILL.md

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

Quality

Content

48%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 lays out a clear, well-sectioned creative workflow with useful worked examples, but it is padded with poetic and repetitious prose and never tells Claude concretely how to produce the .png/.pdf output. Splitting the examples into a reference file and tightening the language would materially raise the score.

Suggestions

Cut the repeated craftsmanship rhetoric and poetic filler ("gather thoughts and clear the mind," "scientific bible") to one concise statement; the repeated emphasis consumes tokens without adding instruction.

Add concrete generation guidance: name the library or approach for rendering .png/.pdf (e.g., a specific drawing/PDF library) so the canvas step is executable rather than aspirational.

Move the five philosophy examples into a references/ file (e.g. PHILOSOPHY_EXAMPLES.md) and link to it from the body, improving progressive disclosure and reducing the monolith.

Dimension	Reasoning	Score
Conciseness	The body is noticeably verbose: it deliberately repeats craftsmanship phrases ("meticulously crafted," "master-level execution"), uses poetic filler ("Take a moment to gather thoughts and clear the mind," "scientific bible"), and the ESSENTIAL PRINCIPLES section restates points already made above, matching the anchor 2 of several padded sections.	2 / 5
Actionability	It gives concrete guidance for philosophy creation (name the movement in 1-2 words, 4-6 paragraphs, five worked examples) and design directives (repeating patterns, limited palette, thin fonts, no overlaps), but provides no tooling or executable method for actually generating the .png/.pdf, leaving the technical execution incomplete as in the anchor 3 example.	3 / 5
Workflow Clarity	The process is clearly sequenced (philosophy .md, deduce the subtle reference, canvas creation, final refinement pass) with explicit checkpoints ("nothing falls off the page and nothing overlaps... Check carefully"; the second-pass refinement), matching anchor 4, though there is no explicit render/validate-verification loop.	4 / 5
Progressive Disclosure	The skill is a 130-line monolith with no bundle files, and the five inlined philosophy examples plus detailed philosophy guidance are content that could live in a separate reference file; section headers give some structure but nothing is split out, fitting anchor 3.	3 / 5
	Total	12 / 20 Passed

Description

73%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 cleanly covers both capability and explicit trigger conditions with natural user vocabulary, making it highly complete and distinctive. Its main weakness is the second-person phrasing, which both violates the third-person voice guideline and depresses the specificity score.

Suggestions

Rewrite in third person to avoid the second-person penalty, e.g. "Creates original visual art as .png and .pdf files using a design-philosophy approach. Use when the user requests a poster, piece of art, design, or other static visual piece."

Add more concrete action verbs and synonyms (illustration, graphic, flyer, render) to lift specificity and trigger-term coverage toward 5.

Trim the redundant final sentence about copyright into the trigger clause to keep the description tight.

Dimension	Reasoning	Score
Specificity	Names the domain and one concrete action ("Create beautiful visual art in .png and .pdf documents"), matching the anchor 3 example of a single named action, but the description uses second person ("You should use this skill when..."), which the rubric penalizes by reducing the specificity score by 1.	2 / 5
Completeness	It explicitly answers both "what" (create visual art in .png/.pdf using design philosophy) and "when" with concrete 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 5 example.	5 / 5
Trigger Term Quality	It includes natural user terms ("poster, piece of art, design, or other static piece") plus file extensions (.png, .pdf), giving good coverage, but it lacks common synonyms such as illustration, graphic, or flyer that would push it to a 5.	4 / 5
Distinctiveness Conflict Risk	The art/design-philosophy framing with poster/art/design triggers carves a mostly distinct niche with minimal overlap risk, though it could still brush against generic image- or document-generation skills, so it stops short of a 5.	4 / 5
	Total	15 / 20 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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: einverne/dotfiles
Path: claude/skills/canvas-design/SKILL.md
Commit: 7d18cf4

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.