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.

64

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./packages/builtin-skills/skills/canvas-design/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

62%

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

A well-structured creative workflow with a clear sequence and refinement loop, but it is over-padded with repeated craftsmanship emphasis and lacks both a concrete rendering mechanism and any progressive disclosure into reference files.

Suggestions

Collapse the repeated craftsmanship emphasis (lines 48, 83, 106, 114, 122, 126) into a single stated principle; remove the ESSENTIAL PRINCIPLES restatement to cut significant token bloat.

Add concrete, executable rendering guidance (e.g., a script or library call and a command) for actually generating the .pdf/.png, rather than only aspirational direction like "push aesthetics to the frontier".

Move the five philosophy examples and the MULTI-PAGE OPTION into a referenced file (e.g., references/philosophy-examples.md) so SKILL.md stays a lean overview with one-level-deep navigation.

DimensionReasoningScore

Conciseness

The guidance is domain-relevant rather than explaining basics Claude already knows, but it is padded: the craftsmanship theme ("meticulously crafted", "countless hours", "top of their field") is restated roughly six times and the ESSENTIAL PRINCIPLES section repeats points already made above, so it could be tightened considerably.

2 / 3

Actionability

Concrete guidance exists (1–2 word movement name, 4–6 paragraphs, search ./canvas-fonts, output .pdf/.png, no-overlap margin rules, five worked examples) but it is mixed with abstract aspirational direction ("push aesthetics to the frontier", "create a masterpiece") and provides no concrete rendering mechanism for actually producing the image.

2 / 3

Workflow Clarity

The process is clearly sequenced (Design Philosophy Creation → Deducing the Subtle Reference → Canvas Creation → FINAL STEP refinement) with explicit quality checks ("Double-check that nothing overlaps", "Check carefully that all text, graphics, and visual elements have breathing room") and a genuine feedback loop via the second-pass FINAL STEP.

3 / 3

Progressive Disclosure

Sections are well organized, but the skill is monolithic at ~125 lines with no bundle files (references/scripts/assets absent) and content that could be split—such as the five philosophy examples and the multi-page option—is kept inline rather than referenced one level deep.

2 / 3

Total

9

/

12

Passed

Description

90%

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 strong description with explicit what-and-when triggers and natural user keywords; its only notable weakness is second-person voice, which costs it specificity per the rubric's voice rule.

DimensionReasoningScore

Specificity

It names the domain and several concrete actions ("Create beautiful visual art in .png and .pdf documents", "Create original visual designs", "never copying existing artists' work"), which approach multiple specific actions, but the second-person phrasing "You should use this skill" triggers the rubric's voice penalty, reducing the score by one.

2 / 3

Completeness

It answers both halves explicitly: the "what" ("Create beautiful visual art in .png and .pdf documents using design philosophy") and an explicit "when" trigger ("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

Natural user-facing terms are well covered: "poster, piece of art, design, or other static piece" alongside ".png" and ".pdf" are exactly what a user would say when requesting this skill.

3 / 3

Distinctiveness Conflict Risk

The static-visual-art / poster niche scoped to .png and .pdf outputs is a clear, distinct trigger set unlikely to fire for unrelated skills.

3 / 3

Total

11

/

12

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
shareAI-lab/Kode-CLI
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.