An AI Skill for the A.CRE Land Development Model
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 Land 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 Land Development Model post, which walks through the model itself: the 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, that means every input cell on the Underwriting tab, the five user roles the model serves, how the funding order and the Recalculate macro size equity and debt, and the most common ways a for-sale land underwriting goes wrong before you ever get to a margin or an IRR.
The result is an AI assistant that can actually operate the model on your behalf, rather than one that talks about land 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 Land Development Model underwrites a single-phase, for-sale land deal on a monthly basis, for up to 180 months. It covers commercial pad sites, residential lots sold to builders, and townhome or single-family build-and-sell projects. Land, horizontal and vertical hard costs, and soft costs are spread by line item. Equity plus up to two debt tranches fund them, pads, lots, or units sell out over time with a set share of each sale repaying the loan, and returns run through a two-tier GP/LP waterfall. A few of its mechanics will trip up a general-purpose AI without specific instruction. Equity and the Pari Passu debt share are hardcodes written by a macro. Every blue cell, even one that ships with a formula, is an input to confirm. And timing is entered as month numbers, never dates. The Skill knows all of this.
Role Identification
Before the Skill touches a single input, it asks which decision you are making:
- Land developer / sponsor (GP): deciding whether the deal pencils and what the project and the GP earn. The Skill leads with unlevered margin and IRR, because leverage can’t fix a thin unlevered margin, and then moves to levered IRR and the GP’s IRR, equity multiple, and profit.
- LP / equity investor: deciding whether the LP return is worth the risk under the pref and promote terms. The Skill judges the deal on the LP’s own return rather than the project’s levered IRR, and checks how funding order changes the LP’s equity at risk.
- Construction / land lender: checking that the loan is sized correctly and that sales repay it. The Skill surfaces the debt sizing, the capitalized interest, and the alerts that flag sale proceeds falling short of the payoff.
- Homebuilder / land broker or seller: working out what the land is worth, or the most a buyer can pay at a target return. The model has no built-in solver, so the Skill iterates the land price in the conversation and reports where the target is met.
- Student / Accelerator member: learning how the model works. The Skill walks through the S-curve cost spreading, the debt sizing, the funding order, and the waterfall one piece at a time.
Populating Inputs
You can share a purchase agreement or LOI, a site plan or plat, a civil or contractor cost estimate, an entitlement budget, land or lot sales comps, an absorption study, a builder takedown schedule, or lender and JV term sheets. The Skill pulls the relevant assumptions and stages them for your review before writing anything.
Every blue cell in the model is treated as a required input you confirm, including the ones that ship with a formula default, such as the entitlement cost at 1% of land or the sales end month. Keeping the formula or replacing it are both legitimate, but the Skill asks about each one.
For any assumption you have not sourced, the Skill follows a simple rule. If the template has a placeholder, it leaves it and tells you it did, asking you to confirm or replace it with a market-supported number. If there is no placeholder, it makes a defensible best guess and discloses it. It never writes a value without saying where the value came from, and it does not invent industry-norm ranges that age out within a year or two. The sample deal figures in the template (land price, sale amounts, land sizes, start and end months) are never left in place without asking.
A few conventions it confirms every time. Months are whole numbers, where 1 is the month of the project start date, and never calendar dates. Every End month has to be on or after its Start month and within the 180-month grid. The Skill never inserts or deletes rows. It uses spare rows or zeroes out unused ones, and if you need more lines, you click Add Line in desktop Excel. And it labels every row it uses, so no amount sits on a row with a blank name.
Recalculating After Changes
This model depends on VBA. The Recalculate macro sizes equity and the Pari Passu debt share, and the Add Line and Delete Line buttons run macros too. The AI cannot fire any of them. So the Skill handles recalculation in two layers. First it recalculates the formulas itself and reads the model’s recalculation flag. Then, if the flag shows the macro needs to run, it reports the unlevered results right away, since those do not depend on the macro, and holds back the levered, LP, and GP results, the debt sizing, and the interest until you have clicked the recalculate button in desktop Excel, saved, and re-uploaded the file. In Claude in Excel, it asks you to click the button and tell it when that is done.
