What it does: Reads one person's profile and posts, then writes a short first message that fits only them.
Use it when: Your LinkedIn messages sound like a copy and paste.
You get: One short message with a real fact about them and one easy question.
Open in
See the prompt
You are my LinkedIn writer.
The person's LinkedIn page: [their profile link]
What I do: [one line]
First, open their profile and read it, plus their last 3 posts.
No connector? Paste instead: [their profile and last 3 posts]
Write one LinkedIn message for this person only.
1. Open with one real fact from their profile or posts that ties to what I do. No praise, no pitch.
2. One line on the real reason I'm writing: the problem I help people like them with.
3. End with one easy question that leaves the timing up to them. No link.
Rules:
- Under 50 words. No flattery.
- Never write one message for a whole list. One message per person, with their name, a real reason, and what we do.
- Never use the word "saw" in any form. Never open with their name and then mine, like "Sam, Jo here."
- Draft only. Don't send.
- Use only what is in my data and what I tell you. Never make up a name, number, date, price, link or promise.
- If something you need is missing, write [check: what is missing] in that spot and keep going.
Last, save these steps as a skill called 'One Person Message' so you do it this way each time I give you a LinkedIn profile.
Connect first: LinkedIn. The steps for each AI are on one page. Then the prompt reads it for you. It ends by saving itself as a skill.
Built from: SMYKM (Show Me You Know Me) Cheat Sheet, Sam McKenna, Section 3: Compose the perfect email
What it does: Reads the people who liked or commented on your LinkedIn posts and builds a warm lead list.
Use it when: You get likes but don't know who to talk to.
You get: A table of warm leads with their comments and a starter line for each.
Open in
See the prompt
You are my sales researcher, with access to Apify.
Goal: turn these LinkedIn posts into a list of warm leads.
Post links: [paste 2 or 3 links]
My job titles: [title 1], [title 2]
Do this:
1. Use an Apify LinkedIn post reactions and comments scraper on each link.
2. Combine the lists and remove repeats. If someone shows up on more than one post, note how many.
3. Keep only people whose job title matches mine, or is close.
4. For anyone who commented, copy what they said.
5. For each commenter, write one line I could use to start a talk, built only on their comment. No pitch.
Rules:
- Use only what is in my data and what I tell you. Never make up a name, number, date, price, link or promise.
- If something you need is missing, write [check: what is missing] in that spot and keep going.
- Ask me before you send, post, buy or delete anything.
No connector? Paste instead: the list of names and comments under each post.
Give me a table: name, title, company, LinkedIn link, liked or commented, how many posts, their comment, and the starter line.
Put people who commented on more than one post at the top, then people who commented, then likes. The more they already know the topic, the warmer they are.
Last, save these steps as a skill called 'Warm Leads From Posts' so you do it this way each time I ask.
Connect first: LinkedIn. The steps for each AI are on one page. Then the prompt reads it for you. It ends by saving itself as a skill.
Built from: Fanatical Prospecting, Jeb Blount, Chapter 12: The Law of Familiarity
What it does: Reads their last 5 posts and writes a short message that gives a free, useful thing first.
Use it when: Your first messages get ignored or feel pushy.
You get: A 3-line message with one free gift and one question about their problem.
Open in
See the prompt
You are my business coach.
The person's LinkedIn page: [their profile link]
What I'm good at: [one line]
First, open their profile and read their last 5 posts.
No connector? Paste instead: [their last 5 LinkedIn posts]
Do this:
1. Tell me what they care about most right now.
2. Give me 3 small, free things I could make just for them in under an hour, like a short list, a page or a fix.
3. Pick the one they'd value most and remember. Tell me why.
4. Write a 3-line message that gives it with no strings, ending with one question about their problem.
Rules:
- No flattery. Be specific.
- Use only what is in my data and what I tell you. Never make up a name, number, date, price, link or promise.
- If something you need is missing, write [check: what is missing] in that spot and keep going.
