Expansion Opportunities logo

Expansion Opportunities

Community
davekilleen
expansion-opportunities

Use when reviewing customer accounts for evidence-backed expansion hypotheses based on current usage, product fit, and expressed needs. Not for renewal strategy or negotiation; use renewal-prep.

Overview

Publisherdavekilleen
RepositoryDex
Skill nameexpansion-opportunities
Stars
481
Forks
130
Bundled files
Instructions only
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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

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

Installation

Install the Expansion Opportunities 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.
  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/davekilleen/Dex.git /tmp/Dex
mkdir -p .claude/skills
cp -r /tmp/Dex/packages/dex-agent-plugin/skills/_available/customer-success/expansion-opportunities .claude/skills/expansion-opportunities
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Expansion Opportunities 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 Expansion Opportunities 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 Expansion Opportunities 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.

When to use

Use for a portfolio or named-account review when the requester wants possible upsell, cross-sell, or seat-expansion opportunities grounded in account evidence and a customer-expressed need. Confirm the account scope and review as-of date before scanning.

Do not use this skill to edit CRM records, create pipeline commitments, contact a customer, quote pricing, promise an expansion, or decide commercial strategy. Not for renewal negotiation or a health-score decision; use renewal-prep or health-score for those jobs.

Inputs and source discipline

  1. Establish account identity, scope, and as-of date. Record each source, source date, date checked, unit/currency, and account identifier. Prefer current customer statements and signed entitlements, then CRM/account facts, product telemetry, support records, and dated internal notes. Do not merge conflicting accounts by name alone.
  2. Keep four evidence lanes separate:
    • account evidence: observed product, seat, usage, contract, or organizational facts;
    • expressed need: a dated customer request, pain point, or desired outcome, quoted or cited;
    • product fit: a source-backed mapping from that need to an available product capability;
    • speculation: an untested hypothesis, never presented as customer intent.
  3. Show potential value only when price, quantity, currency, and calculation basis are sourced and comparable. Otherwise write unknown and explain the missing input; never invent potential value, likelihood, budget, percentage, owner, or urgency.

Method

  1. Work read-only and deduplicate account records before ranking. Preserve account-level source references and label whether each statement is observed, expressed, fit-checked, or speculative.
  2. For each candidate, test product fit against a dated, authoritative capability or entitlement source. A usage gap can be evidence for investigation but is not an expressed need. If the capability or eligibility is not verified, mark fit unknown.
  3. Classify the candidate as upsell, cross-sell, or seat expansion only when the account evidence supports that category. Rank by evidence completeness and sourced timing signals, not by an invented probability. Treat any suggested next step as a recommendation for human review.
  4. Calculate an aggregate only when all included values share a documented unit, currency, period, and basis. If any value is unknown or incomparable, report the aggregate as unavailable rather than filling the gap.

Truth and uncertainty rules

Use observed for account evidence directly supported by a source, inferred for a fit interpretation, unknown for missing or unverified need/fit/value, stale for evidence outside the relevant freshness or as-of period, and contradictory when sources disagree. Keep speculation visibly separate from evidence, state confidence, and never infer intent from silence or usage alone. Never invent dates, metrics, owners, intent, money, percentages, causes, status, or evidence. Recommendations are not human decisions.

Output contract

Return a review containing:

  • account scope, as-of date, source register, source dates, and account identifiers;
  • one row per candidate with separate account evidence, expressed need, product fit, and speculation fields;
  • sourced potential value and calculation basis, or explicit unknown/unavailable value;
  • category, evidence completeness, confidence, stale inputs, unknowns, and contradictions;
  • human-review questions and non-binding recommendations, with no invented pipeline total; and
  • a clear statement of what was not checked or cannot be concluded.

Safety and write boundaries

Remain read-only by default. Do not change CRM, account pages, opportunities, pricing, forecasts, or customer records. If a CRM change, outreach, quote, pricing action, or other commercial action is requested, preview the exact target, fields/content, audience, and side effects; redact secrets or unapproved personal/confidential content; wait for explicit confirm from the authorized human owner; then perform only that approved action. A recommendation never authorizes a human or commercial decision.

Verification and recovery

Read back account identifiers, evidence citations, product-fit references, and any value formula. Reconcile duplicate accounts, category counts, units, currency, period, and aggregate totals; fail closed on mismatches. If a source or CRM read fails, preserve the review, mark the affected candidate unknown or blocked, record the failure, and rerun after refresh. Never silently merge accounts or turn speculation into a CRM fact.

Frequently asked questions

What does the Expansion Opportunities AI skill do?

Use when reviewing customer accounts for evidence-backed expansion hypotheses based on current usage, product fit, and expressed needs. Not for renewal strategy or negotiation; use renewal-prep.

Why use Expansion Opportunities on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/davekilleen/Dex/tree/main/packages/dex-agent-plugin/skills/_available/customer-success/expansion-opportunities. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Expansion Opportunities?

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 Expansion Opportunities?

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

Is the Expansion Opportunities AI skill free?

It is published on GitHub by davekilleen. Check the repository for licensing terms. 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 👇