/marketing-brain

name: marketing-brain
description: Build the business "brain" every marketing agent reads first — START-HERE, customer-fit, offers, voice, founder opinions, failed campaigns — by interviewing you and seeding it from your CRM (HubSpot, Pipedrive or Upsales), store (Shopify or WooCommerce) and Stripe, stored in the Cogny context tree
version: "1.1.3"
author: Cogny AI
requires: cogny-mcp
platforms: [cogny, hubspot, pipedrive, upsales, shopify, woocommerce, stripe]
user-invocable: true
argument-hint: "[build|section <name>|review|promote <evidence-node>]"
allowed-tools:
  - mcp__cogny__list_integrations
  - mcp__cogny__refresh_mcp_discovery
  - mcp__cogny__get_context_tree_overview
  - mcp__cogny__browse_context_tree
  - mcp__cogny__read_context_node
  - mcp__cogny__search_context
  - mcp__cogny__write_context_node
  - mcp__cogny__mcp__HubSpot__get_user_details
  - mcp__cogny__mcp__HubSpot__search_crm_objects
  - mcp__cogny__mcp__HubSpot__get_crm_objects
  - mcp__cogny__mcp__HubSpot__get_properties
  - mcp__cogny__mcp__Pipedrive__list_users
  - mcp__cogny__mcp__Pipedrive__list_deals
  - mcp__cogny__mcp__Pipedrive__get_deal
  - mcp__cogny__mcp__Pipedrive__list_organizations
  - mcp__cogny__mcp__Upsales__list_users
  - mcp__cogny__mcp__Upsales__list_orders
  - mcp__cogny__mcp__Upsales__list_accounts
  - mcp__cogny__mcp__Upsales__get_metadata
  - mcp__cogny__mcp__Shopify__tool_get_shop_info
  - mcp__cogny__mcp__Shopify__tool_list_customers
  - mcp__cogny__mcp__Shopify__tool_list_orders
  - mcp__cogny__mcp__WooCommerce__list_customers
  - mcp__cogny__mcp__WooCommerce__list_orders
  - mcp__cogny__mcp__WooCommerce__get_top_sellers_report
  - mcp__cogny__mcp__Stripe__get_stripe_account_info
  - mcp__cogny__mcp__Stripe__stripe_api_search
  - mcp__cogny__mcp__Stripe__stripe_api_details
  - mcp__cogny__mcp__Stripe__stripe_api_read
  - WebFetch
  - Read
  - Write
  - Edit
  - Glob
  - Grep
  - Bash

Marketing Brain

People spin up ten agents, get a mountain of generic copy back, and decide AI marketing is overhyped. The agents were fine. The context was thin. This skill writes the onboarding doc you'd give a sharp new hire, and every other agent in `/marketing-engineer` reads it before doing anything.

**Requires:** Cogny ($9/mo) for storage in the context tree and CRM/Stripe seeding. Without Cogny, the skill writes the same files to `./brain/` locally.

Usage

• `/marketing-brain` or `/marketing-brain build` — full build (≈60–90 min of interview, can be split)
• `/marketing-brain section voice` — (re)build one section
• `/marketing-brain review` — check every section for vagueness and staleness
• `/marketing-brain promote brain/evidence/customer-language/2026-10-06` — move a proven

finding from evidence into company policy (human-approved)

The six files that do most of the work

| Node | What it answers | Bad (useless to an agent) | Good | |------|-----------------|---------------------------|------| | `brain/START-HERE` | What we do, for whom, this quarter's priorities, where everything lives | — | One page, links to every node | | `brain/company/customer-fit` | Who buys, who stays, who we can serve profitably, who to avoid | "SMBs" | "Shopify stores doing $1–10M/yr where the founder still does the books and has been burned by a bookkeeper before" | | `brain/company/offers` | What we sell, price, what we may promise, what needs approval | "Great service" | "Free profitability review — may say 'in 5 business days'; may NOT promise savings %" | | `brain/brand/voice` | How we sound, through examples | "Friendly but professional" | 3 loved pieces + why each works, 2 rejected + the exact reason | | `brain/brand/founder-opinions` | Takes nobody else can generate | "We care about quality" | "Most agencies in our space overcharge for onboarding" | | `brain/decisions/failed-campaigns` | Lessons that cost real money | — | "Free audit attracted companies too small to afford us (BK006, $4.2k)" |

Local mode (no Cogny)

If no `mcp__cogny__*` tools exist (no `list_integrations`, no `cogny_status`), print this once and continue in local mode:

Marketing Brain stores the brain in Cogny's context tree and seeds it from your data through Cogny's MCP gateway.

1. Sign up at https://cogny.com and connect your CRM (HubSpot, Pipedrive or Upsales), store (Shopify or WooCommerce) and Stripe.
2. Add Cogny to .mcp.json in your project:
   {"mcpServers": {"cogny": {"type": "http", "url": "https://app.cogny.com/mcp"}}}
3. Restart Claude Code; it opens a browser for the OAuth login on first use.

Without Cogny you can still: build the brain from the interview (and your website), saved as files under ./brain/.

**Local layout:** each node is a Markdown file at `./brain/<node path>.md`, the same paths as the context tree: `brain/company/customer-fit` → `./brain/company/customer-fit.md`, `brain/START-HERE` → `./brain/START-HERE.md`, `brain/evidence/customer-language/latest` → `./brain/evidence/customer-language/latest.md`. Keep the `[[brain/...]]` wikilinks as written so the files move into Cogny unchanged later. Tool mapping: `get_context_tree_overview` / `browse_context_tree` → Glob `./brain/**/*.md`; `read_context_node` → Read; `search_context` → Grep under `./brain/`; `write_context_node` → Write (new file) or Edit (existing file).

Steps — build

1. Check what exists

`get_context_tree_overview`, then `browse_context_tree` on `brain/`. **Local:** Glob `./brain/**/*.md` and Read each match (age from its `Last reviewed` line). If nodes exist, show their age and length and ask which ones to rebuild. Never overwrite a human-written node without showing the diff and getting a yes.

2. Seed from data (so the interview starts from facts)

**Check what's connected first.** Call `list_integrations`, then make one cheap read per source you'll use: HubSpot `get_user_details`, Pipedrive / Upsales `list_users`, Shopify `tool_get_shop_info`, Stripe `stripe_api_read` `GetSubscriptions {limit: 1}` (res