--- name: al-557-find-the-deals-already-sitting-in-your-lead-list-give-an description: "Investors and wholesalers pay to generate seller leads, then most of them go quiet in the CRM. On the Collecting Keys podcast (write-up dated Oct 27, 2026), investor Dylan Koch said his AI bots scrape county records, read PDFs for mortgage balances, estimate ARV and drop records that don't pencil, then format the data, upload it to his CRM, skip trace and push records to a dialer. He also asked a bot to search the thousands of leads already in his CRM for active ones matching one specific buyer's criteria, and it surfaced two or three he had forgotten about that may turn into deals. The hosts are frank that bots still fail (one report broke when a bot connected to the wrong system), so Koch has a second 'chief of staff' bot review the others' output daily. The episode gives no deal results, only that the leads may become deals. Use when the user wants help with investor lead re-mining by buyer buy box (sales) for a small business." --- # Find the deals already sitting in your lead list: give an AI one cash buyer's buy box and have it search your old seller leads for matching properties, drop the ones that don't pencil, and list who to call back first Investors and wholesalers pay to generate seller leads, then most of them go quiet in the CRM. On the Collecting Keys podcast (write-up dated Oct 27, 2026), investor Dylan Koch said his AI bots scrape county records, read PDFs for mortgage balances, estimate ARV and drop records that don't pencil, then format the data, upload it to his CRM, skip trace and push records to a dialer. He also asked a bot to search the thousands of leads already in his CRM for active ones matching one specific buyer's criteria, and it surfaced two or three he had forgotten about that may turn into deals. The hosts are frank that bots still fail (one report broke when a bot connected to the wrong system), so Koch has a second 'chief of staff' bot review the others' output daily. The episode gives no deal results, only that the leads may become deals. ## Inputs to collect first Ask the user for anything below that they haven't already given you. Don't guess missing facts. - CHECK ## Instructions Do the task below with the user's inputs in place of each [bracket]. 1. Write down one active buyer's buy box: property types, areas or ZIP codes, price or max offer, beds/baths, condition they'll take on, and minimum equity or spread. Keep it about the property and the numbers only. 2. Export your seller leads from your CRM (address, property details, lead date, last contact, status, notes, any mortgage or equity info) and remove anyone marked do-not-contact. 3. Ask your AI: "Search these leads for properties that match this buy box. For each match, give the address, why it fits, what's unknown, and a rough spread using only the numbers in the data. Drop anything where what's owed means it can't work, and mark any estimate you're unsure of as [CHECK]. Don't invent values." 4. Then: "Rank the matches by how recently we spoke and how strong the fit is, and draft a short, friendly call-back note for each that mentions what they told us last time. No pressure or made-up deadlines." 5. Check each property's current details and ownership in public records yourself, confirm contact consent and do-not-call rules, then make the calls. Each week, have the AI (or a second check routine) list any lead it couldn't read or any step that failed, so errors don't pile up silently. ## Safety checks (share these with the user) - Check every figure, price and total against your own records before anything is sent, posted or booked. A person approves refunds, discounts, payments and price changes. - Remove names, contact details, account numbers and other personal data the task doesn't need before you paste, and check your AI tool's data and training settings. - Check names, dates, numbers and any claim against your own source material before you use the answer. AI can misread or invent details. - Say clearly which parts need a person to review or approve before anything is sent, paid, posted or filed. ## About this skill - Works with: ChatGPT, Claude, CRM, county records, spreadsheet - Based on this real-world example: https://collectingkeys.com/articles/how-investors-are-using-ai-agents-to-run-daily-operations/ - Free prompt from AgentPlaybook Real Estate: https://agentic-library.netlify.app/prompt/al-557-find-the-deals-already-sitting-in-your-lead-list-give-an-ai/ - To install in an agent that supports Agent Skills, save this file as SKILL.md in a folder with the same name as `name` above (for example in your skills directory). Install steps for Claude.ai, Claude Code, Cursor and Codex: https://agentic-library.netlify.app/skills/