My 11-Skill AI Content Team (Built in Claude Code)
Episode
28 min
Read time
2 min
Topics
Startups, Leadership, Artificial Intelligence
AI-Generated Summary
Key Takeaways
- ✓Lookalike Content Scaling: Feed Claude Code a data dump of your top-performing posts — the system analyzes the top 30% by engagement, extracts structural and emotional patterns, then generates new content ideas mapped to those winning formulas. Without performance data, it analyzes the full dataset. Works with other creators' content if you lack your own archive.
- ✓Self-Improving Feedback Loop: Build a companion app that captures every piece of content the system produces, then manually input performance metrics monthly. Run a review skill that reads all performance data and automatically rewrites the underlying skill files — meaning the content system improves itself each month based on what actually performed well or poorly.
- ✓Audience Profile Over ICP: A content audience profile differs from a standard ICP. It maps vocabulary the audience uses versus avoids, emotional registers, validation hooks, and specific content formats they react to — all grounded in engagement data. One profile per platform per persona produces more targeted output than a single generic customer profile.
- ✓Orchestrator Skill Architecture: Build one master orchestrator skill that calls all other skills automatically. When activated, it loads the correct audience profile, writing style, and prior research, then executes tasks across the full system. This eliminates manual navigation between tools and enables a fully autonomous mode where content is generated overnight without human input.
- ✓Post Enrichment Layer: After generating a first draft, run a separate enrichment skill that appends platform-specific modules — data points, case studies, executive quotes, or narrative examples — sourced from external research. Each enriched post logs its enrichment source, word count, hook pattern type, and originating talking point file, creating a traceable content production record.
What It Covers
A marketer builds an 11-skill AI content system in Claude Code, structured across five layers: audience profiling, writing style generation, research and ideation, multi-platform drafting, and a self-improving feedback loop that updates all skills monthly based on real content performance data.
Key Questions Answered
- •Lookalike Content Scaling: Feed Claude Code a data dump of your top-performing posts — the system analyzes the top 30% by engagement, extracts structural and emotional patterns, then generates new content ideas mapped to those winning formulas. Without performance data, it analyzes the full dataset. Works with other creators' content if you lack your own archive.
- •Self-Improving Feedback Loop: Build a companion app that captures every piece of content the system produces, then manually input performance metrics monthly. Run a review skill that reads all performance data and automatically rewrites the underlying skill files — meaning the content system improves itself each month based on what actually performed well or poorly.
- •Audience Profile Over ICP: A content audience profile differs from a standard ICP. It maps vocabulary the audience uses versus avoids, emotional registers, validation hooks, and specific content formats they react to — all grounded in engagement data. One profile per platform per persona produces more targeted output than a single generic customer profile.
- •Orchestrator Skill Architecture: Build one master orchestrator skill that calls all other skills automatically. When activated, it loads the correct audience profile, writing style, and prior research, then executes tasks across the full system. This eliminates manual navigation between tools and enables a fully autonomous mode where content is generated overnight without human input.
- •Post Enrichment Layer: After generating a first draft, run a separate enrichment skill that appends platform-specific modules — data points, case studies, executive quotes, or narrative examples — sourced from external research. Each enriched post logs its enrichment source, word count, hook pattern type, and originating talking point file, creating a traceable content production record.
Notable Moment
The system includes a fully autonomous mode where Claude Code runs the entire content pipeline overnight — pulling research, generating drafts across LinkedIn, Substack, and X, and saving outputs — so the user arrives each morning to completed content without having initiated a single prompt.
