, ,

An AI Skill for the A.CRE Ground Lease Valuation Model

I’ve been working on a project to make our library of Excel models AI-ready. The idea is straightforward – pair every A.CRE Excel model with an AI Skill for CRE, a packaged set of instructions and reference files that teaches an AI assistant how to operate that specific real estate model on your behalf. The Ground Lease Valuation Model is among the first models in the library to ship with one, and this post introduces the AI Skill we built to accompany it.

Think of this as a sister post to the Ground Lease Valuation Model post, which walks through the model itself — sections, inputs, outputs, and mechanics. If you haven’t seen that one yet, start there. This post focuses specifically on the AI Skill: what it does, how it works, and how to use it.

  • While we refer to these as Claude Skills or AI Skills, the instructions inside the Skill are largely platform-neutral. You can use the Skill with Claude in other platforms such as ChatGPT, Gemini, or any other capable AI assistant. You can also use these in Claude in Excel, ChatGPT in Excel, etc.

What is an AI Skill?

If you’re new to the concept, an AI Skill is a packaged set of instructions and reference files that an AI assistant loads alongside your file. It teaches the assistant things it wouldn’t otherwise know — in this case, every input cell, every output, the five user roles the Ground Lease Valuation Model serves, the modeling discipline behind the analysis, and the most common ways analysts get ground lease math wrong.

The result is an AI assistant that can actually operate the model on your behalf, rather than one that talks about ground leases in the abstract.

For a primer with a short video tutorial, see our practical guide to Claude Skills.

What the AI Skill Does for You

A ground lease is one of those instruments where the analyst’s role completely changes the math that matters. The landowner cares about one set of numbers. The improvements owner cares about a different set. The acquirer cares about returns. The lender cares about coverage. The model serves all five roles — but feed an analyst the wrong outputs for their role, and the analysis ends up worse, not better.

So the Skill handles a few jobs for you that you’d otherwise be doing manually.

Role Triage

Before touching the file, the Skill asks which side of the deal you’re on:

  • Landowner — valuing the leased fee position
  • Improvements owner — valuing the leasehold (improvements on someone else’s land)
  • Sizing the payment — negotiating a ground rent that works
  • Acquirer — buying an existing leased fee position
  • Lender — underwriting a loan against either side

Each path has its own inputs, its own outputs, and its own interpretation. The Skill knows the difference.

Populating Inputs Conversationally

You can paste in a ground lease summary, upload an OM, or attach an appraisal — the Skill pulls the relevant terms (start date, payment, escalation method, lease length, and so on) and stages them for the model. Nothing writes to the workbook until you confirm.

Catching Common Mistakes

Stabilized NOI entered net of ground rent instead of gross. A discount rate set above the underlying property cap rate (it should usually sit below). Reversion growth rates that look fine for ten years and absurd over eighty. Loan-to-cost confused with loan-to-value. The Skill flags these before they make it into the analysis.

Framing Outputs in Your Role

For the landowner, the Skill leads with PV and the implied cap rate. For the improvements owner, it frames the leasehold as the fee simple value minus the present value of the ground lease obligation. For the acquirer, it leads with unlevered IRR and equity multiple — and then layers in the levered counterparts if debt is in play. Same model, different lens.

Operating Contexts (Chat or Claude in Excel)

The Skill works in two environments. You can upload the Excel file to a Claude conversation and have Claude operate the model via code execution. Or — if you’re using Claude in Excel — operate the model live with Claude reading and writing to the workbook directly. The Skill handles both, with the mechanics adjusted under the hood. And as noted earlier, the Skill is also portable to other AI assistants, though the integration may be lighter.

Before Using This AI Skill with the Ground Lease Valuation Model

An important note worth surfacing before you download.

Who this Skill is for. This Skill is built for real estate professionals with a strong grasp of financial modeling, ground lease valuation, and ideally a graduate of our A.CRE Accelerator real estate financial modeling program.

AI assistants make mistakes; the Skill assumes the professional on the other side will catch them. Treat its output the way you’d treat work from a sharp junior analyst; useful, fast, but always verified before it goes into a memo.

A Note on the Underlying Model

Briefly: the model values both sides of a ground lease (leased fee and leasehold) and computes returns for an acquirer of the ground. It’s built on a single worksheet so it can be used standalone or inserted as a module into a larger property-level model. It handles ground leases up to 99 years, four escalation methods (None, % Inc., $ Inc., Custom), and an optional debt layer for levered returns. The full walkthrough is on the ground lease model page.

