banner-design

Design banners for social media, ads, website heroes, creative assets, and print. Multiple art direction options with AI-generated visuals. Actions: design, create, generate banner. Platforms: Facebook, Twitter/X, LinkedIn, YouTube, Instagram, Google Display, website hero, print. Styles: minimalist, gradient, bold typography, photo-based, illustrated, geometric, retro, glassmorphism, 3D, neon, duotone, editorial, collage. Uses ui-ux-pro-max, frontend-design, ai-artist, ai-multimodal skills.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

85%

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

The body is highly actionable with executable commands and a clear, well-sequenced workflow backed by a real one-level-deep reference file. The main weakness is redundant inline duplication of the size and style tables that already appear in the reference, which modestly hurts token efficiency.

Suggestions

Remove the inline 'Banner Size Quick Reference' and 'Art Direction Styles (Top 10)' tables (or shrink them to 3-4 rows) since the full data lives in references/banner-sizes-and-styles.md, relying on the existing 'Full reference' links instead.

Add a brief verification checkpoint in Step 4 confirming each exported PNG exists at the requested dimensions before presenting options, to harden the batch export loop.

Consider moving the model-selection and aspect-ratio guidance into the reference file to further lean down the core workflow.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and free of concept-explanation fluff, but the banner-size quick-reference table and the top-10 art-direction styles table are duplicated inline while the full versions live in the reference file, so it could be tightened.	2 / 3
Actionability	It provides fully executable, copy-paste-ready commands with exact flags (e.g., gemini_batch_process.py with --model/--prompt/--aspect-ratio/--size/--output and screenshot.js with --width/--height/--output), plus a concrete model-selection table.	3 / 3
Workflow Clarity	A clear five-step sequence (gather → research → design → export → present) with an explicit feedback loop in Step 5 ('Iterate based on user feedback until approved') and a built-in auto-compress checkpoint in the export step.	3 / 3
Progressive Disclosure	SKILL.md is an overview with a real, clearly signaled, one-level-deep reference (references/banner-sizes-and-styles.md, verified to exist) and content appropriately split between inline quick reference and the full reference file.	3 / 3
	Total	11 / 12 Passed

Description

72%

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 specific about domain, platforms, and styles and uses natural trigger terms in third person, but its named actions are generic verbs and it lacks an explicit 'Use when...' trigger clause. Adding concrete actions and an explicit activation clause would raise specificity and completeness.

Suggestions

Replace the generic 'Actions: design, create, generate banner' with concrete, distinct actions (e.g., 'compose HTML/CSS banners, generate AI visuals, export platform-sized PNGs').

Add an explicit 'Use when...' clause stating when Claude should activate this skill (e.g., 'Use when the user requests banner, cover, or header design for social, ads, web, or print').

Trim the long platform/style enumeration slightly to keep the description concise while preserving the strongest trigger terms.

Dimension	Reasoning	Score
Specificity	Names a concrete domain (banners across social/ads/web/print) plus specific platforms and styles, but the listed 'Actions: design, create, generate banner' are generic verbs rather than distinct concrete actions, so it stops short of the level-3 anchor.	2 / 3
Completeness	It clearly states what the skill does, but there is no 'Use when...' clause or equivalent explicit trigger guidance; the 'Actions:' list is only a weak trigger signal, so per the guideline completeness is capped at 2.	2 / 3
Trigger Term Quality	Covers natural terms users would actually say — 'banner', 'cover', 'header design', plus platform names (Facebook, Twitter/X, LinkedIn, YouTube, Instagram) and common style labels — giving good trigger coverage.	3 / 3
Distinctiveness Conflict Risk	Banner/cover/header design is a clear niche with distinct triggers, written in third person, and unlikely to fire for unrelated skills despite referencing several helper skills.	3 / 3
	Total	10 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 8 missing	Warning

	Total	14 / 16 Passed

Repository: nextlevelbuilder/ui-ux-pro-max-skill
Commit: cc3d1be

Reviewed: 2 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.