An AI Skill for the A.CRE Commercial Real Estate Lease Analysis Tool
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 Commercial Real Estate Lease Analysis Tool 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 Commercial Real Estate Lease Analysis Tool post, which walks through the tool 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 tool 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 in the Lease Abstract, every output, the five user roles the tool serves, how the Base and Option tags set the analysis period, and the most common ways a lease abstract goes wrong before you ever get to a net effective rent.
The result is an AI assistant that can actually operate the tool on your behalf, rather than one that talks about lease analysis 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
A lease abstract reads the same no matter who is holding it, but the question behind it changes completely. A landlord asks what the lease is worth after concessions. A tenant asks what the space really costs. A broker asks what the commission is and when it gets paid. A buyer asks what the remaining lease income is worth at closing. The tool handles all of them, because every tenant inflow is a landlord outflow, but the right outputs and the right framing differ in each case. The Skill handles that part for you.
Role Identification
Before the Skill touches a single input, it asks which side of the lease you are on:
- Landlord / owner / asset manager: evaluating a proposed or in-place lease. The Skill leads with landlord net effective rent per SF, landlord NPV, and the impact of leasing commissions, and compares net effective rent to contract rent to show what the concessions cost.
- Tenant / occupier / tenant rep: evaluating the total cost of occupying the space. The Skill leads with net effective cost per SF and tenant NPV. Costs show as negative numbers, so the less negative proposal is the better one for the tenant.
- Leasing broker: sizing the commission and its payment timing. The Skill surfaces the total commission, the broker cash flow by year, and what the commission does to the landlord’s NPV.
- Acquisitions / lender analyst: valuing an in-place lease from a closing or valuation date. The Skill sets the analysis start to that date, treats the tenant estoppel as the authority on what has already been paid, and leads with landlord NPV and the remaining base term.
- Student / analyst learning lease analysis: working through the template to understand the mechanics. The Skill walks the Lease Abstract from top to bottom as a worked example, flips a tag or a date to show the effect on the outputs, and then restores the original values.
Populating Inputs
You can share the lease and all of its amendments, an LOI or proposal, the operating budget or operating statement, the commission agreement, or a tenant estoppel. The Skill pulls the lease terms into the Lease Abstract tab and stages them for your review before writing anything.
Lease terms are never left on the template’s fictional placeholders. If the dates, rentable area, rent schedule, expense responsibilities, or inducements are missing, the Skill asks for them. Assumptions are different. For the discount rates, expense growth, and commission tiers, the Skill uses the value you provide, and if you provide none it leaves the template placeholder and tells you it did.
A few conventions it confirms every time. The rent schedule is entered as total dollars per month, not dollars per SF per year. Expense amounts are annual. Every rent step carries a Base or Option tag, and the tag drives the lease expiration date. And for an in-place lease, only the amounts still outstanding go in: inducements already paid before the analysis start and commission installments already paid stay out.
Catching Common Mistakes
Eleven errors show up repeatedly on this tool. A rent step tagged Option instead of Base, which silently moves the expiration date and every output (in a test on the template lease, one mis-tagged row cut net effective rent from $27.47 to $17.26 per SF). Forgetting that outputs cover the remaining base term from the analysis start date, not the full lease from commencement. Misreading the sign convention, where tenant cost and tenant NPV are negative. Treating net effective rent as a discounted number when it is an undiscounted average. Entering inducements or commissions that were already paid on an in-place lease, which pulls them to Time 0 and understates value. Leaving the commission “Already Paid?” flag at No on past installments, which lands the full commission at Time 0. A base year amount that sits above the current expense estimate, which produces a negative reimbursement, since the tool has no floor. Entering rent as dollars per SF per year when the schedule expects total dollars per month. Assuming the SF/M2 toggle converts units, when it only relabels them. Expecting the termination option or billing frequency to change the cash flows, when both are informational only. And leaving the template’s free rent labels in place, so they no longer match their dates.
