Arturo Parada
, , ,

An AI Skill for the Real Estate Asset Management Model

We’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, a packaged set of instructions and reference files that teaches an AI assistant how to operate that specific model on your behalf. The Simple Actual + Forecast DCF 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 Real Estate Asset Management 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 (the format is Anthropic’s), the instructions inside the Skill are largely platform-neutral. You can use the Skill with Claude, where it integrates most natively, especially via the Claude in Excel add-in — but also 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. Some integrations are smoother than others, but the underlying knowledge transfers.AI Skill for the Real Estate Asset Management Model

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 three user roles the Simple Actual + Forecast DCF Model serves, the mechanics behind the actual-vs-forecast blending logic, and the most common ways analysts get the Current Year boundary wrong.

The result is an AI assistant that can actually operate the model on your behalf, rather than one that talks about held-asset tracking 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 held-asset DCF is one of those exercises where the same spreadsheet serves completely different masters. An asset manager wants a performance verdict: is this deal ahead of the original underwriting or behind? An LP wants to know whether the sponsor is delivering on what they promised, and what the remaining hold would need to return to get back on target. A student wants to understand why substituting actuals for forecast assumptions moves the return numbers the way it does. The model handles all three, but the right outputs and the right framing are different in each case.

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

Role Triage

Before the Skill touches a single input, it asks what role you’re working in. The three it supports:

  • Asset manager / property owner — tracking a held asset against the original underwriting. The Skill populates actuals, calculates the performance delta, and frames the forward IRR.
  • LP / passive investor — assessing sponsor performance mid-hold. The Skill supports re-underwriting the remaining period using your own independent assumptions.
  • Student / educator — working through the blending mechanic. The Skill explains how substituting actuals for forecast assumptions moves the return numbers and why.

Populating Inputs Conversationally

You describe your property and operating history in plain language — the Skill handles the translation into model inputs. It steps through property details, analysis period, original forecast assumptions, and per-year actuals for every closed period. Nothing is written to the workbook until you’ve reviewed and confirmed what it’s staging.

Cell F12 — the Current Year — gets confirmed before anything else. This is the cell that draws the line between historical actuals and forward forecast. One year off in either direction and the blending logic shifts silently across every combined output. No red cells, no broken formulas — just wrong numbers. The Skill locks this down first.

Catching Common Mistakes

Four errors show up repeatedly on this model, and none of them announce themselves: F12 set to the wrong year, shifting the actual-vs-forecast boundary without any visible warning; blank actuals in closed years, which the blending formula treats as zero rather than missing; the forecast block edited to reflect what actually happened, which erases the original underwriting as a benchmark; and formula cells in the combined cash flow rows overwritten with hard numbers, which silently corrupts the IRR inputs. The Skill checks for all four before you get to outputs.

Framing Outputs in Your Role

Results are always shown as a paired comparison: Original Underwriting alongside Combined (Actual + Forecast), covering IRR, Equity Multiple, and average Free and Clear Return. The spread between the two IRRs is the signal. An asset manager gets that framed as a performance verdict — ahead, behind, or on track. An LP sees what the remaining hold would need to return to hit the original target. A student gets a walkthrough of the mechanical change.

Operating Contexts (Chat / Cowork and 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.

A Note on the Underlying Model

The Simple Actual + Forecast DCF Model is an unlevered, property-level annual DCF for tracking held CRE assets against original underwriting. It blends per-year actuals from closed periods with forecast assumptions for the remaining hold, producing two return views side by side: what the original underwriting projected, and what the current actual+forecast picture shows. Outputs are unlevered IRR, Equity Multiple, and average Free and Clear Return. No debt, no waterfall, no tax. See the model post for the full walkthrough.

Video Walkthrough: Using the AI Skill

The video below walks through the full AI-assisted workflow: uploading the model, selecting your role, populating forecast assumptions and historical actuals from an investment summary, and reading the combined vs. original underwriting output in the context of a real asset management decision.

