canvas-design

These are instructions for creating design philosophies - aesthetic movements that are then EXPRESSED VISUALLY. Output only .md files, .pdf files, and .png files.

Quality

22%

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 ./plugins/AI-Agents-Safe-Coding-Skills/skills/canvas-design/SKILL.md

Quality

Content

27%Scale 1-3

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

This skill is highly verbose and repetitive, spending enormous token budget on restating the same aesthetic principles (craftsmanship, minimalism, visual expression) rather than providing concrete, executable guidance. While the creative vision is clear and the two-step workflow is logical, the skill lacks technical specificity—there are no code examples for PDF/PNG generation, no tool usage instructions, and no validation steps. The entire content is a monolithic block that would benefit greatly from restructuring and aggressive trimming.

Suggestions

Cut repetitive emphasis on craftsmanship, minimalism, and visual expression to single authoritative statements—the current content repeats these themes 5+ times each without adding new information.

Add concrete, executable code examples for PDF/PNG generation (e.g., using reportlab, PIL/Pillow, or cairo) including font loading from the referenced `./canvas-fonts` directory.

Split philosophy examples into a separate EXAMPLES.md file and canvas creation technical details into a CANVAS.md file, keeping SKILL.md as a concise overview with clear references.

Add explicit validation checkpoints: e.g., verify PDF renders correctly, check all elements are within canvas bounds programmatically, validate font files exist before use.

Dimension	Reasoning	Score
Conciseness	Extremely verbose and repetitive. The instruction to emphasize 'expert craftsmanship' is itself repeated at least 5-6 times across different sections. Concepts like 'minimal text,' 'visual expression,' and 'museum quality' are restated redundantly throughout. The skill could be cut by 60%+ without losing actionable content.	1 / 3
Actionability	Provides some concrete guidance through philosophy examples and a structured two-step workflow, but lacks executable code, specific tool commands, or concrete technical instructions for actually generating PDFs/PNGs. References a `./canvas-fonts` directory but gives no code for font loading, PDF generation libraries, or canvas rendering.	2 / 3
Workflow Clarity	The two-step workflow (philosophy creation → canvas creation) is clearly sequenced, and there's a refinement pass at the end. However, there are no validation checkpoints, no error recovery steps, and the 'final step' refinement lacks concrete criteria for what 'pristine' means. The destructive/iterative nature of the refinement step ('go back to the code') has no feedback loop.	2 / 3
Progressive Disclosure	Monolithic wall of text with no references to external files for detailed guidance. The philosophy examples, canvas creation instructions, multi-page options, and refinement steps are all inline in one massive document. Content like the philosophy examples or canvas creation technical details could easily be split into separate referenced files.	1 / 3
	Total	6 / 12 Passed

Description

17%Scale 1-3

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 too vague and abstract to effectively guide skill selection. It lacks concrete actions, natural trigger terms users would use, and any explicit 'Use when...' guidance. The mention of output file formats is a minor positive but doesn't compensate for the overall lack of specificity and completeness.

Suggestions

Add a 'Use when...' clause with natural trigger terms, e.g., 'Use when the user asks to create a design philosophy, visual aesthetic, art movement concept, mood board, or style guide.'

List specific concrete actions the skill performs, e.g., 'Defines aesthetic principles, generates visual mood boards as .png files, produces written style manifestos as .md or .pdf files.'

Include common user-facing keywords like 'design style', 'visual identity', 'art direction', 'aesthetic concept', or 'mood board' to improve trigger term coverage.

Dimension	Reasoning	Score
Specificity	It names the domain ('design philosophies', 'aesthetic movements') and mentions output formats (.md, .pdf, .png), but the core actions are vague—'creating' and 'expressed visually' don't describe concrete steps like 'generate mood boards' or 'produce style guides'.	2 / 3
Completeness	The 'what' is only partially addressed (creating design philosophies expressed visually), and there is no 'when' clause or explicit trigger guidance at all. Per the rubric, a missing 'Use when...' clause caps completeness at 2, and the weak 'what' brings it to 1.	1 / 3
Trigger Term Quality	The description lacks natural keywords a user would say. Terms like 'design philosophies' and 'aesthetic movements' are niche and abstract; common trigger terms like 'design style', 'visual aesthetic', 'art movement', 'mood board', or 'style guide' are absent.	1 / 3
Distinctiveness Conflict Risk	The combination of 'design philosophies' and 'aesthetic movements' is somewhat distinctive, but the vague framing could overlap with general design, art, or visual creation skills. The output format constraint (.md, .pdf, .png) adds some distinction but isn't enough for a clear niche.	2 / 3
	Total	6 / 12 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills/skills/canvas-design/SKILL.md
Commit: 7520423

Reviewed: ~11 hours 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.