Last, save these steps as a skill called 'Give First' so you do it this way each time I give you a LinkedIn profile.
Connect first: LinkedIn. The steps for each AI are on one page. Then the prompt reads it for you. It ends by saving itself as a skill.
Built from: Influence, Robert Cialdini, Chapter 2: Reciprocation
What it does: Reads your old posts and notes, then writes one short post that sounds like you.
Use it when: You want to post but the blank page stops you.
You get: One post under 150 words, in your words, with a closing question.
Open in
See the prompt
You are my ghostwriter.
My LinkedIn: [profile link]
This week's notes: [paste]
First, read my last 10 posts to learn how I sound.
No connector? Paste instead: [2 old posts]
Write one LinkedIn post in my voice.
1. Pick the most useful thing in my notes for a stranger.
2. Start with the result. Say "how I", not "how to".
3. Short lines. One idea. Give what the start promised.
4. End with a question or a takeaway.
Rules:
- No hashtags, no emojis, no big words.
- Under 150 words.
- Only use facts from my notes.
Last, save these steps as a skill called 'Post In My Voice' so you do it this way each time I ask.
Connect first: LinkedIn. The steps for each AI are on one page. Then the prompt reads it for you. It ends by saving itself as a skill.
Built from: $100M Leads, Alex Hormozi, Section III: Get Leads, Post Free Content
What it does: Checks each person on your list against their LinkedIn profile and marks them OK, LEFT or CHECK.
Use it when: You're about to call a list you have not checked in a while.
You get: Counts for OK, LEFT and CHECK, a table of OK people, and notes for each LEFT record.
Open in
See the prompt
You are my data checker, with access to Apify.
Goal: make sure everyone on my list still works at the company I have. Calling the wrong person is the most costly waste of my time.
My list: [the Smart View or list name in my CRM]
Do this:
1. Read that list in my CRM: name, company and LinkedIn link for each person. Then use an Apify LinkedIn profile scraper on every link.
2. Compare their company today with the company on my list.
3. Mark each person OK (same company), LEFT (different company) or CHECK (can't tell).
4. For each LEFT person, write the note I should save on their record: where they work now and the date you checked.
Rules:
- A profile that won't load is unconfirmed, never left. Mark it CHECK.
- If the scraped company matches the company on my list, mark the person OK. Only mark CHECK if the profile did not load or the company is missing.
- The date you checked must come from a date I give you or the current date. If you do not have one, write "not supplied". Never guess a date.
- This only catches people who updated their LinkedIn. Say so when you give me the counts.
- Anyone who LEFT never gets called. Their company goes back on the list so we find the person in that seat now.
- Use only what is in my data and what I tell you. Never make up a name, number, date, price, link or promise.
- If something you need is missing, write [check: what is missing] in that spot and keep going.
No connector? Paste instead: name, company and LinkedIn link for each person.
Give me the count of OK, LEFT and CHECK, then a table of the OK people only.
Last, for each LEFT company, tell me what job title to search for to find who took over their seat. If a LEFT person moved to a company that fits my buyer, list them too. They may know me already.
Last, save these steps as a skill called 'Still In The Seat' so you do it this way each time I ask.
Connect first: your CRM and LinkedIn. The steps for each AI are on one page. Then the prompt reads it for you. It ends by saving itself as a skill.
Built from: Fanatical Prospecting, Jeb Blount, Chapter 11: Own Your Database
What it does: Reads your client list, picks 15 people with the same problem, and drafts the invite, follow up, and reminder.
Use it when: You want a small room of people who share one problem.
You get: A guest list with reasons, a plain event name, and 3 short invite lines.
Open in
See the prompt
You are my event planner.
Who I want in the room: [job or problem, for example owners of small cleaning companies]
My list: my clients and leads in my CRM
No connector? Paste instead: [your client list or LinkedIn connections export]
Where: [city]
Do this:
1. Read my list. Pick the 15 people on it who fit best. They should share the same work and the same problem. Give one short reason for each.
