Customer Expansion Scoring logo

Customer Expansion Scoring

Organization
swan-gtm
customer-expansion-scoring

Use this skill when scoring a paying customer (closed-won account) for expansion. It evaluates product usage depth, persona quality, and expansion headroom to produce an expansion tier with short actionable reasoning. Designed as a sub-skill of your lead-scoring methodology — the parent runs the ACV assessment first and this returns a tier to it.

Overview

Publisherswan-gtm
Repositorygtm-skills
Skill namecustomer-expansion-scoring
Stars
216
Forks
103
Bundled files
1
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.

  • 1 bundled files

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

  • Open source

    Published by swan-gtm on GitHub. Read the source before you install it.

Installation

Install the Customer Expansion Scoring 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/swan-gtm/gtm-skills/tree/main/skills/ariel-cohen/customer-expansion-scoring
  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/swan-gtm/gtm-skills.git /tmp/gtm-skills
mkdir -p .claude/skills
cp -r /tmp/gtm-skills/skills/ariel-cohen/customer-expansion-scoring .claude/skills/customer-expansion-scoring
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Customer Expansion Scoring 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 Customer Expansion Scoring 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 Customer Expansion Scoring 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.

Template placeholders

Replace every {{...}} before enabling. See the setup checklist reference for the full setup list.

  • {{PRODUCT}} — Your product name
  • {{PARENT_SCORING_SKILL}} — The parent lead-scoring skill this returns to (runs ACV assessment before this)
  • {{CRM}} — Your CRM (e.g. HubSpot)
  • {{DEPTH_SIGNALS}} — Your product's REAL usage-depth indicators (see Signal Stack #2 — must be replaced)
  • {{AUTO_CREATED_ARTIFACTS}} — Objects your onboarding auto-creates for every account (excluded from depth)
  • {{FOUNDER_CONTENT}} — Whose LinkedIn content signals post-conversion advocacy (usually a founder)
  • {{TIER_SCALE}} — Tiers, low→high (default: Bronze / Silver / Gold / Diamond)
  • {{INACTIVITY_CAP}} — Inactivity window that caps the tier (default: 30 days → cap at Silver)

Use when the account is a paying customer (Closed Won stage).

Goal: How deeply are they using {{PRODUCT}}, and how much bigger could this account get?

The parent skill ({{PARENT_SCORING_SKILL}}) has already run the ACV assessment and applied the ACV tag. Reference those results here — do not re-research ACV dimensions covered there.


Signal Stack (highest to lowest weight)

Gather all available signals from account memory, product event history, and {{CRM}}.

  1. Meeting — a completed call signals active relationship depth. Extract: topics discussed (expansion, new use cases, additional team members mentioned), questions and objections, action items, attendee roles. A meeting that surfaces new departments, budget conversations, or advanced use cases = strong expansion signal.

  2. Product depth — the real indicators of depth for {{PRODUCT}} are {{DEPTH_SIGNALS}}.

    Reference implementation (an AI GTM platform) used:

    • Integrations/tools connected beyond defaults — each = deliberate setup effort

    • Automations/triggers created beyond the default one — variety and count signal how much the user is actually building on the product

    • Usage credits consumed (volume = active usage)

    • Multiple team members active

    What does NOT count as product depth: {{AUTO_CREATED_ARTIFACTS}} — anything your onboarding auto-creates is present on virtually every account. Do NOT treat these as engagement or power-user signals. Judge depth only by artifacts the customer deliberately built.

  3. Chatbot / support interactions — technical or advanced use-case questions signal active exploration

  4. Website visits (post-signup) — return visits to docs, pricing (plan upgrade signal?), or feature pages

  5. LinkedIn engagement — post-conversion engagement with {{FOUNDER_CONTENT}} signals advocacy or a deepening relationship


Persona Quality

Strong: CRO, VP Sales, Head of Sales, RevOps, GTM Engineer, Growth Lead, CEO (small co), Agency Owner (tune to your buying committee) Weak: Product, Engineering, Finance — requires stronger product signals to compensate Multiple strong personas actively using {{PRODUCT}} = significant positive multiplier for the top tier

Persona quality reflects expansion potential. A VP Sales actively building on {{PRODUCT}} is a more valuable expansion signal than a junior IC doing the same. Always note the persona role in your reasoning.


Expansion Headroom

Assess how much room this account has to grow:

  • Current seat count vs. total relevant org size (from the parent ACV assessment)
  • Teams or divisions not yet using {{PRODUCT}}
  • Growth signals: recent funding, active hiring, new leadership joins
  • Are they approaching credit, usage, or seat limits?

Hard Caps

No product usage signals in the last {{INACTIVITY_CAP}} → cap at the second-lowest tier (churn risk takes priority over expansion scoring). Note explicitly: "[window] inactivity — capped, churn risk flagged."

Senior Stakeholder Exception (overrides seat-count limitations): If the registered user is a very senior stakeholder (VP, SVP, C-suite, or equivalent Director-level executive) AND the company is high-quality ($10M+ funded OR 100+ employees OR well-known brand with a clear motion in your market), score the second-highest tier regardless of team size or seat count. Seniority + company quality is itself a strong expansion signal — this person can unlock budget and teammates.


Tier Definitions

(Defaults shown for a Bronze/Silver/Gold/Diamond scale — remap to {{TIER_SCALE}}.)

Diamond: Deep product usage (multiple integrations connected, multiple deliberate automations active, multi-user) + high ACV potential (per parent assessment) + clear expansion headroom. This account could 3–5x in ARR.

Gold: Meaningful usage (1–2 integrations connected, active workflows running) + medium-to-high ACV potential + some expansion headroom. Nurture toward deeper adoption.

Silver: Active customer but shallow usage (minimal integrations, few automations, limited engagement) OR low ACV potential with limited expansion ceiling.

Bronze: Barely active — minimal or no usage in recent weeks, no integrations, low ACV potential. Prioritize re-engagement or churn prevention before expansion.


Output

Produce: tier + 2–3 sentence reasoning (usage depth, persona quality, expansion headroom, ACV ceiling from parent). Then return to {{PARENT_SCORING_SKILL}} and continue its remaining steps.


What good looks like

A great output is a tier plus two-to-three sentences a CSM can act on immediately, citing all four dimensions: usage depth (deliberately built artifacts only), persona quality, expansion headroom, and the ACV ceiling from the parent assessment. Inactive accounts get capped with the churn risk flagged explicitly, and senior-stakeholder exceptions are called out as such.

Mediocre looks like: a tier derived from seat count alone, depth credited for onboarding auto-created objects, ACV re-researched when the parent already assessed it, or essay-length reasoning nobody reads.

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 Customer Expansion Scoring AI skill do?

Use this skill when scoring a paying customer (closed-won account) for expansion. It evaluates product usage depth, persona quality, and expansion headroom to produce an expansion tier with short actionable reasoning. Designed as a sub-skill of your lead-scoring methodology — the parent runs the ACV assessment first and this returns a tier to it.

Why use Customer Expansion Scoring on TypingMind?

Because you install it once and use it with any model. Customer Expansion Scoring 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 Customer Expansion Scoring in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/swan-gtm/gtm-skills/tree/main/skills/ariel-cohen/customer-expansion-scoring. 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 Customer Expansion Scoring?

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 Customer Expansion Scoring?

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

Is the Customer Expansion Scoring AI skill free?

Yes. It is published on GitHub by swan-gtm 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 👇