Listing Command Center Claude Plugin

What This Is

The Listing Command Center is a Cowork plugin that turns your listing’s source files into the marketing assets you need to launch and sell it. You drop the MLS report, photos, and comps into a folder. You ask for what you need in plain language. The agent reads what’s there and produces the asset.

Six outputs you can request:

• Listing description — MLS Public Remarks written to be found by AI search engines like ChatGPT, Perplexity, and Google AI Overviews. Noun-dense, feature-rich, compliant.
• Photo ordering — renames your photo files into proper MLS display sequence: front exterior first, logical walk-through flow, outdoor and garage last.
• Photo captions — one MLS-ready caption per photo, in display order.
• Deal of the Week email — a plain-text email that reads like a personal note, not a marketing blast. Two variants per run so you can pick the one that fits.
• Just-listed HTML email — a branded campaign email, built in your colors and fonts, ready to paste into your email platform.
• Pricing analysis — a full CMA with a sales-comparison adjustment grid, an appraised value, a marketable value, and a list price recommendation that bridges the two.

This one’s a plugin, which is new. If you’ve set up a Cowork agent before, you know the routine — download a folder, install each skill one at a time, drop in a file that tells the agent what to do, then point Cowork at the whole thing. A plugin puts all of it under one hood. One download installs the skills, the instructions that run them, and the setup that personalizes them, together. Nothing to assemble.

That leaves one thing to do: answer a few questions so it writes like you and knows your market. About five minutes, and most of it is confirming what it already pulled off your website. Your answers save to your account, not to a folder — so it’s there in every Cowork session you open from then on, whether you run one per listing or one for all of them.

Fair Housing and RESPA guardrails are baked in. The skills avoid school quality ratings, demographic framing, steering language, and lender recommendations. You should still review every output before it goes to your MLS, your database, or a client — AI guardrails reduce risk, but they don’t replace your professional judgment.

How to Use It

You’ll need the Claude desktop app (Mac or Windows, any paid plan) and about five minutes. There’s nothing to configure beyond answering a few questions.

STEP 1: DOWNLOAD AND INSTALL THE PLUGIN

Download the file below, then install it in Claude. Five steps, about a minute — no skill uploads one at a time, no folder setup, no task instructions to paste.

1. Download the plugin file above.
2. Open Claude and click Customize in the sidebar.
3. Click Plugins, then Add, then Upload plugin.
4. Unzip the folder you downloaded. Inside is a single file: listing-command-center.plugin.
5. Drag that .plugin file into the upload area and click Upload.

Nine skills come with it: the orchestrator that routes your requests, a guided setup, and the seven skills that do the actual writing. They install together and turn on automatically.

STEP 2: START A COWORK TASK AND PICK YOUR FOLDER

Open Claude, switch to Cowork, and start a new task. Cowork will ask you to choose a folder on your computer. That folder is the only thing it can see — so choose the one where your listing files already live.

You don’t have to reorganize anything or move files around first. However you already keep your listings is fine. Find yourself below:

• You keep a separate folder for each listing. Choose the folder for whichever listing you’re working on today. It’s the only property in there, so you’ll never get asked which one you mean.
• You keep one folder with all your listings inside it. Choose that folder. When you ask for something, just say the address — “write the description for 123 Main” — and it’ll go to the right one.
• Your listing files aren’t really organized. Choose whatever folder they’re sitting in. It reads the files themselves to figure out which ones belong to which property, and asks you if it can’t tell.

Whatever you put in that folder is what it has to work with. Here’s what it looks for. You don’t need all of it — add what you have:

• MLS report — the PDF export from your MLS. The single highest-value file; most outputs run off it.
• Photos — .jpg, .png, or .heic. Required for photo ordering and captions.
• Comps — CSV or XLSX. Required for pricing analysis. Pull it broad: every status, full year, wider than the immediate subdivision. The agent sorts out what’s relevant.
• Tax record or sales history — optional, sharpens the CMA.
• Prior listing remarks — optional. Used as a voice reference, never copied.

The listing description runs on the MLS report alone. Add files as you get them — the agent tells you when something’s missing for what you asked.

STEP 3: RUN SETUP

In that same task, say:

Set up my Listing Command Center.

