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.

94

1.75x
Quality

50%

Does it follow best practices?

Impact

98%

1.75x

Average score across 10 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/anthropic-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 body lays out a coherent two-phase creative workflow with useful worked examples, but it is heavily padded with repeated exhortations and provides no concrete mechanism for actually generating the promised .pdf/.png output, nor any verification step that the rendered artifact is valid.

Suggestions

Add concrete generation guidance: name the rendering approach (e.g., a specific PDF/graphics library or HTML-to-PDF pipeline) and a minimal working code skeleton for producing the single-page output.

Collapse the craftsmanship and minimal-text exhortations (repeated in DESIGN PHILOSOPHY CREATION, ESSENTIAL PRINCIPLES, CANVAS CREATION, and FINAL STEP) into one short section, cutting the body roughly in half.

Add an explicit validation checkpoint after canvas creation: open/inspect the generated file to confirm it renders, that no elements overlap or fall outside margins, and only then proceed to the refinement pass.

Fix or remove the ./canvas-fonts reference — the directory does not exist in the skill bundle.

DimensionReasoningScore

Conciseness

The body is noticeably padded: craftsmanship exhortations ('meticulously crafted', 'countless hours', 'top of their field') repeat across at least five sections, the minimal-text rule is restated six times, and filler like 'Take a moment to gather thoughts and clear the mind' and 'This is true art.' earns no tokens — it even explicitly instructs repeating points ('Emphasize craftsmanship REPEATEDLY').

2 / 5

Actionability

The philosophy-creation step has concrete shape (1-2 word name, 4-6 paragraphs, five worked examples), but the canvas step offers only high-level aesthetic direction with no executable mechanism — no library, command, or rendering approach for producing the .pdf/.png — and its one concrete pointer ('Search the ./canvas-fonts directory') references a path absent from the bundle.

2 / 5

Workflow Clarity

A real sequence exists (create philosophy .md, deduce the subtle reference, render canvas, take a refinement second pass, optional multi-page) including a refinement loop, but validation is implicit — 'Check carefully that all text... have breathing room' is an instruction to be careful, not a checkpoint that verifies the output file renders correctly or that elements stay in-bounds.

3 / 5

Progressive Disclosure

The single file is well-organized with clear section headers, but at ~120 lines it exceeds the simple-skill exception, content that could be split (the five philosophy examples, font guidance) is inlined, and the only external reference (./canvas-fonts) is not clearly signaled and does not resolve to a file in the bundle.

3 / 5

Total

10

/

20

Passed

Description

65%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.

A solid description with an explicit trigger clause, natural keywords, and a clear output format, weakened by second-person phrasing and a 'what' that stays at the level of vibes ('beautiful', 'design philosophy') rather than enumerating the skill's actual two-step deliverables.

Suggestions

Rewrite in third person (e.g., 'Use when the user asks to create...' instead of 'You should use this skill when...') to avoid the specificity penalty.

Enumerate the concrete deliverables: write a design-philosophy manifesto as a .md file, then render a single-page .pdf/.png artwork, with a multi-page option when requested.

DimensionReasoningScore

Specificity

The description names the domain and 1-2 concrete actions ('Create beautiful visual art in .png and .pdf documents', 'Create original visual designs') but omits the philosophy-manifesto and multi-page capabilities, which alone would anchor at 3; the rubric's second-person penalty for 'You should use this skill when...' reduces it to 2.

2 / 5

Completeness

Both what ('Create beautiful visual art in .png and .pdf documents using design philosophy') and an explicit when ('when the user asks to create a poster, piece of art, design, or other static piece') are present, but 'beautiful' and 'using design philosophy' are vague, so it falls short of the fully concrete 5 anchor.

4 / 5

Trigger Term Quality

Good natural keyword coverage ('poster', 'piece of art', 'design', 'static piece') plus file extensions (.png, .pdf), but common synonyms users would say such as 'image', 'illustration', 'artwork', or 'graphic' are missing, fitting the 'a few natural terms missing' anchor rather than the comprehensive 5.

4 / 5

Distinctiveness Conflict Risk

The static-art niche with .png/.pdf outputs and triggers like 'poster' is mostly distinct from document- or data-oriented skills, with only minor overlap risk against general image/diagram-generation skills.

4 / 5

Total

14

/

20

Passed

Validation

100%

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
boisenoise/skills-collections
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.