Claims Library Entry
I built a marketing brain you can install in 30 seconds
Kamil Banc introduces a Claude Cowork plugin that turns the desktop app into a trained marketing operator with 12 skills and 5 slash commands, requiring no prompt engineering. The article explains why structured plugin systems outperform prompt libraries and Claude Projects, and walks through installation and usage.
Published March 9, 2026 by Kamil Banc
Lead claim
A single plugin file turns Claude's desktop app into a trained marketing operator with 12 skills and 5 commands.
Atomic Claims
What this article supports
Copy individual claims as needed.
Claim 1 · Source summary
Plugin Turns Claude Into Marketer
Kamil Banc built a plugin file that turns Claude's desktop app into a trained marketing operator.
Claim 2 · Source summary
Twelve Skills, Five Commands
The marketing plugin ships with twelve skills and five slash commands requiring zero prompt engineering.
Claim 3 · Source summary
Cowork Mode Explained
Anthropic's Cowork mode reads files, writes documents, browses the web, and executes multi-step tasks.
Claim 4 · Source summary
Command Orchestrates Multiple Skills
The /audit-page command orchestrates two skill files to deliver one unified five-section page audit.
Claim 5 · Source summary
Skills Are Decision Trees
Skill files act as decision trees with scoring rubrics rather than simple persona prompts.
Evidence
Context behind the claims
Quote
"Giving your team an AI assistant without structured instructions is like hiring a brilliant intern with no onboarding."
Key statistics
12 skills
The plugin bundles twelve skill files across three categories: conversion rate optimisation, content and copy, and SEO and visibility.
5 slash commands
Five one-line commands, including /audit-page and /seo-check, trigger complex marketing workflows inside Claude Cowork.
30 seconds
Installation requires opening Claude Desktop, entering Cowork mode, and dragging the plugin file in, with no configuration or API keys.
30 minutes
Each slash command reportedly replaces what used to be a 30-minute manual marketing process.
Supporting context
The article describes a practitioner-built plugin for Anthropic's Claude desktop app in Cowork mode, distributed via a GitHub repository for paid subscribers. The methodology centers on structured skill files that function as decision trees with specific criteria, scoring rubrics, and output formats, rather than free-form persona prompts. Skills cross-reference one another so commands like /audit-page can chain multiple knowledge files into a single unified deliverable. For marketing practitioners, the approach offers a reproducible way to standardize audits, email sequences, and SEO checks without writing prompts each time. The author positions plugin orchestration as a maturity step beyond prompt libraries and Claude Projects, though the performance claims remain self-reported rather than independently benchmarked.
How to Cite
Use the claim-level citation when you need a precise statement. Use the article or claims-collection citation when you want the wider argument and source context.
Individual Claim
Best when you need to cite one atomic claim directly inside a memo, deck, research note, or AI output.
"[claim text]" (Banc, Kamil, 2026, https://kbanc.com/claims-library/i-built-a-marketing-brain-you-can-install-in-30-seconds)Original Article
Use this when you want to cite the full newsletter article at AI Adopters Club rather than the structured claims page.
Banc, Kamil (2026, March 9, 2026). I built a marketing brain you can install in 30 seconds. AI Adopters Club. https://aiadopters.club/p/marketing-plugin-claude-coworkClaims Collection
Use this when you want to reference the full structured claims collection on this page.
Banc, Kamil (2026). I built a marketing brain you can install in 30 seconds [Structured Claims]. Retrieved from https://kbanc.com/claims-library/i-built-a-marketing-brain-you-can-install-in-30-secondsAttribution Requirements
- Include the author name: Kamil Banc.
- Include the source: AI Adopters Club or the structured claims page.
- Link to the original article or the claims page you used.
- Indicate any edits or transformations if you changed the wording.
Related Reading
More from the library
A structured prompt approach transforms performance reviews into actionable development plans by interviewing managers through six categories. The method prevents common AI pitfalls by collecting complete information before generating recommendations, producing budget-aligned plans in a single session.
5 claims
A detailed analysis of 30 days of ChatGPT and Claude conversations reveals 10 repeating prompt patterns that demonstrate systematic AI use. The author shares specific prompt structures for tasks like email triage, presentation assembly, and workflow documentation, showing how to treat AI as infrastructure rather than a casual tool.
5 claims
AI adoption fails because of habit problems, not training gaps. This practical guide shows how to build an AI reflex muscle in 20 minutes by automating one annoying task. The goal is developing automatic pattern recognition for AI opportunities.
5 claims