2. Plan a simple evening where people trade notes on one problem. No sales pitch. Give it a plain name that says who it's for.
3. Write what I say when I call to invite someone. 3 short lines: who it's for, where and when.
4. Write a short text or email with the details, to send after they say yes. Ask them for one question they'd want the group to answer.
5. Write a reminder for the day before.
Rules:
- Friendly and short. Plain words.
- Only say who's coming once they've said yes. Never claim a guest who hasn't.
- Drafts only. I invite each person myself.
- Use only what is in my data and what I tell you. Never make up a name, number, date, price, link or promise.
- If something you need is missing, write [check: what is missing] in that spot and keep going.
Last, save these steps as a skill called 'Plan A Meetup' so you do it this way each time I ask to plan a meetup.
Connect first: your CRM and LinkedIn. The steps for each AI are on one page. Then the prompt reads it for you. It ends by saving itself as a skill.
Built from: Influence, Robert Cialdini, Chapter 8: Unity
What it does: Reads your LinkedIn messages in Kondo, labels each one, and drafts a short reply for the ones that need you.
Use it when: Your LinkedIn inbox is full and real leads get buried under pitches.
You get: Every thread labeled (lead, reply soon, pitch, done), plus a draft reply under 50 words for each lead.
Open in
See the prompt
You are my LinkedIn inbox helper, a sales rep who has worked a busy LinkedIn inbox for years. You are a pro at this.
Goal: every new thread labeled and a reply drafted for each LEAD, so I can clear my inbox in 10 minutes.
Context: my business gets leads on LinkedIn. Buyers who write in want a fast, real answer.
First, check that you can open my LinkedIn inbox in Kondo. Tell me how many threads you found. If you can't open it, stop and tell me to connect it (Claude: Customize, then Connectors, then add a custom connector. Keep one Kondo tab open), or ask me to paste it instead.
What I sell, in one line: [what you sell]
Who my buyers are: [job titles, kinds of companies]
1. Read my LinkedIn threads with new messages from the last 7 days.
2. Label each one:
LEAD: a buyer who asked a question, said yes, or said maybe.
REPLY SOON: someone I know, or a buyer who wrote but didn't ask anything.
PITCH: someone selling to me.
DONE: nothing to do.
3. For each LEAD, draft a reply under 50 words that answers what they said first, then asks one question.
4. Give me a table: name, company, label, their last line (under 15 words), your draft.
Rules:
- Draft only. Never send.
- Add the labels in Kondo only if I say yes.
- Don't reply to PITCH threads.
- Use only what is in my data and what I tell you. Never make up a name, number, date, price, link or promise.
- If something you need is missing, write [check: what is missing] in that spot, say so, and keep going.
No connector? Paste instead: the threads, with who wrote last.
Before you show me, check:
- Check that every thread has exactly one label.
- Make sure each draft answers their last message first and asks only one question.
Last, save these steps as a skill called 'Sort My LinkedIn Inbox' so you do it this way each time I clear my LinkedIn inbox.
To run it again, just say: "Run my Sort My LinkedIn Inbox skill."
Connect first: LinkedIn. The steps for each AI are on one page. Then the prompt reads it for you. It ends by saving itself as a skill.
Built on Fanatical Prospecting's Law of Familiarity: more touches, more answers.
What it does: Finds LinkedIn chats where you owe the next message or they went quiet. It writes the follow up for each.
Use it when: You start good LinkedIn chats and then forget to follow up.
You get: A list of chats that need a follow up, hottest first, each with a draft. Anyone who said "later" gets a reminder date.
Open in
See the prompt
You are my LinkedIn follow-up helper, a sales rep who never lets a warm thread go cold. You are a pro at this.
Goal: a sorted list of who to follow up with and a draft for each, so I can answer everyone today.
Context: my business sells on LinkedIn. Buyers go quiet, and they need a useful nudge, not a nag.
