May 7, 2026 · 5 min read
Free AI skills for real estate teams.
By Jeff Schacher, Chief AI Officer
We built a free library of AI skills for commercial real estate because people kept asking us the same question: "What should I use AI for?"
A skill packages instructions and supporting material for a recurring task. It can include the steps to follow, business context, examples, and checks. Your team can adapt it as you learn what works.
For example, an acquisitions analyst could use a skill to compare an offering memorandum with the firm's investment criteria. A portfolio manager could draft a variance summary from operating reports. A lease administrator could extract critical dates and ask for a source reference beside each one. These are examples of tasks to test, not measured client results.
Now here's why we made them available.
AI Activity Isn't the Same as AI Capability
Every commercial real estate company I talk to is in a different place with AI. Some have built internal tools and aren't sure what to do next. Some are paying for Microsoft Copilot and wondering how long they should wait for it to get better. Some are experimenting with ChatGPT and Claude but haven't figured out how to make it useful for their teams. Some haven't started at all and are starting to feel the pressure.
Different starting points, but increasingly the same question: we have people using AI. So why doesn't it feel like we're building anything?
More people can help build the workflow
Agentic tools let the person who knows a task work directly on the instructions, examples, and checks it needs. Some work that would once have required a custom application can now be handled in an existing AI tool.
That makes it easier to try an idea. It also makes task design more important. The more complex the work, the more care the instructions, context, and review process need. Systems access, permissions, and unattended operation may still need IT or engineering help.
When Employees Become the Builders
Skills changed who gets to build. If you can describe the task clearly, provide examples, and judge the output, you can now co-design a working version with Claude or ChatGPT directly. The employee who knows the task best is now the person who can build the tool to handle it.
That changes where AI capability comes from inside an organization. The team can test an idea while the requirements are still taking shape.
The next challenge is sharing what works. Otherwise, colleagues may keep solving the same problem separately. The experimentation matters, but it needs a process layer: shared skills, common standards, a way to turn what works for one person into something the whole team uses. That's where firms figure out what AI is actually good at, and which workflows are worth standardizing.
Useful internal tools need someone to understand the users, test the workflow, and maintain it. Teams can take on some of that work themselves; more complex projects benefit from product and engineering experience.
Why Make the AI Skills Library Available to All?
First, breadth. The library includes tasks across acquisitions, asset management, leasing, and operations. Browse the areas closest to your work.
Second, it's a menu. One of the most common things we hear from clients is some version of "we know we should be doing more with AI, we just don't know where to start." The library answers that. Browse it, find tasks that look familiar, and you've got your starting point. You don't need a strategy deck before you can take a first step.
Third, it's an invitation. The skills are open and available to all. You can adapt them yourself. We can help with business context, testing, integrations, and more complex builds when you need it.
From Skills to Systems
A maintenance triage skill is one starting point. It could help a property manager categorize requests, identify missing information, and draft a response for review.
Connecting that skill to incoming requests is a separate step. You need to define urgent cases, decide who approves a response, and test what happens when the instructions do not cover a request. Scheduling and system access also need to be configured.
That distinction matters. A skill describes how to do the task. The surrounding workflow determines when it runs, what it can access, and who handles problems.
How to Start
Pick a task your team does every week and find the closest skill in the library. Use a tool approved by your firm and confirm it supports the skill's requirements. Start with material you are allowed to use, then compare the result with work you can check.
Keep the useful parts. Adjust what is missing. Before colleagues rely on the skill, test it on different inputs and agree who will maintain it.