An AI Skill for the A.CRE Industrial 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. Our latest model in that effort is here, and this post introduces it: AI Skill for the A.CRE Industrial Development Model.
Think of this as a sister post to the Industrial 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 the Industrial Development Model, the five user roles the model serves, the two-layer recalculation check that must pass before any return is reliable, and the most common ways industrial development underwriting goes wrong before you ever get to a development spread.
The result is an AI assistant that can actually operate the model on your behalf, rather than one that talks about industrial 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 Industrial Development Model has a few mechanics that differ sharply from other development models — and that a general-purpose AI will get wrong without specific instruction. The headline metric shifts depending on the exit strategy: for a merchant-build deal, Development Spread leads; for build-to-core, Levered IRR leads. The model has two separate recalculation convergence checks — one for the LTC, one for the management fee — and both must pass before any return is internally consistent. Land is entered in acres, not square feet. Rent is annual per SF, not monthly. And timing inputs are month offsets from the analysis start, not calendar dates. The Skill knows all of this.
Role Identification
Before the Skill touches a single input, it asks which decision you’re making — and, for the developer role, it asks which exit strategy:
- Developer / sponsor — evaluating whether the project pencils. The Skill’s first question is the exit: merchant-build or build-to-core? For merchant-build, Development Spread leads. For build-to-core, Levered IRR leads. Both are always reported; only the emphasis shifts.
- JV sponsor structuring a partnership — sizing the promote and hurdle structure. The Skill confirms the hurdle basis, populates the waterfall, and surfaces LP and GP IRR. It always flags when the GP equity share (H215) is changed, because it silently moves the promote splits in three downstream cells.
- LP / equity investor — reviewing a sponsor’s file for diligence. The Skill runs a structured diligence check before reporting anything: whether the recalculation check passes, whether the exit cap still equals today’s cap (the most common source of an optimistic spread), whether the rent growth placeholder was cleaned, and whether recoveries are realistic for the building type.
- Construction lender — sizing or stress-testing the loan. The Skill surfaces actual LTC versus target, interest reserve versus total construction interest, DSCR and debt yield at the refinance month, and whether the permanent loan proceeds cover the construction debt payoff.
- Student / Accelerator member — learning the mechanics. The Skill teaches the model one input at a time: the font convention, the month-offset system, how cost spreading redistributes without changing the total, and the interest reserve circularity that the Recalculate macro resolves.
Populating Inputs
You can share a land PSA, a GC bid, a site plan, lease comps, or a loan term sheet — the Skill pulls the relevant assumptions and stages them for the model. A few things it always confirms before writing:
Land area (E15) is in acres. This is the most consequential unit trap in the model — a user thinking in square feet enters a number roughly 43,560 times too large, and every land-cost-per-SF metric explodes. The Skill confirms the convention explicitly before touching land. Rent (H103:H106) is annual per SF — some industrial markets quote monthly, and a $0.55/SF/month rate is $6.60/SF/year. Timing inputs are month offsets, not calendar dates — month 0 is closing. And Development Spread (H204/I204) is in basis points, not a decimal.
The Skill also confirms the model’s six binary toggles on the first reply: permanent debt, Argus CF Drop, double promote, fixed/variable rate, and two others. These change what cells mean, and reporting them up front means both sides are working from the same configuration.
The C279 Recalculation Check
This model has a two-layer convergence problem. Construction loan interest depends on the draw balance, which depends on capitalized interest. The management fee depends on effective gross revenue, which is net of the fee. A.CRE resolves both with a Recalculate macro — not Excel’s iterative calculation. Cell C279 is the AND of both checks: C277 (LTC converged) and C278 (management fee converged). If C279 is FALSE, every return on screen is internally inconsistent and must not be quoted.
After any change to LTC, construction rate, or management fee, the Skill will tell you to run the Recalculate module and wait for your confirmation before reading any outputs. The AI cannot run this macro.
