An AI Skill for the A.CRE Advanced Mortgage Amortization Module
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, a packaged set of instructions and reference files that teaches an AI assistant how to operate that specific model on your behalf. The Advanced Mortgage Amortization Module 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 Advanced Mortgage Amortization Module post, which walks through the module itself, features, 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, every input cell, the four user roles the module serves, the three mode toggles that must be set before anything else is entered, and the most common ways loan modeling goes wrong before you ever get to a payment number.
The result is an AI assistant that can actually operate the module on your behalf, rather than one that talks about mortgage amortization 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
The Advanced Mortgage Amortization Module handles four distinct use cases, and the right inputs and the right outputs differ meaningfully across each one. A borrower wants monthly debt service, total interest cost, and the balloon balance at sale or refinance. A lender wants Lender Yield (APR), duration, and average life — three numbers that answer whether the loan’s economics hit the required yield target. An assumption buyer needs the remaining schedule from a current balance, not the original, and the contractual payment that’s already been set, not a freshly computed one. A modeler just needs a clean schedule to drop into a larger acquisition or development model. The Skill handles all four, triage first.
Role Triage
Before the Skill touches a single input, it asks which decision you’re making:
- Borrower / sponsor — analyzing debt service on a contemplated loan. The Skill leads with monthly payment, payoff balance at the end of the term, and total interest cost.
- Lender / debt analyst — checking the economics of a loan being quoted. The Skill leads with Lender Yield (APR), duration, and average life, and explains why the APR is always higher than the stated coupon when a loan fee is involved.
- Assumption buyer — modeling an assumed loan’s remaining schedule. The Skill collects the current balance (not the original), the remaining term (not the original), and the actual contractual monthly payment, and flags the single most common error: using original figures instead of current ones.
- Modeler — generating a clean schedule to embed in a larger property or portfolio model. The Skill outputs the monthly schedule and annual rollup in the format the module was designed to provide as a drop-in debt component.
Setting the Three Mode Toggles First
Before any loan terms are entered, the Skill sets three mode toggles that determine which cells are live and how the module behaves. New Loan vs. Loan Assumption (cell E4) determines whether the module builds a fresh schedule or models an assumed loan’s remaining cash flows. Fixed vs. Variable (cell F8) determines whether the annual rate is a single entry or a forward benchmark curve entered month by month. Static vs. Dynamic payments (cell F17) determines whether debt service stays constant or recalculates each period to ensure exact amortization. Setting these in the wrong order, or leaving them at defaults that don’t match the actual loan, means the module is structuring the wrong loan before a single dollar amount is entered.
Populating Inputs Conversationally
You can share a term sheet, describe the loan terms verbally, or paste in a commitment letter — the Skill pulls the relevant details and stages them for the module. Two things it always confirms: term and amortization are different inputs (a 10-year term on a 30-year amortization means entering 120 and 360 respectively, not 10 and 30), and the lender spread for variable-rate loans is entered in basis points, not as a decimal. The module ships with a forward SOFR curve already populated for variable-rate analysis.
Catching Common Mistakes
Six errors show up repeatedly on this module. Confusing term (F16) with amortization period (F14) — one sets the balloon date, the other sets the payment calculation base, and conflating them produces a wrong schedule silently. Expecting Lender Yield (APR) to equal the coupon rate — it won’t when there’s a loan fee, and the Skill explains the gap before a lender is surprised by it. Entering amortization and term in years instead of months. Entering the lender spread as a decimal instead of basis points. For loan assumptions, using original balance and original term instead of current balance and remaining term. For variable-rate loans, leaving the benchmark curve column empty, which produces a wrong schedule with no error flag.
Framing Outputs in Your Role
For a borrower, the headline is the monthly payment and the balloon payoff — those two numbers answer whether the debt service fits the cash flow and whether the exit works. For a lender, the headline is Lender Yield (APR) alongside duration and average life, because those three numbers together answer the yield target question and the rate-risk question in one pass. For an assumption buyer, the headline is the remaining schedule and the payoff, so the economics of assuming the in-place debt can be compared directly to new financing. For a modeler, the headline is the schedule itself — clean, formula-intact, and ready to drop in.
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 module via code execution — the Skill bundle includes a clean copy of the module so no upload is needed to get started. Or, if you’re using Claude in Excel, operate the module live with Claude reading and writing to the workbook directly. The Skill handles both, with 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 Module
The Advanced Mortgage Amortization Module is a debt-terms-in, metrics-out tool. It takes loan amount, rate, amortization, term, IO period, and day-count method and produces a full monthly schedule plus four headline metrics: Lender Yield (APR), balloon payoff, duration, and average life. It handles new originations and loan assumptions, fixed and variable rates, four day-count conventions (30/360, Actual/Actual, Actual/360, Actual/365), and static versus dynamic payments. It is a module designed to run standalone or to be dropped into a larger property or portfolio model — it does not size loans, compute DSCR or debt yield, or model prepayment penalties. See the module post for the full walkthrough.
Note: This AI Skill is built for v3.2 of the module. If you’re on an older version, confirm key cell positions before running the Skill — notably v3.0 introduced the Loan Assumption feature and the Variable Rate module.
Before You Use This AI Skill with the Advanced Mortgage Amortization Module
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 commercial mortgage mechanics, loan structuring, and debt analysis. It’s best suited to graduates of our A.CRE Accelerator real estate financial modeling program, or analysts comfortable building debt schedules 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 a financing 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 Advanced Mortgage Amortization Module + AI Skill
To make this module 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 Excel modules 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 module, the AI Skill (.skill file), and a short README explaining how to use them together. The Skill bundle includes a clean copy of the module — no upload needed to get started with Claude.
We regularly update both the module 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 Advanced Mortgage Amortization Module
Version Notes – AI Skill
Version 3.2
- Initial release of the AI Skill for the A.CRE Advanced Mortgage Amortization Module
- Paired with v3.2 of the Excel module
- Supports both Chat / Cowork (Skill bundle includes a clean copy of the module — no upload needed) and Claude in Excel (operate the live workbook directly)
- Includes 4-role triage (borrower/sponsor, lender/debt analyst, assumption buyer, modeler), three-mode-toggle sequencing, conversational input population from term sheets and loan documents, and mistake-catching across term vs. amortization confusion, APR vs. coupon distinction, months vs. years entry, basis-points spread entry, loan assumption original-vs-current figures, and variable-rate curve state
- Portable to other capable AI assistants (ChatGPT, Gemini, etc.) via the SKILL.md file
