An AI Skill for the A.CRE Hotel Valuation 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 Hotel Valuation 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 Hotel Valuation Model post, which walks through the model itself, tabs, 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.
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, the full nine-tab structure of the Hotel Valuation Model, every input cell and how it flows downstream, the four user roles the model serves, and the most common ways hotel underwriting goes wrong before you ever get to a return number.
The result is an AI assistant that can actually navigate and operate the model on your behalf, rather than one that talks about hotel finance 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
Hotel underwriting is one of the more complex asset classes in real estate financial modeling. The operating statement follows the USALI structure — rooms revenue flows through departmental expenses to GOP, then management fees, fixed expenses, EBITDA, FF&E reserve, and NOI — and building that correctly across a nine-tab model requires knowing exactly where each input lives and how it flows downstream. The same model serves four very different users: a buyer trying to price a deal, a sponsor trying to structure a JV promote, an LP deciding whether to commit capital, and a lender stress-testing coverage ratios. The Skill handles all four, triage first.
Role Triage
Before the Skill touches a single input, it asks which decision you’re making:
- Acquisitions analyst / buyer — evaluating whether to bid and at what price. The Skill leads with levered and unlevered IRR, equity multiple, going-in and exit cap rate, and per-key basis, then frames the “what can I pay” question by flexing the purchase price against a target return.
- Sponsor structuring a JV or syndication — setting the promote and hurdle structure. The Skill populates the Waterfall tab after the full proforma is complete and surfaces LP IRR, GP IRR, and GP profit across the four promote tiers.
- LP / capital allocator — assessing whether the deal is a good passive investment. The Skill leads with LP IRR, LP equity multiple, and average cash-on-cash, then stresses occupancy, ADR, and exit cap to show how the preferred return holds up in a soft scenario.
- Lender / debt underwriter — sizing or stress-testing the acquisition loan. The Skill leads with minimum DSCR, minimum debt yield, and LTV, identifies the worst coverage year, and walks through adjusting loan structure to find a coverage-compliant solution.
Populating Inputs Conversationally
You can share an offering memorandum, an STR comp set report, a trailing twelve-month operating statement, or describe the property in plain language — the Skill pulls the relevant assumptions and stages them for the model. Two things it always confirms before writing anything: occupancy, ADR, and ADR growth are entered per year across the row for each hold-period column, not as single values. And the purchase price method (cell C16 on the Summary tab) must be set first, because it determines which of the three pricing inputs — discount rate, going-in cap rate, or custom price — is the live cell. Populating the wrong pricing cell produces a silently wrong purchase price.
VBA Mode Toggles – A Critical Note
Several of the model’s mode toggles — Static vs. Custom on the Other Expenses and Other Operating Departments tabs, and Simple vs. By-Year on the F&B tab — are VBA click-events. The AI cannot fire these macros. When a different mode is needed, the Skill will tell you exactly which toggle cell to click in Excel and wait for your confirmation before continuing. This is not a limitation to work around — it’s the correct workflow for a macro-enabled model.
Catching Common Mistakes
Six errors show up repeatedly on this model. Entering occupancy, ADR, or ADR growth as a single number when the model expects a value for each hold-period year across the row — the per-year array is what drives the proforma engine. Populating the wrong pricing cell for the active purchase price method, which silently misprices the deal. Writing into or deleting part of the sensitivity data table (K38:N46 on the Summary tab), which breaks the fragile Excel data table and cannot be rebuilt outside Excel. Misreading an active toggle mode before populating expenses or F&B revenue. Treating the FF&E reserve or management incentive fee as ordinary operating expenses, when they sit in specific USALI positions downstream of GOP. And reading a franchise fee rate before confirming which flag is active on the relevant toggle cell.
Framing Outputs in Your Role
For a buyer, the headline is the levered IRR and equity multiple against the target hurdle, with the unlevered IRR alongside to separate asset quality from leverage contribution. For a sponsor, the focus shifts to the waterfall — whether the LP clears the preferred return before promote kicks in, and how GP economics scale across the four tiers. For an LP, the downside scenario is as important as the base case — the Skill stresses the exit cap and occupancy ramp to show how the LP preferred return holds. For a lender, the headline is the minimum DSCR across all hold-period years, because the worst year is the binding year.
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 populate inputs 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. In both environments, VBA toggles must be clicked by the user and the sensitivity table requires Excel to recalculate. 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 Hotel Valuation Model is an annual, single-property acquisition underwriting tool for existing stabilized and value-add hotel opportunities. It builds a USALI-structured operating proforma from occupancy and ADR inputs, covers departmental revenue and expense across rooms, F&B (up to five outlets), and other operating departments, outputs NOI through management fees and FF&E reserve, and produces unlevered and levered IRR, equity multiple, DSCR, debt yield, and a four-tier LP/GP waterfall. The model does not cover ground-up development, monthly periods, portfolios, or mid-hold refinancing. It is currently in beta. See the model post for the full walkthrough and tutorials.
Note: This AI Skill is built for beta v2.1 of the model. If you’re on an older version, confirm key cell positions before running the Skill — notably v2.0 added the sensitivity analysis and v2.02 fixed the data table exit cap reference. The model is macro-enabled (.xlsm) — macros must be enabled in Excel for the mode toggles to function.
Before You Use This AI Skill with the Hotel Valuation 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 prior exposure to hotel underwriting, USALI operating statements, and hospitality capital markets. It’s best suited to graduates of our A.CRE Accelerator real estate financial modeling program, or analysts comfortable building hotel pro formas 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.
Macros required. The model is macro-enabled (.xlsm). Macros must be enabled in Excel for the mode toggle buttons to function correctly. The AI cannot fire VBA macros — it will tell you which button to click and wait for your confirmation.
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 Hotel 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 hotel models sell for $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. 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.
Frequently Asked Questions about the AI Skill for the A.CRE Hotel Valuation Model
Version Notes – AI Skill
beta v2.1
- Initial release of the AI Skill for the A.CRE Hotel Valuation Model
- Paired with beta v2.1 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 (acquisitions analyst/buyer, sponsor structuring a JV, LP/capital allocator, lender/debt underwriter), conversational input population from OMs, STR reports, and T-12 statements, and mistake-catching across per-year occupancy and ADR entry, purchase price method toggle sequencing, sensitivity data table integrity, VBA mode toggle state, USALI FF&E and incentive fee positioning, and franchise fee flag confirmation
- Portable to other capable AI assistants (ChatGPT, Gemini, etc.) via the SKILL.md file
