An AI Skill for the A.CRE Condominium Development 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 Condominium Development 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 Condominium 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, every input cell across all seven tabs, the four user roles the model serves, the critical Recalibrate LTC step that must happen before any return is reliable, and the most common ways condo development underwriting goes wrong before you ever get to an IRR.
The result is an AI assistant that can actually operate the model on your behalf, rather than one that talks about condo 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
Condo development underwriting has a few mechanics that set it apart from other asset classes, and that a general-purpose AI will get wrong without specific instruction. Revenue doesn’t come from stabilized rent; it comes from unit closings, driven by pre-sales and monthly absorption pace against a sell-out timeline. The construction loan doesn’t amortize from cash flow; it gets paid down through a cash sweep as units close. And every time you change a cost, a timing input, or a financing assumption, the loan has to be recalibrated to the target LTC before any return number is meaningful. The Skill understands all of this.
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, then surfaces the unlevered IRR as the deal-quality read and the cost/revenue gain-on-sale for the margin picture.
- JV sponsor structuring a partnership: sizing the promote and hurdle structure. The Skill populates the Waterfall tab after the full proforma is complete, confirms the IRR vs. equity multiple hurdle basis first, and surfaces LP and GP IRR alongside how the promote shifts as the 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 checking the loan. The Skill surfaces actual LTC versus target LTC, peak drawn balance, interest carry, and how the cash sweep percentage drives loan repayment through unit closings.
Populating Inputs
You can share a GC budget, a sales comps summary, 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 unit program and stacking plan (Inputs tab) must be set before pricing flows through correctly. The sale price is entered as dollars per saleable square foot, not a unit-level price. Construction timing inputs are month offsets from the project start, not calendar dates. The property tax entry uses mills per thousand dollars of assessed value, not a decimal rate, and entering the wrong convention produces a silently wrong pre-sale carry cost.
The Skill also checks whether the implied sell-out date from pre-sales plus monthly absorption pace falls before construction completes. That mismatch is one of the most common modeling errors on this type of deal and it has no visible warning in the model.
The Recalibrate LTC Button – A Critical Step
After any change to costs, timing, or financing assumptions, the construction loan must be re-sized to the target LTC by clicking the Recalibrate LTC button on the Summary tab. The AI cannot fire this VBA macro. When inputs change, the Skill will tell you to click the button and wait for your confirmation before reading any returns. The model displays a red warning on the Summary and CF tabs when the loan is out of sync, if that warning is showing, no return number is reliable. The Skill always checks this before surfacing any output.
Catching Common Mistakes
Seven errors show up repeatedly on this model. Not recalibrating the loan after an input change, the single most consequential mistake, and one with no automatic safeguard beyond the red warning flag. 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 toggle left on IRR when the term sheet uses equity multiple hurdles, or vice versa. Writing into a formula or cross-sheet cell. Treating the Custom disbursement method as permanent when it is fully reversible. And assuming budget line-item row ranges are uniform across categories, Marketing and Contingency extend to row 39, while Land, Soft, Hard, and G&A stop at row 20.
Framing Outputs
For a developer, the headline is levered IRR and total profit, with the unlevered IRR alongside to separate asset quality from financing contribution. For a JV sponsor, the focus is the LP/GP split across the three waterfall tiers and how promote sensitivity behaves. For an LP, the priority is whether the preferred return is cleared in both the base case and a stress scenario. For a lender, the key numbers are LTC actual versus target, peak drawn balance, and the cash sweep percentage as the primary repayment mechanism, for-sale construction debt repays from closings, not stabilized income.
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 Condominium Development Model is a monthly-period, ground-up for-sale condo development tool. It takes a line-item development budget, a unit program and stacking plan, a sell-out absorption schedule, and a construction loan with a cash sweep to produce unlevered and levered IRR, equity multiple, and total profit at the project level, plus an optional three-tier LP/GP partnership waterfall. The model covers a single for-sale condo development from land acquisition through unit sell-out, not rental multifamily, not a stabilized asset acquisition, and not a portfolio roll-up. The model is macro-enabled (.xlsm). See the model post for the full walkthrough and video tutorials.
Note: This AI Skill is built for v3.2 of the model. If you’re on an older version, confirm key cell positions before running the Skill, notably v3.1 extended the analysis period to 10 years and v2.5 introduced the buyer deposit module. 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 Condominium 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, 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 Condominium Development 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, 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 lifetime updates and unlimited downloads.
Frequently Asked Questions about the AI Skill for the A.CRE Condominium Development Model
Version Notes – AI Skill
beta v3.2
- Initial release of the AI Skill for the A.CRE Condominium Development Model
- Paired with v3.2 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 identification (developer/sponsor, JV sponsor, LP/equity investor, construction lender), input population from GC budgets, sales comps, and JV term sheets, and mistake-catching across the Recalibrate LTC step, millage rate convention, sell-out vs. construction timing, waterfall hurdle basis, formula cell integrity, Custom disbursement reversibility, and budget row range assumptions
- Portable to other capable AI assistants (ChatGPT, Gemini, etc.) via the SKILL.md file