Before You Use This AI Skill with the Simple Actual + Forecast DCF Model

A couple of notes 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 — and ideally some prior exposure to held-asset tracking, DCF analysis, and NOI underwriting. It’s best suited to graduates of our A.CRE Accelerator real estate financial modeling program, or analysts comfortable building models from scratch. AI assistants make mistakes; the Skill assumes an analyst on the other side who can catch them. Treat its output the way you’d treat work from a sharp junior analyst — useful, fast, and always verified before it goes into a memo.
  • License: The Skill is distributed under the A.CRE software license, with full terms in the LICENSE.txt file included in the bundle. The short version: use it for personal, organizational, and client-facing analysis; don’t resell or redistribute it. Use by an AI assistant operating on your behalf is expressly permitted — that’s the whole point.

Download the Simple Actual + Forecast DCF 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 below). Paid contributors receive a new download link via email each time either is updated.

Proceed to Download Page

Frequently Asked Questions about the AI Skill for the Real Estate Asset Management Model

When you ask Claude a general question about asset management, it draws on training data. An AI Skill is different — it’s a packaged instruction file that loads alongside your specific Excel model and tells the AI exactly how that workbook is structured: which cells to write, what the outputs mean, what roles the model serves, and which errors to catch. It’s model-specific knowledge, not general knowledge.

Claude integrates Skills most natively, especially via the Claude in Excel add-in. But the SKILL.md file inside the bundle can be uploaded to ChatGPT, Gemini, or any other capable AI assistant alongside the Excel model, and the assistant can follow the same playbook. Some integrations are smoother than others, but the underlying knowledge transfers.

It starts by establishing your role — asset manager, LP, or student. Then it steps through inputs conversationally: property details, analysis period, original forecast assumptions, and per-year actuals for each closed year. Before writing anything, it confirms cell F12 (the Current Year). It flags any of the four common errors that would silently corrupt outputs, stages the values for your review, and once confirmed, presents the combined vs. original underwriting comparison framed for your specific role.

Yes. In Claude in Excel, the Skill reads from and writes to the open workbook directly — no upload required. In a standard Claude conversation, you upload the Excel file and the Skill operates it via code execution. The role logic, input steps, and output framing are identical either way.

The Skill is paired with v1.0 of the A.CRE Simple Actual + Forecast DCF Model. If you’re on a different version, check the Version tab before running it — cell addresses may not align. The Skill flags a version mismatch automatically on load.

Yes. The Skill and the model are versioned and updated together. Paid contributors receive a new download link via email each time either file is updated.

Start by verifying F12, checking that actuals are filled in for all closed years, and confirming no formula cells in the combined rows have been overwritten. The Skill is designed to catch most issues before they reach outputs, but it’s not infallible. Review its work the same way you’d review any analyst’s work. If you spot a genuine bug, send it along and it’ll be addressed in the next update.

Upload the .skill file to Claude the same way you’d upload any other file. Claude reads the SKILL.md inside and follows it. For step-by-step setup, see our practical guide to Claude Skills. For other AI assistants, upload the SKILL.md file alongside the Excel model.

Version Notes: AI Skill

Version 1.1

  • Initial release of the AI Skill for the A.CRE Simple Actual + Forecast DCF Model
  • Paired with v1.0 of the Excel model
  • Supports both Chat / Cowork (upload the .xlsx and operate via code execution) and Claude in Excel (operate the live workbook directly)
  • Includes 3-role triage (asset manager, LP/investor, student/educator), conversational input population for forecast assumptions and per-year actuals, and mistake-catching across the Current Year boundary, blank actuals, forecast-editing errors, and formula cell overwrites
  • Portable to other capable AI assistants (ChatGPT, Gemini, etc.) via the SKILL.md file

About the Author: Arturo is a Financial Analyst at A.CRE. With a background as a Mechanical Engineer, he further honed his skills by obtaining a Master’s Degree in Industrial Maintenance. His experience spans over a decade as a university professor, and he has dedicated 3 years to the real estate domain, holding an instrumental role in administering the A.CRE Accelerator real estate financial modeling program and helping its members master complex modeling solutions.

Arturo's passion lies in building, improving, and analyzing real estate financial models. Arturo loves being with his family and climbing mountains in his free time. You can contact Arturo from his LinkedIn page.

Contact Arturo

by