CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

66

1.48x
Quality

52%

Does it follow best practices?

Impact

89%

1.48x

Average score across 3 eval scenarios

SecuritybySnyk

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
SKILL.md
Quality
Evals
Security

Quality

Content

35%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 skill has a legible high-level workflow and consistent aesthetic vision, but the body is padded with repeated motivational prose and provides almost no executable guidance — no rendering tool, no code, and a font directory reference that does not exist. It would benefit substantially from tightening and from concrete output-generation instructions.

Suggestions

Name the actual rendering mechanism (e.g., a specific library or script for generating the .pdf/.png) or include a minimal executable example, instead of "express it on a canvas" with no tooling.

Collapse the repeated craftsmanship language into one guideline and cut filler sentences; the same point is made in CRITICAL GUIDELINES, ESSENTIAL PRINCIPLES, CANVAS CREATION, and FINAL STEP.

Move the five philosophy examples to a references file (e.g., references/philosophy-examples.md) and either ship the ./canvas-fonts directory or remove the dangling reference.

Replace the fabricated user quote in FINAL STEP with an explicit, self-triggered verification step (e.g., re-render and check margins/overlap before delivering).

DimensionReasoningScore

Conciseness

The body is noticeably verbose with several padded, repetitive sections: craftsmanship exhortations ("meticulously crafted," "painstaking attention," "countless hours") appear in at least four places, and filler like "Take a moment to gather thoughts and clear the mind" and "This is true art." earns no tokens. It avoids anchor 1 only because it does not explain concepts Claude already knows — the padding is motivational repetition, not tutorial material.

2 / 5

Actionability

Guidance is almost entirely abstract: the canvas step never names a tool, library, or code path for actually producing a .pdf or .png, and font handling boils down to "Download and use whatever fonts are needed" plus a pointer to a ./canvas-fonts directory that does not exist in the bundle. This fits anchor 2 (high-level hints, missing the specific steps to execute) rather than anchor 1 because the two-step structure and output formats do give minimal concrete direction.

2 / 5

Workflow Clarity

A clear two-step sequence exists (create philosophy .md, then express on canvas as .pdf/.png) followed by a refinement pass, but validation is implicit only — "Check carefully that all text, graphics, and visual elements have breathing room" is a directive with no verification loop, and the FINAL STEP invents a user quote ("The user ALREADY said…") as its trigger. This matches anchor 3: sequence present, checkpoints missing or implicit.

3 / 5

Progressive Disclosure

Section headers (DESIGN PHILOSOPHY CREATION, CANVAS CREATION, FINAL STEP, MULTI-PAGE OPTION) give real structure, but ~130 lines of inline content — including five full philosophy examples and long canvas prose — clearly belongs in separate reference files, and the only path reference, ./canvas-fonts, is not present in the bundle. This is anchor 3 (some structure, content that should be separate is inline, references not clearly signaled) rather than anchor 2 because navigation between the existing sections is straightforward.

3 / 5

Total

10

/

20

Passed

Description

70%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 well-formed with an explicit use-when clause containing natural trigger terms and file extensions. Its main weakness is a somewhat vague 'what' — "beautiful visual art… using design philosophy" — that leans on buzzwords instead of enumerating concrete capabilities.

Suggestions

Replace "using design philosophy" with concrete capabilities, e.g. "Creates original poster art and visual designs as .png or .pdf, developing a custom aesthetic philosophy and applying it with intentional typography and composition."

Add common synonyms users would say, such as flyer, illustration, artwork, or graphic, to the use-when clause.

Trim evaluative filler like "beautiful" and the copyright note could be shortened to keep the description token-lean.

DimensionReasoningScore

Specificity

The description names the domain ("Create beautiful visual art in .png and .pdf documents") and 1-2 concrete actions (create original visual designs, avoid copying artists' work), but adds padding like "using design philosophy" and "beautiful" without covering the actual capability surface (typography, layout, multi-page output). It matches anchor 3 (domain plus 1-2 concrete actions, not comprehensive) rather than anchor 4, which requires several specific listed actions.

3 / 5

Completeness

Both parts are present: what ("Create beautiful visual art in .png and .pdf documents") and an explicit when ("You should use this skill when the user asks to create a poster, piece of art, design, or other static piece"). It does not reach anchor 5 because the 'what' is vaguer than the exemplar's list of concrete actions — "using design philosophy" describes approach, not capability.

4 / 5

Trigger Term Quality

"poster, piece of art, design, or other static piece" plus ".png and .pdf" gives good natural keyword coverage a user would actually say. It falls short of anchor 5 because common synonyms like flyer, illustration, graphic, or artwork are missing, though it is clearly above the generic-keyword level of anchor 3.

4 / 5

Distinctiveness Conflict Risk

The poster/art/static-piece niche with .png/.pdf outputs is mostly distinct from document- or data-processing skills, but the broad trigger "design" and "other static piece" leave minor overlap risk with image-generation, diagram, or presentation skills, keeping it below anchor 5.

4 / 5

Total

15

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
davepoon/buildwithclaude
Reviewed

Table of Contents

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.