Gtm System Architecture logo

Gtm System Architecture

Organization
LeadMagic
gtm-system-architecture

Design a complete GTM operating system — revenue model, data model, operating model, growth model, and GTM model per WbD's 6-model framework. Use when designing a GTM system from scratch, auditing an existing one, or aligning teams around a unified revenue architecture. Triggers on: "GTM system", "revenue architecture", "operating model", "GTM model", "revenue system", "go-to-market design", "GTM audit", or any request about designing how GTM works end-to-end.

Overview

PublisherLeadMagic
Repositorygtm-skills
Skill namegtm-system-architecture
Stars
72
Forks
18
Bundled files
3
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 3 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by LeadMagic on GitHub. Read the source before you install it.

Installation

Install the Gtm System Architecture AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/LeadMagic/gtm-skills/tree/main/skills/analytics/gtm-system-architecture
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/LeadMagic/gtm-skills.git /tmp/gtm-skills
mkdir -p .claude/skills
cp -r /tmp/gtm-skills/skills/analytics/gtm-system-architecture .claude/skills/gtm-system-architecture
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Gtm System Architecture in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Gtm System Architecture on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Gtm System Architecture is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

GTM System Architecture

Overview

A GTM system is the operating system underneath your revenue. It's the answer to "how does money flow through this company?" — not "what tactics are we running this quarter?"

Winning by Design's GTM Index framework scores 1-10 across six interconnected models. Most companies break because they optimize one model while neglecting the others. This skill designs all six as one unified system.

When to Use

  • "Design our GTM system"
  • "Audit our revenue architecture"
  • "Build a GTM operating model"
  • "Our GTM is fragmented — fix it"
  • "Align sales, marketing, and CS"
  • "Design how revenue flows"

Authoritative Foundations

  • Winning by Design GTM Index — six models (Revenue, Data, Math, Operating, Growth, GTM). 1-10 scoring per model. Average across 1000+ companies benchmarked.
  • Winning by Design Bowtie — revenue is a continuous loop: acquire → retain → expand. Not a funnel that ends at "closed won."
  • SiriusDecisions Demand Waterfall — demand flows through stages with defined handoffs and conversion metrics.

Step-by-Step Process

Phase 1: The Six Models (WbD GTM Index)

Score each 1-10, then identify the weakest link:

1. Revenue Model — "Do we know how we make money?"

  • Pricing clarity, packaging, discount authority, expansion model.
  • Weak: "We charge whatever the customer agrees to."
  • Strong: "Standard tiers, defined discount rules, clear expansion path."

2. Data Model — "Can we answer basic questions about our business?"

  • CRM hygiene, pipeline data, conversion rates, attribution.
  • Weak: "We don't know our MQL→SQL conversion rate."
  • Strong: "Every deal has stage, source, close date, and MEDDIC dimensions."

3. Math Model — "Do unit economics work?"

  • LTV:CAC, payback period, CAC by channel, churn rates, NRR.
  • Weak: "We don't track CAC by channel. We think churn is around 3%."
  • Strong: "CAC payback is 8 months, LTV:CAC is 4:1, NRR is 115%."

4. Operating Model — "Is there a documented process someone could follow?"

  • Sales process stages, playbooks, enablement, handoff documentation.
  • Weak: "Reps sell however they want. No two deals look the same."
  • Strong: "Stage definitions with Goals and Exit Criteria. Playbook documented. New reps ramp in 90 days."

5. Growth Model — "Do we know which channels work and at what cost?"

  • Channel mix, CAC by channel, channel ROI, experimentation velocity.
  • Weak: "We try things and see what sticks."
  • Strong: "Paid search CAC is $X, content CAC is $Y, outbound CAC is $Z. We allocate budget to highest-ROI channels."

6. GTM Model — "Is the whole system connected?"

  • Sales-marketing-CS alignment, shared metrics, unified customer journey.
  • Weak: "Marketing generates MQLs sales ignores. CS doesn't know what was sold."
  • Strong: "Unified Bowtie. Shared metrics across functions. Single customer view from first touch through renewal."

