skills/creator-style-mimic/SKILL.md
Analyze and mimic the writing style, hooks, voice, and patterns of successful creators from your Airtable database and content frameworks. Match creator voice based on audience, platform, and content type. Use when testing different voices, creating content in a specific influencer's style, or finding your unique voice through analysis.
npx skillsauth add kitfunso/omniskill creator-style-mimicInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Analyze and replicate the unique writing styles of successful creators based on proven patterns from your Airtable data. This skill helps you understand what makes different voices work and apply those patterns to your own content.
Creator style isn't random—it's a set of identifiable patterns:
This skill extracts these patterns from successful creators and applies them to your content.
Based on your Airtable data and framework analysis:
Voice Characteristics:
Hook Preferences:
Title Patterns:
Content Structure:
Emoji Usage: Minimal. Occasional 🔥, 🤖, ⚡ for emphasis
Platform Voice:
Example (Jack Roberts Style):
I Automated My Entire Content Pipeline with Claude Code (And It's Insane)
Here's what I built:
→ Daily project scanner (runs automatically)
→ Framework matcher (applies viral hooks)
→ Platform formatter (outputs for Twitter, LinkedIn, etc.)
→ Content database (7,540 ideas generated)
Time investment: 6 hours building
Time saved: 10 hours/week ongoing
The breakdown:
[Technical architecture explanation with screenshots]
ROI: Break-even in week 1, infinite returns after
Want the code? Link in comments.
Voice Characteristics:
Hook Preferences:
Title Patterns:
Content Structure:
Emoji Usage: Moderate. Uses for visual breaks and categories
Platform Voice:
Example (Riley Brown Style):
Build a FULL Content System With Claude Code With 3 SCREENSHOTS!
By the end of this, you'll have a working content generator that:
✓ Analyzes your projects automatically
✓ Generates viral hooks using proven frameworks
✓ Outputs formatted posts for every platform
No coding experience needed.
Here's the full guide:
Step 1: Create your project scanner
[Screenshot of CLAUDE.md file]
Copy this template into a file called CLAUDE.md:
[Template code]
Step 2: Add framework library
[Screenshot of frameworks folder]
Download my framework library here:
[Link to templates]
Step 3: Connect to Claude Code
[Screenshot of Claude Code interface]
Run this command:
[Command]
That's it! You now have a content system.
Want the complete setup guide with all templates?
Link in bio 👉
Voice Characteristics:
Hook Preferences:
Title Patterns:
Content Structure:
Emoji Usage: Minimal. Focused on 💰, 📈, 🎯
Platform Voice:
Example (Codie Sanchez Style):
Stop building content manually.
Here's the deal:
You're spending 10+ hours weekly on what should take 1 hour.
The fix: Framework-driven AI generation.
What I built:
→ Agent that applies proven viral hooks
→ Library of 123 tested frameworks
→ Automated output for all platforms
Result: 10 hours back. Every week. Forever.
ROI: Infinite.
Here's how to build it:
1. Clone this repo
2. Add your API key
3. Run the script
That's it.
Cost: $0 if you use Claude Code locally.
Stop wasting time. Start this today.
Link: [URL]
Each creator has signature word patterns:
Jack Roberts:
Riley Brown:
Codie Sanchez:
Jack Roberts: Medium complexity with technical clarity
The agent scans project files every morning, extracts recent changes, matches them to framework patterns, and generates 5-10 hook variations for each update.
Riley Brown: Simple, instructional, one step per sentence
First, create a new file. Name it CLAUDE.md. Paste the template code. Save the file. You're done with step one.
Codie Sanchez: Ultra-short. Punchy. Direct.
Stop manual content creation. Use frameworks. Save 10 hours weekly. Here's how.
Jack Roberts: Tech Demo Hook Pattern: "I {automated/built} {thing} with {tool} ({reaction})"
I automated my debugging workflow with Claude Code (and it's honestly wild)
Riley Brown: Tutorial Hook Pattern: "Build a FULL {thing} with {tool} with {number} {input}!"
Build a FULL AI Agent with Claude Code with 2 PROMPTS!
