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.

Quality

50%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

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

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 is prose-heavy and repetitive, offering aesthetic philosophy rather than executable guidance, and relies on a font directory that is not bundled. Workflow sequence exists but lacks validation checkpoints and includes a fabricated user quote.

Suggestions

Cut repeated craftsmanship rhetoric to one concise statement and remove poetic filler (e.g., the "scientific bible" passage) to reduce token load.

Add concrete, executable guidance for producing output: a minimal code snippet or tool/command for rendering .png/.pdf, and either bundle `./canvas-fonts` or replace that reference with a real path.

Replace the fabricated FINAL STEP user quote with an explicit validation checkpoint (e.g., "Verify nothing overlaps and all elements sit within margins before finalizing") and a real refine/retry loop.

Dimension	Reasoning	Score
Conciseness	Noticeably verbose with repeated padding: "meticulously crafted", "countless hours", "painstaking attention", "master-level execution" and "expert craftsmanship" are restated many times across sections, and poetic filler ("Treat the abstract philosophical design as if it were a scientific bible") adds tokens without guidance value.	2 / 5
Actionability	Provides high-level aesthetic direction but no executable code, commands, or rendering specifics for producing .png/.pdf files, and references a `./canvas-fonts` directory that is not present in the bundle. Claude is told to "express it on a canvas" without concrete steps to do so.	2 / 5
Workflow Clarity	A recognizable two-step sequence (Design Philosophy Creation -> Canvas Creation) with an added refinement pass is present and headed, but there are no validation/checkpoint steps for verifying output, and the FINAL STEP fabricates a quoted user request ("the user ALREADY said...") which is misleading rather than a real feedback loop.	3 / 5
Progressive Disclosure	Content is organized into headed sections but is a single monolithic file with no external reference files (references/scripts/assets dirs are absent); the only cited path (`./canvas-fonts`) does not exist, so navigation and reference structure are underdeveloped.	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.

The description clearly states both capability and trigger conditions with good natural keyword coverage, but uses second-person voice and somewhat abstract action language. Specificity is the weakest dimension due to the voice penalty and lack of concrete operational actions.

Suggestions

Rewrite in third person (e.g., "Creates visual art... Use when the user asks to create...") and reframe "You should use this skill" as an impersonal trigger clause.

Replace abstract actions ("Create beautiful visual art", "Create original visual designs") with more concrete operations (e.g., "Generates poster layouts, typographic compositions, and pattern-based visuals as .png/.pdf").

Tighten the "when" clause by dropping the generic "or other static piece" in favor of a few more specific trigger nouns.

Dimension	Reasoning	Score
Specificity	States the domain ("Create beautiful visual art in .png and .pdf documents") and a couple of actions ("Create original visual designs"), but the actions are generic and abstract rather than concrete operations. Reduced by 1 for second-person voice ("You should use this skill") per the rubric's voice guideline.	2 / 5
Completeness	Answers both "what" (create visual art in .png/.pdf) and "when" ("You should use this skill when the user asks to create a poster, piece of art, design, or other static piece"). The "when" is explicit with concrete triggers, though "other static piece" is somewhat generic, keeping it just below a 5.	4 / 5
Trigger Term Quality	Includes natural user terms ("poster, piece of art, design, or other static piece") plus file extensions (.png, .pdf), giving good keyword coverage with only a few natural synonyms missing.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (static visual art / posters in .png and .pdf) with distinct triggers and low overlap risk with unrelated skills; only minor overlap risk with general document skills.	4 / 5
	Total	14 / 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: shareAI-lab/Kode-CLI
Path: packages/builtin-skills/skills/canvas-design/SKILL.md
Commit: c7f6fcc

Reviewed: 3 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.