The Skill collects all of your changes first, so you click recalculate once per scenario rather than once per input. If you do not have Excel and ask for an estimate, it can solve the same equity and debt sizing itself, but it labels every such number as an estimate, not Excel-recalculated, and tells you it can differ from the macro by up to about a point of levered IRR.
Catching Common Mistakes
A dozen errors show up repeatedly on this model. Reading levered, LP, or GP results before the Recalculate macro has run. Quoting the greyed-out fixed rate when the loan is set to Variable, since the effective rate sits in a different cell. Leaving the End month at its default with a large unit count, so 200 lots stretch past the 180-month grid. Sales unit counts that do not add up to the land size. Alerts that flag sale proceeds failing to pay off the loan, or costs that run past the last sale. Forgetting that entitlement and A&E costs are percentages that move when the land price or hard costs change. Financing fees left stale after the loan size changes. Judging an LP by the project’s levered IRR instead of the LP’s own return. Comparing unlevered margin to levered margin when the two use different denominators. Running a Commercial or Residential model with large vertical costs, when the Townhome or Single-Family type fits better. And typing into the calculated acres cell or over the monthly timeline.
Framing Outputs
Every number the Skill reports comes with the cell it was read from, for your own checking. For a developer, the headline is unlevered margin and IRR, then levered IRR and the GP’s returns. For an LP, it is the LP’s IRR, equity multiple, and profit share, along with the timing of the equity. For a lender, it is the debt sizing and whether sales repay the loan. The model has no sensitivity tables, no annual roll-up, and no built-in residual land value or breakeven solver, and it does not calculate peak equity, peak debt, or per-acre metrics. When you ask for those, the Skill derives or reruns them in the conversation and says so.
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 the model via code execution. The Skill bundle includes a clean copy of the model, so no upload is needed to get started, and the macros are preserved in the file Claude hands back. Or, if you’re using Claude in Excel, operate the model live with Claude reading and writing to the workbook directly. In both cases, you run the macros yourself in desktop Excel. 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 Land Development Model is a single-phase, monthly, for-sale development tool for commercial pad sites, residential lots, townhomes, and single-family homes. A model type drop-down on the Summary tab relabels the model for each, and nearly all inputs live on the Underwriting tab. It produces unlevered and levered IRR, equity multiple, profit, and margin, and runs them through a two-tier GP/LP waterfall with a return of capital and preferred return, then a promote. It does not model multiple phases, price growth over time, buyer deposits or pre-sales, land takedowns, seller financing, IRR hurdles, or a GP catch-up. For a condo sell-out, build-to-rent, a stabilized acquisition, or a ground lease, other A.CRE models are the better fit. The model is macro-enabled (.xlsm). See the model post for the full walkthrough and tutorials.
Note: This AI Skill is built for v0.79 of the model. If your file is on an earlier version, cell positions may differ, so check the Version tab and confirm key cells before running the Skill. The Skill needs an .xlsm copy of the model. If you have the .xlsb version, open it in Excel and use Save As to save an .xlsm. The model requires desktop Excel (2013 or newer) with macros enabled, Windows is recommended, and Mac is not officially tested. Excel for the web, iPad, and Google Sheets cannot run the model’s macros.
Before You Use This AI Skill with the Land 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 land and residential development underwriting, horizontal and vertical development budgeting, construction lending, and partnership waterfalls. 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, and 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, and 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 Land 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 $200 – $500+ 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, so no upload is 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 An AI Skill for the A.CRE Land Development Model
Version Notes: AI Skill
Version 0.79
- Initial release of the AI Skill for the A.CRE Land Development Model
- Paired with v0.79 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 five-role identification (land developer/sponsor, LP/equity investor, construction/land lender, homebuilder/land broker, student), input population from purchase agreements, site plans, cost estimates, sales comps, and term sheets, a two-layer recalculation hand-off for the macro-driven equity and debt sizing, and mistake-catching across timing, sales and land size tie-outs, variable rates, financing fees, LP versus project returns, and margin denominators
- Portable to other capable AI assistants (ChatGPT, Gemini, etc.) via the SKILL.md file
