brand-visual-generator

When the user wants to define, audit, or apply visual identity (typography, colors, spacing, design tokens, frontend aesthetics). Also use when the user mentions "brand style guide," "visual identity," "design system," "typography," "color palette," "brand guidelines," "AI brand aesthetics," "brand colors," "font choices," "spacing system," "design tokens," "motion," "distinctive design," "frontend aesthetics," "PowerPoint theme," "Google Slides brand," or "slide master colors." For brand story, positioning, and voice, use branding.

Quality

76%

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 ./skills/components/branding/brand-visual/SKILL.md

Quality

Content

57%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 a well-organized, reasonably actionable design-reference skill, but it spends tokens on marketing stats, redundant keyword lists, and widely known design rules, keeps its workflow implicit, and inlines large reference tables that belong in bundled reference files. Tightening the preamble, making the assess→design→output sequence explicit with checkpoints, and externalizing the trends/archetype tables would lift all four dimensions.

Suggestions

Delete the revenue-lift/consumer statistics line, the Keywords line (duplicates the description's triggers), and the 'When invoking' preamble; they add tokens without adding capability.

Make the workflow an explicit numbered sequence (assess scope/touchpoints → define tokens → verify against the accessibility checklist → output per the Output Format section) so validation becomes a checkpoint rather than an appendix.

Move the AI Brand Aesthetics trend/archetype tables and the Frontend Aesthetics deep dive into references/ files (e.g. references/ai-aesthetics.md) and link to them from the body, keeping SKILL.md as a lean overview.

Dimension	Reasoning	Score
Conciseness	Mostly dense, actionable bullets, but padded with material Claude does not need: unverifiable marketing statistics ("23-33% revenue lift; 94% of consumers"), a Keywords line that duplicates the description's triggers, a "When invoking" meta preamble, and restated common knowledge (WCAG 4.5:1 ratios, "Don't: Stretch, recolor" logo rules).	3 / 5
Actionability	Concrete, specific guidance throughout: type ratios ("1.25–1.5"), spacing base ("8px"), industry-to-color mappings, named fonts (Source Sans 3, Lora, IBM Plex Sans), named icon libraries (Heroicons, Lucide), a HEX-to-RGB tuple rule for python-pptx, and a copy-paste Contextus return template. As an instruction-only skill the absence of code is acceptable; only minor gaps remain (no example token or CSS-variable output).	4 / 5
Workflow Clarity	The Initial Assessment → Best Practices → Output Format flow is inferable but never explicitly sequenced, and the Accessibility Checklist reads as reference material rather than a validation checkpoint in the workflow (no "verify contrast after palette selection" step or feedback loop).	3 / 5
Progressive Disclosure	No bundle files exist, so everything is inlined in a ~190-line body. Sections are well-organized and navigable, but the AI visual-trends/archetypes tables and the Frontend Aesthetics deep dive are optional reference-shaped content that should live in one-level-deep reference files rather than inline.	3 / 5
	Total	13 / 20 Passed

Description

95%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 strong description: explicit what and when, dense natural trigger coverage including slide-tool-specific terms, and a clear disambiguation boundary against the branding skill. The only gap is that the capability list is slightly less concretely itemized than the top specificity anchor.

Dimension	Reasoning	Score
Specificity	The description lists three concrete actions ("define, audit, or apply visual identity") with a scoped subdomain list (typography, colors, spacing, design tokens, frontend aesthetics), but stops short of the fully itemized action coverage of the top anchor.	4 / 5
Completeness	It explicitly answers both questions: what ("define, audit, or apply visual identity (typography, colors, spacing, design tokens, frontend aesthetics)") and when ("When the user wants to... Also use when the user mentions...") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Seventeen natural, quoted trigger phrases including synonyms and tool-specific variants ("brand style guide," "color palette," "font choices," "motion," "PowerPoint theme," "Google Slides brand," "slide master colors") give comprehensive coverage of what users would actually say.	5 / 5
Distinctiveness Conflict Risk	It carves a clear visual-execution niche and adds an explicit boundary clause ("For brand story, positioning, and voice, use branding."), minimizing overlap with adjacent skills.	5 / 5
	Total	19 / 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: kostja94/marketing-skills
Path: skills/components/branding/brand-visual/SKILL.md
Commit: 26cef34

Reviewed: 23 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.