Back to Skills

creativity

majiayu000
Updated Today
58
9
58
View on GitHub
Metaaidesign

About

This skill provides AI-powered creative direction for marketing campaigns, offering structured recommendations across visual styles, platforms, voiceovers, and music. Developers can use it to generate briefs, plan content, and ensure platform-specific creative alignment. It functions as a searchable database of 55+ styles and 30+ campaign categories for ads, videos, and social content.

Quick Install

Claude Code

Recommended
Plugin CommandRecommended
/plugin add https://github.com/majiayu000/claude-skill-registry
Git CloneAlternative
git clone https://github.com/majiayu000/claude-skill-registry.git ~/.claude/skills/creativity

Copy and paste this command in Claude Code to install this skill

Documentation

Creativity Pro Max - Creative Direction Intelligence

Comprehensive creative direction guide for digital marketing campaigns. Contains 55 styles, 18 platforms, 12 voiceover types, 17 music genres, and 30 campaign category recommendations. Searchable database with priority-based recommendations.

When to Apply

Reference these guidelines when:

  • Planning creative campaigns for any channel
  • Selecting visual styles for ads/content
  • Choosing voiceover/music direction
  • Creating platform-specific content
  • Developing creative briefs

Core Principle

92% prefer authentic content over polished ads. Prioritize real, relatable content over perfection.

Quick Style Selection

Audience/GoalRecommended Styles
Premium/LuxuryMinimalist Clean, Quiet Luxury, Dark Moody Cinematic
Tech/SaaSFuturistic Sci-Fi, Gradient Smooth, Minimalist Tech
Youth/Gen ZRaw Unpolished, Humor Comedic, Nostalgic 90s, Neon Cyber
Wellness/OrganicEarthy Organic, Emotional Storytelling, Pastel Soft
B2B/FinanceAuthoritative Expert, Data Visualization, Corporate Modern
CommunityAuthentic UGC, Conversational Casual, Behind The Scenes

How to Use This Skill

When user requests creative direction (campaign, ad, video, content), follow this workflow:

Step 1: Analyze User Requirements

Extract key information from user request:

  • Campaign type: Product launch, brand awareness, lead gen, etc.
  • Audience: Gen Z, Millennials, B2B, etc.
  • Industry: SaaS, e-commerce, healthcare, etc.
  • Platform: TikTok, Instagram, YouTube, etc.

Step 2: Generate Creative Brief (REQUIRED)

Always start with --creative-brief to get comprehensive recommendations:

python3 .claude/skills/creativity/scripts/search.py "<campaign_type> <audience> <industry>" --creative-brief [-c "Campaign Name"]

This command:

  1. Searches 5 domains in parallel (style, platform, voiceover, music, reasoning)
  2. Applies reasoning rules from creative-reasoning.csv to select best matches
  3. Returns complete brief: style, platform specs, voiceover, music, effects
  4. Includes anti-patterns to avoid

Example:

python3 .claude/skills/creativity/scripts/search.py "SaaS product launch gen z" --creative-brief -c "App Launch Campaign"

Step 3: Supplement with Detailed Searches (as needed)

After getting the creative brief, use domain searches for additional details:

python3 .claude/skills/creativity/scripts/search.py "<keyword>" --domain <domain> [-n <max_results>]

When to use detailed searches:

NeedDomainExample
More style optionsstyle--domain style "minimalist luxury"
Platform specsplatform--domain platform "tiktok reels"
Voiceover directionvoiceover--domain voiceover "authoritative expert"
Music recommendationsmusic--domain music "ambient electronic"
Campaign guidancereasoning--domain reasoning "e-commerce conversion"

Step 4: Load Reference Details (as needed)

For detailed implementation, load relevant references:

ReferenceContentUse When
creative-styles-part1.mdStyles 1-25 with keywords, colors, effectsSelecting visual direction
creative-styles-part2.mdStyles 26-55 with keywords, colors, effectsSelecting visual direction
color-psychology.mdColor meanings, combinations, applicationsChoosing color palette
voiceover-styles.md5 VO categories with delivery specsVideo/audio content
audio-music.mdMusic trends, sonic brandingVideo content, ads
visual-trends.md2025-26 design trendsModern visual direction