Note: This AI Skill is built for v2.33 of the model. If you’ve got an older version, the Skill will flag the mismatch — but you’ll want to grab the current version of both the model and the Skill for the cleanest experience.

Video Walkthrough — Using the AI Skill with the Ground Lease Valuation Model

The video below walks through the full AI-assisted workflow: uploading the model, the role triage, populating inputs from an uploaded lease document, and interpreting the outputs in the language of the investment decision.

Download the Ground Lease Valuation Model + AI Skill

To make this model accessible to everyone, it is offered on a “Pay What You’re Able” basis with no minimum (enter $0 if you’d like) or maximum (your support helps keep the content coming – typical real estate valuation models sell for $100 – $300+ per license). Just enter a price together with an email address to send the download link to, and then click ‘Continue’. If you have any questions about our “Pay What You’re Able” program or why we offer our models on this basis, please reach out to either Mike or Spencer.

Your download includes three files: the Excel model, the AI Skill (.skill file), and a short README explaining how to use them together.

We regularly update both the model and the AI Skill (see version notes). Paid contributors receive a new download link via email each time either is updated.


Frequently Asked Questions about the AI Skill for the Ground Lease Valuation Model

An AI Skill is a packaged set of instructions and reference files that an AI assistant loads alongside your model. It teaches the assistant things it wouldn’t otherwise know — in this case, every input cell, every output, the five user roles served by the Ground Lease Valuation Model, and the modeling discipline behind the analysis. The result is an AI assistant that can actually operate the model on your behalf rather than one that talks about ground leases in the abstract.

While we refer to these as “Claude Skills” (the format is Anthropic’s), the instructions inside the Skill are largely platform-neutral. You can use the Skill with ChatGPT, Gemini, or any other capable AI assistant — just upload the SKILL.md file alongside the Excel model and the assistant can follow the same playbook. Claude integrates Skills most natively (especially through the Claude in Excel add-in), but the underlying knowledge transfers.

Four main jobs. First, it triages your role — landowner, improvements owner, payment-sizer, acquirer, or lender — and routes the conversation accordingly. Second, it populates inputs conversationally from documents you upload (leases, OMs, appraisals), always confirming before writing. Third, it interprets outputs in the frame of your specific investment decision. Fourth, it catches common mistakes — Stabilized NOI entered net of ground rent, discount rates set above the underlying cap rate, reversion growth rates that produce unrealistic terminal values, and similar pitfalls.

Yes. The Skill is built for two environments. You can upload the Excel file to a Claude conversation and have Claude operate the model via code execution, or you can open the model live in Excel and operate it via the Claude in Excel add-in. The Skill adapts to either context, with the mechanics adjusted under the hood.

The AI Skill is built for v2.33 of the Ground Lease Valuation Model. If you use an older version, the Skill will surface the mismatch and recommend grabbing the current version. Cell addresses and named ranges differ across versions, so for the cleanest experience stay on v2.33.

Yes. Paid contributors to the model receive a new download link via email each time the model — or the AI Skill — is updated. The Skill follows its own version notes structure (see below) alongside the model’s.

AI responses may contain errors. The Skill is built for real estate professionals who already have a deep understanding of financial modeling, and any output should be verified by the analyst before being acted on. If you find the Skill making the same mistake repeatedly, please reach out — every Skill in the library is iterative, and reader feedback drives the improvements.

For Claude, the .skill file can be uploaded directly to a project or conversation. For other AI assistants, the .skill file is a standard zip — extract it and provide the SKILL.md file (and supporting reference files) alongside the Excel model. For a step-by-step walkthrough including installation, see our practical guide to Claude Skills.


Version Notes — AI Skill

Version 2.33

  • Initial release of the AI Skill for the Ground Lease Valuation Model
  • Paired with v2.33 of the Excel model
  • Supports both upload-to-chat and Claude in Excel operating contexts
  • Includes the five-role triage workflow, input validation against sanity ranges, and mistake-catching guidance
  • Portable to other capable AI assistants (ChatGPT, Gemini, etc.) via the SKILL.md file

About the Author: Spencer Burton is Co-Founder and CEO of CRE Agents, an AI-powered platform training digital coworkers for commercial real estate. He has 20+ years of CRE experience and has underwritten over $30 billion in real estate across top institutional firms.

Spencer also co-founded Adventures in CRE, served as President at Stablewood, and holds a BS in International Affairs from Florida State University and a Masters in Real Estate Finance from Cornell University.