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.

67

1.48x
Quality

53%

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

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

SKILL.md
Quality
Evals
Security

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 lays out a clear two-phase workflow with concrete deliverables, but it is heavily padded with repetitive craftsmanship rhetoric and poetic framing, lacks executable rendering guidance or validation checkpoints, and is a monolithic wall of text with a dangling directory reference.

Suggestions

Cut the repeated craftsmanship rhetoric and poetic passages; state the aesthetic and quality bar once and lean on Claude's competence to preserve token budget.

Add a concrete, executable method for producing the .pdf/.png canvas (library, script, or precise tool steps) so the actionability reaches copy-paste-ready guidance.

Add a verification checkpoint (e.g., confirm margins, no overlap, fonts embedded) before declaring the output final, and either create the referenced ./canvas-fonts directory or remove the dangling reference.

DimensionReasoningScore

Conciseness

The body is padded with motivational and poetic framing ("Treat the abstract philosophical design as if it were a scientific bible", "Embrace the paradox of using analytical visual language") and explicitly instructs REPEATED craftsmanship phrases ("meticulously crafted", "painstaking attention"), plus a fabricated user quote in the FINAL STEP — well beyond lean instruction.

1 / 3

Actionability

It specifies concrete deliverables (a .md philosophy plus a single .pdf or .png, 4–6 paragraphs, name the movement in 1–2 words, search ./canvas-fonts), but the actual rendering execution is abstract ("create a masterpiece", "push aesthetics to the frontier") with no method or tooling for producing the canvas.

2 / 3

Workflow Clarity

A clear two-step sequence is stated up front (Design Philosophy Creation, then Canvas Creation) with a refinement pass in the FINAL STEP, but there are no validation checkpoints or verification steps to confirm output quality.

2 / 3

Progressive Disclosure

Section headers provide some structure, but the ~120-line body is monolithic with philosophy examples and canvas details all inline; the only referenced path ("./canvas-fonts") does not exist and no reference files are provided to split content into.

2 / 3

Total

7

/

12

Passed

Description

72%

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 states both capability and explicit use-conditions with natural trigger terms, but it loses specificity for second-person phrasing and some vague language, and its broad "design" framing carries mild conflict risk.

Suggestions

Rewrite in third person (e.g., "Creates visual art in .png and .pdf documents... Use when the user requests a poster, artwork, or static design") to remove the second-person penalty.

Replace the vague adjective "beautiful" with more concrete capability language, and add one or two more specific actions to reach full specificity.

Tighten the trigger list to more common natural phrasings (e.g., "poster", "artwork", "flyer", "illustration") to reduce overlap with generic design skills.

DimensionReasoningScore

Specificity

Names the domain and a couple of concrete actions ("Create beautiful visual art in .png and .pdf documents", "Create original visual designs"), but the actions are not comprehensive and "beautiful" is vague; the description uses second person ("You should use this skill when the user asks..."), which per the guidelines reduces specificity by one from a base of 2.

1 / 3

Completeness

Explicitly answers both "what" ("Create beautiful visual art in .png and .pdf documents using design philosophy") and "when" ("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-facing terms "poster, piece of art, design, or other static piece" plus ".png and .pdf", giving good coverage of phrases a user would actually say when requesting this skill.

3 / 3

Distinctiveness Conflict Risk

The png/pdf visual-art framing is a reasonably clear niche, but "design" and "other static piece" are broad enough to overlap with general document or presentation design skills.

2 / 3

Total

9

/

12

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.

Validation15 / 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.