An AI Skill for the A.CRE Mixed-Use Development Model: Condo and Retail
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 Mixed-Use Development Model: Condo and Retail 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 Mixed-Use Development 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 ten-tab structure of the Mixed-Use Development Model, every input cell and how it flows downstream, the five user roles the model serves, and the most common ways mixed-use development underwriting goes wrong before you ever get to an IRR.
The result is an AI assistant that can actually navigate and operate the model on your behalf, rather than one that talks about mixed-use development 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 Mixed-Use Development Model is an expanded version of the Condo Development Model, so if you’re familiar with that one, much of this will feel familiar. The key difference is the optional retail component, and the mechanics around it are worth understanding before you start populating the model.
The retail module is off by default and is toggled from the ControlRoom tab. When it’s on, the retail budget is carved out of the existing development budget, not added on top of it. This is the single most common misunderstanding on this model: turning retail on does not increase total project cost. It reallocates a portion of the existing budget. If you expect the opposite, your numbers will look wrong in ways that aren’t immediately obvious.
The Skill handles the full analysis from first input to final return, across five distinct user roles.
Role Identification
Before the Skill touches a single input, it asks which decision you’re making:
- Developer / sponsor — evaluating whether the project pencils. The Skill leads with levered IRR and total profit, surfaces the unlevered IRR as the deal-quality read, and flags absorption as the dominant risk driver.
- JV sponsor structuring a partnership — sizing the promote and hurdle structure. The Skill confirms the IRR vs. equity multiple hurdle basis first, populates the Waterfall tab, and surfaces LP and GP IRR alongside how the promote shifts as hurdles and split percentages change.
- LP / equity investor — assessing the passive position. The Skill leads with LP IRR and equity multiple, confirms whether the preferred return is cleared, and stresses the absorption pace to show how LP economics hold in a slower sell-out scenario.
- Construction lender — sizing or stress-testing the loan. The Skill surfaces total loan commitment including interest reserve, actual LTC versus target, and how the cash sweep percentage drives repayment through unit closings. Pre-sale coverage from the Buyer Deposit Tracker is also surfaced as the primary credit support.
- Student / Accelerator member — learning the mechanics. The Skill walks through condo sell-out logic, the interest reserve circularity resolved by the Recalibrate LTC macro, and how changing a draw curve’s steepness demonstrates that timing is a cost.
Populating Inputs
You can share a GC budget, a sales comps summary, retail LOIs, a JV term sheet, or describe the project in plain language — the Skill pulls the relevant assumptions and stages them for the model. A few things it always confirms before writing:
The retail toggle must be confirmed before any retail inputs are touched — the Skill asks whether this is a true mixed-use deal or a condo-only run. The loan fee input on the Summary tab (cell C48) is entered as a dollar amount, not a percentage — a common source of confusion since C47 is the derived fee percentage. The millage rate for property taxes is entered as mills per thousand dollars of assessed value, not a decimal. And the floor SF grid on the CondoInputs tab is checked for red cells — any floor where allocated square footage exceeds the floor’s gross SF is flagged before any other inputs are written.
The Recalibrate LTC Button
After any change to costs, timing, or financing assumptions, the construction loan must be re-sized by clicking the Recalibrate LTC button on the Summary tab. The AI cannot fire this VBA macro. When inputs change, the Skill tells you to click the button and waits for your confirmation before reading any returns. The model shows a red warning banner across all ten tabs when the loan is out of sync. The Skill always checks the LTC_Test cell before surfacing any output.
Catching Common Mistakes
Eleven errors show up repeatedly on this model. Not recalibrating the loan after an input change — the single most consequential mistake. Expecting the retail toggle to add cost when it actually reallocates from the existing budget. The loan fee entered as a percentage instead of a dollar amount. The property tax millage rate entered as a decimal instead of mills per thousand. A sell-out absorption pace that implies closings before construction completes. The waterfall hurdle basis left on IRR when the term sheet uses equity multiple hurdles. Writing into formula or cross-sheet cells. Treating Custom disbursement as permanent when it’s fully reversible. Entering more than three retail tenants when the RetailInputs tab has exactly three columns — model the three largest and note the omission. The budget category subtotal cap on four categories that only sums the first nine line items — note that total project cost in the Summary is unaffected, but the category subtotal will look understated. And floor SF over-allocation showing as a red cell before returns are read.
Framing Outputs
For a developer, the headline is levered IRR and profit, with the unlevered IRR alongside to separate deal quality from financing contribution, and the condo gain and retail gain broken out if retail is on. For a JV sponsor, the focus is the LP/GP split across the three waterfall tiers and whether the deal actually clears Tier 2 before the promote becomes real. For an LP, the priority is whether the preferred return is cleared in both the base case and a stress scenario. For a construction lender, the key numbers are total loan commitment including interest reserve, actual LTC versus target, and repayment timing through the cash sweep.
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, the Recalibrate LTC button must be clicked by the user in Excel after input changes — the VBA macro cannot be triggered by the AI. 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 Mixed-Use Development Model: Condo and Retail is a monthly-period, ground-up development tool for projects combining for-sale condominium and optional retail. It takes a line-item development budget, a unit program and stacking plan, a condo sell-out absorption schedule, up to three retail tenant leases, a construction loan with a cash sweep, and an optional buyer deposit tracker to produce unlevered and levered IRR, equity multiple, and total profit at the project level, plus a three-tier LP/GP partnership waterfall. The retail component is off by default and toggled from the ControlRoom tab. The model does not cover for-rent residential, stabilized asset acquisitions, mezzanine debt, or portfolios. The model is macro-enabled (.xlsm). See the model post for the full walkthrough and video tutorials.
Note: This AI Skill is built for v3.6 of the model. If you’re on an older version, confirm key cell positions before running the Skill — notably v3.0 introduced the buyer deposit module and the per-tab recalibration warnings, and v3.5 made several formula corrections to the deposit and retail sale cash flows. The model is macro-enabled (.xlsm) — macros must be enabled in Excel for the Recalibrate LTC button to function.
Before You Use This AI Skill with the Mixed-Use Development 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 for-sale condo development, mixed-use construction financing, and development partnership structures. It’s best suited to graduates of our A.CRE Accelerator real estate financial modeling program, or analysts comfortable building development 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.
Macros required. The model is macro-enabled (.xlsm). Macros must be enabled in Excel for the Recalibrate LTC button to function. The AI cannot run this macro — it will tell you when to click it and wait for your confirmation before reading any returns.
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 Mixed-Use Development Model: Condo and Retail + 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 DCF 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. 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 the AI Skill for the A.CRE Mixed-Use Development Model: Condo and Retail
Version Notes – AI Skill
v3.6
- Initial release of the AI Skill for the A.CRE Mixed-Use Development Model: Condo and Retail
- Paired with v3.6 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 5-role identification (developer/sponsor, JV sponsor, LP/equity investor, construction lender, student/Accelerator member), input population from GC budgets, retail LOIs, sales comps, and JV term sheets, retail toggle confirmation, and mistake-catching across the Recalibrate LTC step, retail budget reallocation logic, loan fee dollar vs. percentage entry, millage rate convention, sell-out vs. construction timing, waterfall hurdle basis, floor SF over-allocation, budget category subtotal cap, and three-tenant limit
- Portable to other capable AI assistants (ChatGPT, Gemini, etc.) via the SKILL.md file