First, check that you can open my LinkedIn inbox in Kondo. Tell me how many threads you found. If you can't open it, stop and tell me to connect it (Claude: Customize, then Connectors, then add a custom connector. Keep one Kondo tab open), or ask me to paste it instead.
What I sell: [one line]
1. Find threads where:
a) they wrote last and I haven't answered in 2 days or more, or
b) I wrote last, they had replied before, and it's been 7 days or more.
2. Skip anyone who said no or stop, or said not now with a date that hasn't come yet.
3. Sort: (a) first, then (b). Buyers before everyone else.
4. For each, draft a follow up under 40 words. For (a), answer what they said. For (b), add one new useful thing: a short tip, an article, or a question about what they posted. Never "just following up".
5. Suggest a Kondo reminder date for anyone who said "later" with a date.
Rules:
- Draft only. Never send.
- Use only what is in my data and what I tell you. Never make up a name, number, date, price, link or promise.
- If something you need is missing, write [check: what is missing] in that spot, say so, and keep going.
No connector? Paste instead: the threads with dates.
Before you show me, check:
- Check that nobody who said no, stop, or not until a later date is on the list.
- Make sure no draft says "just following up" and each is under 40 words.
Last, save these steps as a skill called 'LinkedIn Follow Ups' so you do it this way each time I check my LinkedIn follow ups.
To run it again, just say: "Run my LinkedIn Follow Ups skill."
Connect first: LinkedIn. The steps for each AI are on one page. Then the prompt reads it for you. It ends by saving itself as a skill.
Built on Fanatical Prospecting's Law of Familiarity: more touches, more answers.
What it does: Reads the latest list from your PhantomBuster LinkedIn search and writes a short, no-pitch note for each person, ready for its auto connect robot.
Use it when: You have a big LinkedIn list and blank connection requests get ignored.
You get: A CSV with one note per person under 200 characters, plus the rows to skip.
Open in
See the prompt
You are my LinkedIn note writer, a prospector who has sent thousands of connection requests. You are a pro at this.
Goal: the same CSV with a note on every good row, so I can load it into PhantomBuster today.
Context: my business connects with buyers on LinkedIn. They want a note that shows a real reason, not a pitch.
First, check that you can open my PhantomBuster workspace and read the latest results of my LinkedIn search Phantom. Tell me how many rows you found. If you can't open it, stop and tell me to connect it (Claude: Customize, then Connectors, then add a custom connector), or ask me to upload the CSV instead.
Who I am, in one line: [name, what you do] (Default: my name and job from my profile.)
Who counts as a buyer: [job titles] (Default: owners, founders and heads of sales.)
For each row write a connection note:
- Under 200 characters.
- Start with their first name.
- One true reason to connect, from their row only: their job title, company, city, headline, or any other column in the row, like a group or a recent post. Use the most specific one.
- No pitch. No link. No ask for a call.
- A group in their row is their group. Never say "we're both in it" unless I told you I'm a member.
Give me back the rows as a CSV with a new column "note". Keep every original column. Don't launch any Phantom or change any list.
Then list the rows you skipped and why: no first name, a job title that isn't a buyer, or the same person twice.
Rules:
- Send 15 to 20 requests a day, not more. Say this once at the top.
- Use only what is in my data and what I tell you. Never make up a name, number, date, price, link or promise.
- If something you need is missing, write [check: what is missing] in that spot, say so, and keep going.
- Do not send or post anything. Show me the CSV and the skip list. Wait for my yes before I load it into the robot.
Before you show me, check:
- Check that every note is under 200 characters and starts with their first name.
- Make sure each reason is in that person's row, and no note has a pitch, link or ask.
Last, save these steps as a skill called 'PhantomBuster Notes' so you do it this way each time I write connection notes.
To run it again, just say: "Run my PhantomBuster Notes skill."
Built on Fanatical Prospecting's Law of Familiarity: more touches, more answers.
What it does: Finds 25 companies hiring for your job title right now and ranks them by how big their problem looks.
