An AI Skill for the A.CRE Short-Term Rental Acquisition 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 Short-Term Rental Acquisition Model is the latest in that effort, and this post introduces the AI Skill we built to accompany it.

Think of this as a sister post to the Short-Term Rental Acquisition 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, Agent 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 four user roles the Short-Term Rental Acquisition Model serves, the mechanics behind the occupancy and ADR revenue engine, and the most common ways STR underwriting goes wrong before you ever get to a return number.

The result is an AI assistant that can actually operate the model on your behalf, rather than one that talks about short-term rental underwriting 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

Short-term rental underwriting is harder than it looks. Revenue isn’t a stabilized rent — it’s occupancy × ADR × 365, with a year-by-year curve that requires real comp support from AirDNA, PriceLabs, or host history. Operating expenses run far higher than long-term rentals once you account for cleaning, platform and management fees, furnishing reserves, and insurance. And the same model serves completely different masters: a buyer trying to decide whether to acquire, an LP evaluating whether to commit capital, a lender stress-testing the loan, and a broker needing to present a credible range of outcomes. The Skill handles all four, but the right inputs, the right outputs, and the right framing differ 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 which decision you’re making:

STR acquirer / sponsor — deciding whether to buy and at what price. The Skill surfaces unlevered and levered IRR and equity multiple as the headline pair, along with whether leverage is helping or hurting at the current terms.
Equity investor / LP — evaluating whether projected returns justify the capital commitment. The Skill leads with levered IRR, equity multiple, and average cash-on-cash, and flags whether the return story leans on reversion versus operating income.
Lender / debt underwriter — sizing or stress-testing the loan. The Skill leads with minimum DSCR rather than average DSCR — STR’s seasonal revenue volatility means an acceptable average can mask a sub-1.0x trough year. Debt yield by year rounds out the credit picture.
Broker / advisor — building an underwriting to advise a buyer or price a listing. The Skill surfaces the full return picture alongside all three sensitivity tables, so the range of outcomes is defensible, not just the base case.

Populating Inputs Conversationally

You can paste in a deal summary, share AirDNA or PriceLabs comp data, describe the property and proposed terms in plain language, or upload a case study document — the Skill pulls the relevant terms and stages them for the model. One step it always confirms: occupancy and ADR are entered as year-by-year arrays across the hold period, not single values. Getting that right matters because it’s how the model projects the ramp-up from acquisition through stabilization.

The Skill also confirms the comp basis behind the occupancy and ADR inputs before writing anything. Unrealistic occupancy or ADR is the single most common error in STR underwriting — revenue equals occupancy × ADR × 365, so an inflated either number inflates every downstream return. The Skill asks where the numbers came from.

Catching Common Mistakes

Six errors show up repeatedly on this model. Unrealistic occupancy or ADR without a comp basis. Underweighting STR-specific operating expenses — cleaning, platform and management fees, furnishing reserves, and insurance together commonly run 35–50%+ of revenue, far above long-term rental ratios. Typing over the top-block formula mirrors instead of the blue source cells in the cash-flow grid below, which means values appear to change but formulas immediately recalculate back. An exit cap rate at or below the going-in yield, which inflates reversion value without explicit justification. Entering a single occupancy or ADR value when the model expects a year-by-year array. And reading the sensitivity tables in a chat session where the data tables have not recalculated — those require Excel to update.

Framing Outputs in Your Role

For a sponsor, the headline is the unlevered and levered IRR pair — the spread between them tells you whether leverage is working for or against the deal at current terms. For an LP, the emphasis shifts to whether the levered IRR is being driven by operating cash flow or by a reversion premium, because those carry different risk profiles. For a lender, the minimum DSCR across all projected years is the binding number. For a broker, the three sensitivity tables — exit cap versus hold period, acquisition price versus exit cap, and interest rate versus LTC — are the presentation tools that turn a point estimate into a defensible range.