Here’s how it goes:

1. It asks for your website. That’s the whole first question. It reads your site and pulls what it can — your name, title, brokerage, office address, license, phone, email, market area, neighborhoods, brand colors, fonts, logo, and headshot. No website? Give it your name and brokerage instead.
2. It shows you everything it can do, and you pick. All six outputs, listed plainly. Choose what you want set up now. Pick everything if you’re not sure — it’s only a few more questions, and anything you skip still works later.
3. It shows you what it found on your site. In plain English, not hex codes — “a dark green, a lighter green, and a tan accent.” It tells you which pieces it read directly and which were educated guesses. You say what’s wrong, it fixes just that.
4. It asks the few things it couldn’t figure out. Only for what you picked, and it always tells you which output the questions are for. Your logo and headshot links, your email design preferences, your call-to-action, what you call your Deal of the Week.
5. If you chose the pricing analysis, four market questions — already answered for you. What buyers in your market pay a premium for, how you define a comp, what kills a deal, and which numbers you show a seller first. These are what make a CMA sound like you instead of a generic comp printout, so instead of asking cold, it writes a first pass from your market and you correct it.

At the end it saves everything to your Claude account. Click save, and you’re done — you can go straight to asking for your first output in the same conversation. You’ll never set this up again: not for a new listing, not for a new Cowork session, not on a different computer.

STEP 4: ASK FOR WHAT YOU NEED

Plain language. No commands to memorize.

Write the listing description for 123 Main.

It finds the listing, reads through the files you put there, pulls the property details off the MLS report, looks up what’s nearby, asks you about anything it can’t tell for sure, and saves the finished draft.

Or ask for the whole package at once:

Generate everything for 123 Main — order the photos, write the description, caption the photos, build the HTML email, and run the pricing analysis.

It checks everything up front — which files you have, which you’re missing, and anything you skipped during setup — asks for all of it in one message, then runs start to finish without interrupting you again.

STEP 5: WHAT YOU GET BACK

Output files land in that listing’s output folder. Each is a polished draft you review, edit, and use.

• Listing description → listing-remarks.md — paste into your MLS Public Remarks field
• Photo ordering → photos renamed in place, plus a report showing the changes
• Photo captions → photo-captions.md — paste into your MLS photo captions field
• Deal of the Week email → dotw-email.md — two versions to choose from, each with subject lines
• HTML email → just-listed-email.html — copy the HTML and paste into your email platform’s code editor
• Pricing analysis → cma-seller-facing.md (the narrative for your seller) and cma-internal-memo.md (your internal pricing rationale)

Your original files are never touched. Everything it creates goes into two new folders inside that listing: output, which holds the drafts you asked for, and references, which is scratch work it keeps so repeat requests run faster. The one exception is photo ordering, which renames your actual photo files — and if more than one property’s photos are sitting in the same folder, it shows you exactly which files it’s about to rename and waits for you to say go.

YOUR NEXT LISTING

There’s no setup the second time. Put the files wherever you keep them, start a task on that folder, and ask. It already knows who you are.

If you want to queue a request while you’re away from your computer, use the Dispatch feature in the Claude mobile app. As long as your computer is on with Cowork running, you can trigger a request from your phone — useful when you’re at a listing presentation or driving and want to kick off a draft before you get back to your desk.

USAGE AND COST

Everything runs inside your Claude subscription — nothing else to buy, no separate bill. Each request draws from your usage allowance, the same pool you use for regular Claude chats. Most requests are light. The pricing analysis is the heaviest, since it reads the comps, builds the adjustment grid, and writes two documents. If you’re watching your usage closely, ask for one output at a time rather than “generate everything.”

Tips

• The HTML email needs your photos to already be online. Email apps can’t load a photo off your hard drive, so a link is the only thing that works. Upload your listing photos to your email platform’s media library, copy the links, and paste them in when you’re asked. Avoid Google Drive and Dropbox links; they break in email clients.
• The email greeting is left as a plain “Hi,” on purpose. Merge field syntax is different in every email platform and changes over time — a wrong one shows up as raw code in your recipient’s inbox. There’s a comment in the HTML marking the spot. Use your platform’s own personalization button to insert the first-name field, and it’ll be right every time.
• It remembers each listing. The first request on a property is the slow one — it’s reading the MLS report and researching what’s nearby. It saves all of that, so everything you ask for after that on the same listing comes back much faster.
• Changed brokerages or rebranded? Say “update my profile” and it asks only what changed. You won’t redo setup. This is rare — your profile is static information, not something you maintain.
• Review before you publish. Every output is a draft, never auto-published. Read it. Check the local details and the numbers. Make sure the voice sounds like you. You’re the agent of record — the output is your responsibility before it goes to your MLS, your database, or a client.