Phase 2: Bowtie Architecture

Revenue doesn't end at "closed won." It continues through retention and expansion. Design the Bowtie:

Awareness → Education → Selection → Onboarding → Adoption → Expansion → Renewal
[Marketing]   [Marketing]  [Sales]   [CS]       [CS]      [CS/Sales]   [CS]

Each stage has: owner (which team), goal (what success looks like), handoff criteria (when to pass to next stage), and metrics (how to measure).

Phase 3: System Integration

The six models don't operate independently:

  • Revenue Model ↔ Math Model: Pricing choices determine unit economics. Lower price → lower ARPU → longer CAC payback. Know the tradeoff.
  • Data Model ↔ Operating Model: If CRM data is unreliable, the process can't be inspected. Fix data before adding process.
  • Growth Model ↔ GTM Model: Marketing channels produce demand. Sales converts it. CS retains it. If any link breaks, the system fails.
  • Weakest link principle: The lowest-scoring model caps the entire system. A 9/10 Revenue Model with a 3/10 Data Model is a 3/10 system.

Phase 4: Implementation Roadmap

Don't fix all six at once. Sequence by impact:

  1. Fix the Math Model first. If unit economics don't work, nothing else matters. Know your CAC, LTV, churn, payback.
  2. Fix the Data Model. Clean CRM, define stages, establish reporting.
  3. Design the Operating Model. Document processes, build playbooks.
  4. Optimize the Growth Model. Test channels, measure CAC per channel.
  5. Refine the Revenue Model. Pricing, packaging, discount rules.
  6. Align the GTM Model. Cross-functional alignment, shared metrics.

Output Format

GTM system design: six-model assessment (current scores + target scores), Bowtie architecture with ownership per stage, weakest-link analysis, implementation roadmap with 90-day priorities, and measurement dashboard.

Quality Check

  • All six models scored 1-10 with evidence
  • Weakest link identified (lowest scoring model)
  • Bowtie architecture with owner, goal, handoff criteria per stage
  • Implementation roadmap (not trying to fix everything at once)
  • Shared metrics across functions (not siloed KPIs)
  • Re-assessment cadence (quarterly GTM Index check)

Common Pitfalls

  1. Optimizing one model in isolation. Improving the Operating Model without fixing the Data Model means adding process to bad data. Fix data first.

  2. No Bowtie. Treating revenue as a pipeline that ends at "closed won" ignores the 70%+ of lifetime value that comes after the sale.

  3. Self-assessment without evidence. "I think our Math Model is a 7" without actually calculating LTV:CAC. Score with data, not feelings.

  4. Trying to fix everything at once. Six-model overhauls take 12-18 months. Sequence one or two per quarter.

  5. GTM model owned by one function. GTM alignment requires sales, marketing, and CS leadership in the same room with shared metrics.

Execution Artifacts

  • references/framework-notes.md — named frameworks, citation anchors, and operating assumptions
  • templates/output-template.md — copy-paste deliverable structure for the user
  • scripts/check-output.py — local checklist validator for required sections This skill includes lightweight artifacts the agent can load on demand: Use the artifacts when the user asks for an implementation-ready deliverable, a repeatable workflow, or a quality check rather than generic advice.

Related Skills

  • gtm-metrics: Model measurement and dashboards
  • pipeline-management: Operating model execution
  • marketing-strategy: Growth model design
  • sales-team-building: Operating model staffing

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Gtm System Architecture AI skill do?

Design a complete GTM operating system — revenue model, data model, operating model, growth model, and GTM model per WbD's 6-model framework. Use when designing a GTM system from scratch, auditing an existing one, or aligning teams around a unified revenue architecture. Triggers on: "GTM system", "revenue architecture", "operating model", "GTM model", "revenue system", "go-to-market design", "GTM audit", or any request about designing how GTM works end-to-end.

Why use Gtm System Architecture on TypingMind?

Because you install it once and use it with any model. Gtm System Architecture is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Gtm System Architecture in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/LeadMagic/gtm-skills/tree/main/skills/analytics/gtm-system-architecture. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Gtm System Architecture?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Gtm System Architecture?

As many as you like. As long as a model supports skills, you can use Gtm System Architecture with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Gtm System Architecture AI skill free?

Yes. It is published on GitHub by LeadMagic under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