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 — the Skill bundle includes a clean copy of the model so no upload is needed to get started. 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 mechanics adjusted under the hood. The sensitivity tables work most reliably in Claude in Excel, where Excel’s native engine handles the data-table recalculation. 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 Short-Term Rental Acquisition Model is an investor-focused tool for underwriting single STR acquisitions. It projects year-by-year revenue from an occupancy and ADR curve, layers STR-specific operating expenses, applies a senior loan, and outputs unlevered and levered IRR, equity multiple, total profit, average cash-on-cash, and per-year DSCR and debt yield. Three built-in sensitivity tables stress-test returns across exit cap versus hold period, acquisition price versus exit cap, and interest rate versus LTC. The model is single-property, annual-frequency, and deal-level — no partnership waterfall, no monthly seasonality, no multi-tranche debt. It is currently in beta. See the model post for the full walkthrough.

Note: This AI Skill is built for beta v1.2 of the model. If you’re on an older version, confirm the key cell positions before using the Skill — notably the returns block and the cash-flow grid.

Short-Term Rental Acquisition Model + AI Skill Video Walkthrough: Using the AI Skill

The video below walks through the full AI-assisted workflow: loading the Skill, selecting your role, populating inputs from a deal case study, and interpreting the return and credit outputs in the context of a real acquisition decision.

Before You Use This AI Skill with the Short-Term Rental Acquisition 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 STR underwriting, operating metrics like ADR and occupancy, and real estate capital markets. It’s best suited to graduates of our A.CRE Accelerator real estate financial modeling program, or analysts comfortable building acquisition 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 informs an investment decision.

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 Short-Term Rental Acquisition 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 development 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, you can contact our support team here.

Your download includes three files: the Excel model, the AI Skill (.skill file), and a short README explaining how to use them together. The Skill bundle includes a clean copy of the model — no upload needed to get started with Claude.

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 An AI Skill for the A.CRE Short-Term Rental Acquisition Model

What is an AI Skill (sometimes called a Claude Skill)?

When you ask Claude a general question about short-term rental underwriting, 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, which roles the model serves, and which errors to catch. It’s model-specific knowledge, not general knowledge.

Does the AI Skill only work with Claude?

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.

What does the AI Skill actually do when I am operating the model?

It starts by establishing your role — acquirer, LP, lender, or broker. Then it collects inputs conversationally: property details, acquisition price, financing terms, and the occupancy and ADR year-by-year curves with confirmation of the comp basis. It checks the exit cap against the going-in yield, confirms operating expenses are not underweighted for an STR, stages the values for your review, and once confirmed, surfaces the return and credit outputs framed for your specific role.

Does the Skill work with Claude in Excel?

Yes. In Claude in Excel, the Skill reads from and writes to the open workbook directly, and the sensitivity tables recalculate natively in Excel. In a standard Claude conversation, the Skill bundle includes a clean copy of the model so no upload is needed to start. The sensitivity tables work most reliably in the live-workbook context since they require Excel to update.

Which version of the model does the Skill work with?

The Skill is paired with beta v1.2 of the Short-Term Rental Acquisition Model. If you are on an older version, confirm the returns block and cash-flow grid cell addresses before running the Skill.

Will I receive updates to the AI Skill?

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

What if the AI Skill gets something wrong?

Start by confirming the occupancy and ADR inputs have a real comp basis, checking that operating expenses are not underweighted for an STR, and verifying you are editing the blue source cells rather than the top-block mirrors. The Skill is designed to catch most issues before they reach outputs, but it is not infallible. Review its work the same way you would review any analyst’s work.

How do I install or use the .skill file?

In claude.ai (or the Claude desktop app), go to Customize > Skills, click “+”, choose “Upload a skill,” and upload the .skill file. Toggle it on — it’s ready to use in any new chat. The bundle includes a clean copy of the model, so no file upload is needed to get started. For other AI assistants, upload the SKILL.md file alongside the Excel model. For a full step-by-step walkthrough with screenshots, see our practical guide to Claude Skills.

Version Notes — AI Skill

beta v1.2

Initial release of the AI Skill for the A.CRE Short-Term Rental Acquisition Model
Paired with beta v1.2 of the Excel model
Supports both Chat / Cowork (Skill bundle includes a clean copy of the model — no upload needed) and Claude in Excel (operate the live workbook directly)
Includes 4-role triage (STR acquirer/sponsor, equity investor/LP, lender/debt underwriter, broker/advisor), conversational input population from deal summaries and AirDNA or PriceLabs comp data, and mistake-catching across occupancy and ADR comp basis, STR opex weighting, mirror-vs-source cell edits, exit cap justification, occupancy/ADR array entry, and sensitivity table recalculation state
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