Codie Sanchez: Business Hook Pattern: "Stop {action}. Do this instead"
Stop paying $50/mo for content tools. Build your own in 2 hours.
| Content Type | Recommended Creator Style | |--------------|--------------------------| | Technical tutorial | Jack Roberts | | Beginner guide | Riley Brown | | Business opportunity | Codie Sanchez | | Build demo | Jack Roberts or Riley Brown | | Contrarian take | Jack Roberts or Codie Sanchez | | Step-by-step | Riley Brown | | ROI/metrics focus | Jack Roberts or Codie Sanchez |
Vocabulary:
Sentence Structure:
Hook:
Jack Roberts Layer:
def apply_jack_roberts_voice(content):
- Add technical specificity
- Include metrics and numbers
- Use "Here's the thing" or "Let me show you"
- Moderate enthusiasm (wild, insane, honestly)
- Focus on automation and efficiency
- End with practical CTA
Riley Brown Layer:
def apply_riley_brown_voice(content):
- Simplify language (beginner-friendly)
- Add "full guide" promise
- Break into clear numbered steps
- Offer templates/downloads
- Use "No {barrier} needed" reassurance
- Visual language (screenshots, see, look)
Codie Sanchez Layer:
def apply_codie_sanchez_voice(content):
- Shorten all sentences dramatically
- Start with command (Stop, Start, Do)
- Lead with dollar amounts or ROI
- Remove qualifiers and hedging
- Add urgency
- Direct action CTA
Example: Jack Roberts + Codie Sanchez (Technical demo with business urgency)
Stop wasting 10 hours/week on manual content.
I built an automated system with Claude Code.
Here's the breakdown:
→ Project scanner (automated)
→ Framework matcher (123 viral patterns)
→ Platform formatter (Twitter, LinkedIn, etc.)
Time to build: 6 hours
Time saved: 10 hours/week
ROI: Infinite after week 1
The architecture:
[Technical details in Jack Roberts style]
Cost: $0 with local Claude Code setup.
Build this today: [Link]
When to mix:
Same Content, 3 Creator Styles:
Original (Your Voice): "I created a content generation system using AI and frameworks that saves time."
Jack Roberts Version: "I Automated My Content Pipeline with Claude Code (Results Are Wild)
Built an agent that applies 123 proven frameworks to project data.
Result: 10 hours/week saved, 89% quality approval rate.
Here's the technical breakdown:"
Riley Brown Version: "Build a FULL Content System With Claude Code (Step-by-Step Guide!)
By the end, you'll have an automated content generator.
No coding needed!
Here's exactly how to build it:
Step 1: [...]"
Codie Sanchez Version: "Stop Manual Content Creation.
Built this in 6 hours. Saves 10 hours/week. Forever.
The system: → Auto-scans projects → Applies viral frameworks → Outputs formatted posts
ROI: Infinite.
Build it: [Link]"
Metrics to compare:
Insights:
When applying creator style:
Vocabulary:
Sentence Structure:
Hook:
Content Structure:
Overall Authenticity:
Step 1: Analyze Your Natural Patterns
Step 2: Test Creator Styles
Step 3: Synthesize Your Unique Voice
Example Synthesis:
My Voice =
Jack Roberts' technical specificity
+ Riley Brown's accessibility
+ Codie Sanchez's directness
+ My unique Claude Code expertise
= Technical tutorials with business urgency for technical founders
Recommended Stack:
Workflow:
Raw content idea
↓
Select target audience
↓
Match audience to creator style (Jack/Riley/Codie)
↓
Apply creator's vocabulary and structure
↓
Add creator's signature hooks and phrases
↓
Platform-specific polish if needed
↓
Ready to publish in creator's voice
See /references/ for:
creator_profiles_full.json - Complete creator analysis from Airtable datavocabulary_fingerprints.md - Word frequency analysis per creatorsentence_structure_guide.md - Sentence pattern breakdownvoice_mixing_examples.md - 20+ examples of combined creator voicesdevelopment
Weekly engineering retrospective. Analyzes commit history, work patterns, and code quality metrics with persistent history and trend tracking. Team-aware: breaks down per-person contributions with praise and growth areas. Use when asked to "weekly retro", "what did we ship", or "engineering retrospective". Proactively suggest at the end of a work week or sprint.
development
Systematically QA test a web application and fix bugs found. Runs QA testing, then iteratively fixes bugs in source code, committing each fix atomically and re-verifying. Use when asked to "qa", "QA", "test this site", "find bugs", "test and fix", or "fix what's broken". Proactively suggest when the user says a feature is ready for testing or asks "does this work?". Three tiers: Quick (critical/high only), Standard (+ medium), Exhaustive (+ cosmetic). Produces before/after health scores, fix evidence, and a ship-readiness summary. For report-only mode, use /qa-only.
development
Report-only QA testing. Systematically tests a web application and produces a structured report with health score, screenshots, and repro steps — but never fixes anything. Use when asked to "just report bugs", "qa report only", or "test but don't fix". For the full test-fix-verify loop, use /qa instead. Proactively suggest when the user wants a bug report without any code changes.
testing
Eng manager-mode plan review. Lock in the execution plan — architecture, data flow, diagrams, edge cases, test coverage, performance. Walks through issues interactively with opinionated recommendations. Use when asked to "review the architecture", "engineering review", or "lock in the plan". Proactively suggest when the user has a plan or design doc and is about to start coding — to catch architecture issues before implementation.