Search Reference

Available Domains

DomainUse ForExample Keywords
styleVisual aestheticsminimalist, ugc, cinematic, retro, luxury
platformChannel specstiktok, instagram, youtube, linkedin
voiceoverVO directionconversational, authoritative, playful
musicAudio directionambient, upbeat, orchestral, trending
reasoningCampaign strategyproduct launch, brand awareness, gen z

Example Workflow

User request: "Create a TikTok campaign for Gen Z SaaS product launch"

Step 1: Analyze Requirements

  • Campaign type: Product launch
  • Audience: Gen Z
  • Industry: SaaS
  • Platform: TikTok

Step 2: Generate Creative Brief (REQUIRED)

python3 .claude/skills/creativity/scripts/search.py "gen z saas product tiktok" --creative-brief -c "SaaS Launch"

Step 3: Supplement with Detailed Searches (as needed)

# Get TikTok-specific guidelines
python3 .claude/skills/creativity/scripts/search.py "tiktok" --domain platform

# Get Gen Z style options
python3 .claude/skills/creativity/scripts/search.py "gen z authentic raw" --domain style

Output Formats

# ASCII box (default) - best for terminal display
python3 .claude/skills/creativity/scripts/search.py "e-commerce launch" --creative-brief

# Markdown - best for documentation
python3 .claude/skills/creativity/scripts/search.py "e-commerce launch" --creative-brief -f markdown

Key Stats

  • Humor increases recall 33% (only 33% of ads use it)
  • Color drives 85% purchase decisions
  • Brand recognition +80% with consistent colors
  • UGC: 28% higher engagement, 4x CTR, 50% lower CPA

Platform Quick Specs

PlatformRatioLengthHookStyle Note
TikTok9:1615-60s3sRaw, trending sounds
Instagram Reels9:1615-90s3sPolished-authentic
YouTube16:930s-10m30sHigh production
LinkedIn1:1, 4:530s-2m5sProfessional, value-first
Stories9:1615s1sImmediate hook, swipe CTA

Pre-Production Checklist

  • Brand guidelines reviewed
  • Audience persona confirmed
  • Creative style approved from search results
  • Platform specs verified
  • Success metrics defined
  • Hook in first 3 seconds
  • Sound-off optimized (captions)
  • Mobile-first designed
  • A/B test variables identified

GitHub Repository

majiayu000/claude-skill-registry
Path: skills/creativity

Related Skills

content-collections

Meta

This skill provides a production-tested setup for Content Collections, a TypeScript-first tool that transforms Markdown/MDX files into type-safe data collections with Zod validation. Use it when building blogs, documentation sites, or content-heavy Vite + React applications to ensure type safety and automatic content validation. It covers everything from Vite plugin configuration and MDX compilation to deployment optimization and schema validation.

View skill

creating-opencode-plugins

Meta

This skill provides the structure and API specifications for creating OpenCode plugins that hook into 25+ event types like commands, files, and LSP operations. It offers implementation patterns for JavaScript/TypeScript modules that intercept and extend the AI assistant's lifecycle. Use it when you need to build event-driven plugins for monitoring, custom handling, or extending OpenCode's capabilities.

View skill

sglang

Meta

SGLang is a high-performance LLM serving framework that specializes in fast, structured generation for JSON, regex, and agentic workflows using its RadixAttention prefix caching. It delivers significantly faster inference, especially for tasks with repeated prefixes, making it ideal for complex, structured outputs and multi-turn conversations. Choose SGLang over alternatives like vLLM when you need constrained decoding or are building applications with extensive prefix sharing.

View skill

evaluating-llms-harness

Testing

This Claude Skill runs the lm-evaluation-harness to benchmark LLMs across 60+ standardized academic tasks like MMLU and GSM8K. It's designed for developers to compare model quality, track training progress, or report academic results. The tool supports various backends including HuggingFace and vLLM models.

View skill