Catching Common Mistakes
Thirteen errors show up repeatedly on this model. C279 is FALSE — the single most consequential, and the first thing the Skill checks before any output. Macros disabled, which kills the Recalculate module, the Add/Delete buttons, the CF Drop, and the Residual Land Value tool. Land area entered in square feet instead of acres. Calendar dates entered where month offsets belong. Development spread entered as a decimal instead of basis points. Rent entered as a monthly rate instead of annual per SF. The exit cap left equal to today’s cap, underwriting zero expansion. Lease term and downtime entered in the wrong units — the two adjacent rows use years and months respectively. The GP equity share changed without recognizing it moves three downstream waterfall cells. The permanent debt toggle changing the sale month default without the user noticing. The Argus CF Drop start date misaligned with the analysis start. Overwriting black-font formula cells. And triggering Delete Tenant or Delete OpEx — both destructive, non-undoable, and never triggered by the AI.
Framing Outputs
For a merchant-build developer, the headline is Development Spread in basis points, followed by Yield-on-Cost (untrended and trended). The Skill always notes whether the spread is trended — if most of the spread is trended, the deal is a growth bet, not a development margin story. For build-to-core, Levered IRR leads, alongside stabilized cash-on-cash and DSCR at the refinance. For an LP, the headline is LP IRR and equity multiple, with an explicit check on whether the preferred return clears. For a lender, the headline is actual LTC versus target and whether the interest reserve covers total carry. For all roles, the Skill surfaces total cost per SF (H55), which users often miss and which is the fastest market cross-check.
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 Recalculate macro must be run by the user in Excel with macros enabled — the AI cannot trigger it. 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 Industrial Development Model is a monthly-period, ground-up industrial development tool built for merchant-build and build-to-core strategies. It takes a line-item development budget with selectable draw curves, a tenant-by-tenant lease-up with NNN recovery, a construction loan sized to a target LTC with capitalized interest and operating shortfall reserves, and an optional permanent debt takeout, to produce Development Spread, Yield-on-Cost, and unlevered and levered IRR and equity multiple. It supports an optional Argus CF Drop module (for externally modeled operating cash flows), a Residual Land Value tool, and an optional double-promote waterfall. The model covers a single industrial project, single phase. It does not cover data center development, multi-phase delivery, preferred equity, or after-tax analysis. The model is macro-enabled (.xlsm). See the model post for the full walkthrough and tutorials.
Note: This AI Skill is built for v2.9 of the model. Cell positions differ in earlier releases — v2.87 changed the permanent debt sizing inputs, v2.83 added the dynamic sensitivity block, and v2.8 inserted the Cash Flow Drop module, shifting all rows below it. The model is macro-enabled (.xlsm) — macros must be enabled in Excel for the Recalculate module, the Add/Delete buttons, and the CF Drop to function.
Before You Use This AI Skill with the Industrial 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 industrial development underwriting, NNN lease structures, and construction financing. 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 Recalculate module, the Add/Delete Tenant and OpEx buttons, the CF Drop, and the Residual Land Value tool to function. The AI cannot run these macros.
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 Industrial 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 a new download link via email each time either is updated.
Frequently Asked Questions about the AI Skill for the A.CRE Industrial Development Model
Version Notes – AI Skill
v2.9
- Initial release of the AI Skill for the A.CRE Industrial Development Model
- Paired with v2.9 of the Excel model (no cell-layout changes versus v2.88; version bump for the AI Skill release)
- 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 with merchant-build vs. build-to-core branch, JV sponsor, LP/equity investor, construction lender, student/Accelerator member), input population from land PSAs, GC bids, lease comps, and loan term sheets, two-layer C279 convergence check, and mistake-catching across land area units, timing conventions, rent units, development spread units, exit cap staleness, waterfall cascade from GP equity share, CF Drop start alignment, and destructive macro safeguards
- Portable to other capable AI assistants (ChatGPT, Gemini, etc.) via the SKILL.md file