Framing Outputs
Every headline output covers the remaining base term only, from the analysis start date to the initial expiration, and excludes options. The Skill says so each time it quotes a number. Net effective rent is an undiscounted average, so it shows how much the landlord nets, while NPV shows when. When concessions are front-loaded, the Skill leans on NPV rather than net effective rent.
Before it reports any result, the Skill confirms that the three check cells on the Lease CF and Leasing Commissions tabs read OK, so you know the cash flows tie out.
On request, the Skill also reports a few metrics the tool does not calculate: discounted net effective rent, rent per SF at a given date, concessions as a percentage of rent, and the landlord break-even year. These are calculated in the conversation with the formula shown, and are never written into your workbook.
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 tool via code execution. The Skill bundle includes a clean copy of the tool, so no upload is needed to get started. Or, if you’re using Claude in Excel, operate the tool live with Claude reading and writing to the workbook directly. In a chat session, the Skill recalculates the workbook before it reads any result, so you never see a stale number. And as noted earlier, the Skill is also portable to other AI assistants, though the integration may be lighter.
A Note on the Underlying Tool
The Commercial Real Estate Lease Analysis Tool abstracts a single commercial lease (office, retail, industrial, or other) and projects the cash flows of both the landlord and the tenant over the remaining base term. Most inputs live on the Lease Abstract tab. The Lease CF tab calculates monthly cash flows and rolls them up into annual periods. The Leasing Commissions tab sizes the commission, schedules the broker’s cash flow, and restates landlord net effective rent and NPV after commissions. The Summary tab is a printable one-page report. The tool does not analyze a multi-tenant rent roll, value a property, or calculate IRR, and it does not handle CPI escalations, percentage rent breakpoints, expense stops, caps, or gross-ups. It contains no macros. See the tool post for the full walkthrough.
Note: This AI Skill is built for v0.6 of the tool, which added the Leasing Commissions tab and corrected how Time 0 cash flows are discounted. If you’re on an older version, confirm key cell positions before running the Skill. The tool also requires Excel 2019, 2021, or 365. The lease expiration date uses the MAXIFS function, so Excel 2013 and 2016 return errors across the outputs, even though the Version tab in the file still lists those versions. On older Excel, you can type the expiration date in by hand and keep it consistent with the rent schedule.
Before You Use This AI Skill with the Commercial Real Estate Lease Analysis Tool
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 lease abstraction, expense recovery structures, leasing commissions, and tenant inducements. It’s best suited to graduates of our A.CRE Accelerator real estate financial modeling program, or analysts comfortable building lease 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 a leasing or 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 Commercial Real Estate Lease Analysis Tool + AI Skill
To make this tool 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 analysis tools 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 tool, the AI Skill (.skill file), and a short README explaining how to use them together. The Skill bundle includes a clean copy of the tool, so no upload is needed to get started with Claude.
We regularly update both the tool 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
Version Notes: AI Skill
Version 0.6
- Initial release of the AI Skill for the A.CRE Commercial Real Estate Lease Analysis Tool
- Paired with v0.6 of the Excel tool, which also adds the Leasing Commissions tab and fixes the Time 0 reimbursement reference, the operating expense calculation after lease expiration, and the landlord and tenant NPV formulas
- Supports both Chat / Cowork (Skill bundle includes a clean copy of the tool, no upload needed) and Claude in Excel (operate the live workbook directly)
- Includes five-role identification (landlord/owner/asset manager, tenant/occupier/tenant rep, leasing broker, acquisitions/lender analyst, student/analyst), input population from leases, amendments, LOIs, operating budgets, commission agreements, and estoppels, and mistake-catching across Base and Option tags, the remaining-term frame, sign convention, net effective rent versus NPV, sunk inducements and commissions, base year recoveries, and rent entry units
- Portable to other capable AI assistants (ChatGPT, Gemini, etc.) via the SKILL.md file
