--- name: al-462-stop-sending-every-lead-the-same-emails-paste-the-ad-that description: "In the same Claude CRM write-up, Austin agent William Zhang calls this workflow his favourite: a referral should never get the same emails as a cold Facebook lead, so instead of the generic drip that came with his CRM he pastes the actual ad that generated a group of leads into Claude. It first says in one sentence what the person who clicked actually wants, then writes a five-email sequence (day 0, 2, 5, 12 and 30), each under 90 words, without restating the ad, each ending in one short question, with email 4 giving something useful and no ask, and no price, rate or market statistic he didn't supply. It also lists the assumptions it made about the lead so he can correct them, and nothing loads into the CRM until he approves. On a real Austin ad for single-story homes under $350,000 aimed at downsizers, the first email opened on low-maintenance living, no stairs and quiet neighbourhoods. His test: run it on two different ads and compare the two day-0 emails; if they sound the same,…" --- # Stop sending every lead the same emails: paste the ad that brought in a group of leads and have an AI write a five-email follow-up for exactly the person who clicked it, plus the assumptions it made so you can correct them In the same Claude CRM write-up, Austin agent William Zhang calls this workflow his favourite: a referral should never get the same emails as a cold Facebook lead, so instead of the generic drip that came with his CRM he pastes the actual ad that generated a group of leads into Claude. It first says in one sentence what the person who clicked actually wants, then writes a five-email sequence (day 0, 2, 5, 12 and 30), each under 90 words, without restating the ad, each ending in one short question, with email 4 giving something useful and no ask, and no price, rate or market statistic he didn't supply. It also lists the assumptions it made about the lead so he can correct them, and nothing loads into the CRM until he approves. On a real Austin ad for single-story homes under $350,000 aimed at downsizers, the first email opened on low-maintenance living, no stairs and quiet neighbourhoods. His test: run it on two different ads and compare the two day-0 emails; if they sound the same, the prompt isn't working. Keep fair-housing rules in mind: describe homes and features, not who a neighbourhood suits. ## Inputs to collect first Ask the user for anything below that they haven't already given you. Don't guess missing facts. - The ad text, headline and offer, plus where it ran - E.g. real estate agent in [city ## Instructions Do the task below with the user's inputs in place of each [bracket]. Here is the ad or landing page that brought in a group of my leads: [paste the ad text, headline and offer, plus where it ran]. My business: [e.g. real estate agent in [city]; or your business and what you sell]. 1) In one sentence, tell me what the person who clicked this actually wants. 2) Write a 5-email follow-up sequence for exactly that person, sent on day 0, 2, 5, 12 and 30. Rules: each email under 90 words and written like a note from a real person; don't repeat the ad back to them, they already saw it; end every email with one question they can answer in under ten words; email 4 gives something genuinely useful with no ask at all; never state a price, rate, statistic or timeline I haven't given you; for real estate, describe homes and features, never who a neighbourhood or home suits. 3) Give each email a short subject line. 4) List every assumption you made about this person so I can correct them. Show me the drafts only; don't load anything into my CRM or email tool. I'll keep the unsubscribe wording my email platform requires. ## 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. - Read and edit the draft before it reaches a customer or goes public. If you later automate this prompt, start with "draft and notify me", not "send automatically". - 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: Claude, ChatGPT, Gemini, Follow Up Boss, HubSpot, Mailchimp - Based on this real-world example: https://realestateusecases.com/u/lead-source-follow-up-sequence-from-ad-claude/ - Free prompt from AgentPlaybook Real Estate: https://agentic-library.netlify.app/prompt/al-462-stop-sending-every-lead-the-same-emails-paste-the-ad-that-br/ - 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/