Episode Transcript
I gave Claude Code 51 of my Substack posts, and in five minutes, it told me exactly why some of my content works, why some of it doesn't, and then it generated an infinite number of new ideas that map to my winning formula. Now that's just one skill of a much bigger content system that I've been building over the last number of months. It's an entire AI content team built in cloud code. It's actually 11 skills across five different layers of content. It can research your audience, analyze what content works, draft posts for LinkedIn newsletter, YouTube transcripts, and then it can actually improve itself every single month. On this episode, I'm going to give you a look over my shoulder on how I use Cloud Code to create content, how I use my content team, and I'm going to give you one of the best skills for free. Let's get into that and more on this episode of Marketing Against the Grain. Here's a quick word from HubSpot. HubSpot helped Tumblr solve a big problem. They needed to move fast to produce trending content, but their marketing team was stuck waiting on engineers to code every single email campaign. Now they use HubSpot's customer platform to email real time trending content to millions of users in just seconds. The impact? Three times more engagement, double the content creation. Wanna move faster like Tumblr? Visit hubspot.com. So we are going to give a look over my shoulder as I use my AI content team to create content. Now it's going to be awesome. So what is this? This is really for people who wanna start to see the possibility of cloud code. And if you are a system thinker, a system thinker, how you can use cloud code to be your super weapon, how you can use cloud code to supercharge anything that you're doing in work if you can think about how to build systems with it and in it. And this system is all about content. So I'm gonna give you a quick visual of the system that I'm going to bring you through today. This is over on my Substack for people who want to check it out. And so this is the system we're gonna go through today. The little starred one here is what I'm gonna give you all for free. And so it has an orchestrator skill. So the orchestrator skill is going to actually use all the other skills, which makes it really easy to use the system. You can kinda just dive with the orchestrator skill and ask it to do things, and it goes and uses all of the other skills for you. It makes using these systems really, really easy. You can build a content audience profile, which basically you wanna figure out who you're creating the content for, build a profile, and make sure all of the content is tailored for that person. The system does …
Get the full transcript (5,518 words) + summary by email — free
One-time email with the complete transcript and AI summary of this episode. No account needed.
One email, no spam. We’ll also show you what SignalCast does.
You just read a 3-minute summary of a 25-minute episode.
Get Marketing Against the Grain summarized like this every Monday — plus up to 2 more podcasts, free.
Pick Your Podcasts — FreeKeep Reading
More from Marketing Against the Grain
I Spend $400K/Day on Meta Ads. Here's What's Working Right Now
Sep 10 · 32 min
The Startup Ideas Podcast
AI marketing Masterclass: From beginner to expert in 60 minutes
Feb 9
More from Marketing Against the Grain
The death of the CMO
Sep 8 · 34 min
The AI Breakdown
What To Build First With Claude Design
Apr 20
Books, tools, and gear mentioned in this episode
SignalCast may earn commission on purchases via these links.
Tools
- Claude CodeRecommended
by Anthropic
“A marketer builds an 11-skill AI content system in Claude Code, structured across five layers: audience profiling, writing style generation, research and ideation, multi-platform drafting, and a self-improving feedback loop.”
company
“SPONSORS: HubSpot”
More from Marketing Against the Grain
We summarize every new episode. Want them in your inbox?
I Spend $400K/Day on Meta Ads. Here's What's Working Right Now
The death of the CMO
Turn Every Comment Into a Lead - Automate DMs with Claude
Using Codex to build a Research Dashboard/System
Claude vs. Human Marketer: Which Is Actually Better?
Similar Episodes
Related episodes from other podcasts
The Startup Ideas Podcast
Feb 9
AI marketing Masterclass: From beginner to expert in 60 minutes
The AI Breakdown
Apr 20
What To Build First With Claude Design
How I AI
Apr 13
Claude Cowork 101: How to automate your workday without touching code | JJ Englert (Tenex)
The AI Breakdown
Mar 18
How to Use Agent Skills
How I AI
Feb 23
“I haven’t written a single line of front-end code in 3 months”: How Notion’s design team uses Claude Code to prototype
Explore Related Topics
This podcast is featured in Best Marketing Podcasts (2026) — ranked and reviewed with AI summaries.
Read this week's Startups & Product Podcast Insights — cross-podcast analysis updated weekly.
You're clearly into Marketing Against the Grain.
Every Monday, we deliver AI summaries of the latest episodes from Marketing Against the Grain and 192+ other podcasts. Free for one show.
Start My Monday DigestNo credit card · Unsubscribe anytime