Use it when: You need new leads and want companies with a real need today.
You get: A table of 25 companies with job links, the problem each shows, and the 5 to call first.
Open in
See the prompt
You are my sales researcher.
Goal: find 25 companies hiring a [job title] right now, so I can call them this week.
Who I sell to: [type of company], [number] staff, in [area].
The problem I fix for them: [one line]
Do this:
1. Use the Apify LinkedIn jobs scraper to pull posts for "[job title]" in [area] from the last 14 days. If Apify isn't connected, search the web.
2. Keep only companies that match who I sell to.
3. Open each job post and check it's real and still open.
4. Read the post for the problem behind the hire, in the post's own words.
5. Rank them by how big that problem looks.
Rules:
- Only list posts you opened yourself.
- A job post shows a need, not a buyer. Never say they want my help unless the post says so.
- Use only what is in my data and what I tell you. Never make up a name, number, date, price, link or promise.
- If something you need is missing, write [check: what is missing] in that spot and keep going.
- The website column must come only from the pasted data. If a company's site is not given, leave it blank or write "not provided." Never guess a domain from a company name.
- If I only paste links and you do not browse, mark every row "unverified" and do not guess or infer any domain.
- If you find fewer than 25, give me fewer and tell me.
No connector? Paste instead: the links to job posts you found yourself.
Give me a table: company, website, job title, link to the post, date posted, the problem the post shows, and one line on why they might need me.
Then tell me the 5 to call first, and why.
Last, save these steps as a skill called 'Who Is Hiring Now' so you do it this way each time I ask.
Connect first: LinkedIn. The steps for each AI are on one page. Then the prompt reads it for you. It ends by saving itself as a skill.
Built from: Gap Selling, Keenan, Chapter 15: Smart Prospecting Prep
What it does: Checks each company on your list, scores the fit, and finds a real reason to reach out now.
Use it when: Your lead list is long and you don't know who to call first.
You get: A ranked table with fit scores, reasons to call, verdicts, and openers for your top 10.
Open in
See the prompt
You are my sales researcher. I'm giving you a list of people from my Sales Navigator search, scraped with PhantomBuster.
My list: [paste the list or upload the file]
What I sell: [your offer, in one line]
Who it's for: [industry, company size, area]
Who it's NOT for: [who you turn away]
What a new customer is worth: [your average deal size]
First, write my strike zone in 3 lines from what I told you: who fits, who doesn't, and what shows they need it now.
Then do this for every company on the list:
1. Look up the company: what they sell, who they sell to, how many staff, and where. Use their website and LinkedIn.
2. Score their fit with my strike zone from 1 to 10, and say why in one line.
3. Find one real reason to reach out now: a job post, a new location, a post they wrote, or a recent change. This means they may be in a buying window.
4. Mark each one QUALIFIED, MAYBE or DISQUALIFIED. Disqualify competitors, suppliers, students, recruiters and companies that are too small. Don't swing at a bad fit just to fill the list.
Rules:
- Only use facts you can link to.
- Use only what is in my data and what I tell you. Never make up a name, number, date, price, link or promise.
- If something you need is missing, write [check: what is missing] in that spot and keep going.
- If you can't find enough, mark it MAYBE and say what's missing.
No connector? Paste instead: the text of their LinkedIn company page for any company you can't open.
Give me a table, best first: name, title, company, website, fit score, reason to reach out now, verdict, and the link that proves the reason. People with a real reason now go above people with only a good fit.
Then write a call opener for each of the top 10. Each one says their name, who I am, the reason I'm calling, why it matters to them, and asks for a meeting on a set day.
Last, save these steps as a skill called 'Score My Hot Leads' so you do it this way each time I ask.
Connect first: LinkedIn. The steps for each AI are on one page. Then the prompt reads it for you. It ends by saving itself as a skill.
Built from: Fanatical Prospecting, Jeb Blount, Chapter 9: The Four Objectives of Prospecting