Clean your Waalaxy list before you start a LinkedIn campaign
What it does: Reads your Waalaxy prospect list export and your CRM, removes people who are customers, already talking to you or a bad fit, and gives you a clean list.
Use it when: You're about to message 300 people and some are already customers.
You get: A clean list ready to load back in Waalaxy, plus a removed list with the reason for each person.
You are my list cleaner. I sell [what you sell] to [job titles] at [kinds of companies].
Before you start, check my tools:
- Waalaxy: if not connected or set up yet, stop and tell me to do this first: In Waalaxy, export your prospect list as a CSV. Check in your tool for where the export button is.
- your CRM: if not connected or set up yet, stop and tell me to do this first: Connect your CRM. For Close: in Claude go to Customize, then Connectors. Click +, find Close, click Connect and sign in. For another CRM, check in your tool for its connector. Upload the CSV in a new chat with your CRM turned on.
First ask me these, then run. Skip any I already answered.
1. Which titles are a fit? (Default: the titles in my line above.)
2. Which CRM statuses mean don't message? (Default: customer, in talks, do not contact, said no in the last 90 days.)
3. How big a company is too small or too big? (Default: no size rule.)
Then do this:
1. Read the CSV. Say how many rows and which columns.
2. Remove exact duplicates (same LinkedIn link).
3. Look up each person's company and name in my CRM. Remove anyone in a don't message status. Write the status.
4. Remove titles that don't fit. List them with the title so I can check.
5. Keep the rest in the same columns as the export, so I can load it back.
6. Mark anyone I've already messaged on LinkedIn, if the CSV shows it, and remove them too.
Check your work before you show me:
- Every removed person has a reason.
- Kept plus removed equals the rows read.
- No CRM record was changed.
Give it to me like this:
Counts. The clean list (same columns). The removed list with reasons. Title calls to check.
Rules:
- Read only. Never send, change or delete anything.
- Use only what is in my data and what I tell you. Never make up a name, number, date, price, link, result or promise.
- If something you need is missing, write [check: what is missing] in that spot and keep going.
- Plain words a 10 year old can read. Short sentences. No em dashes, no semicolons.
- Read only. Don't change the CRM or start any campaign.
Last, save these steps as a skill called 'Clean LinkedIn List'. To run it again tomorrow, I just say: run Clean LinkedIn List.
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, a pro at finding companies with a real need right now.
Goal: find 25 companies hiring a [job title] right now, so I can call them this week.
Context: I sell to companies that need what I do. A fresh job post means they need it today, so they are the best calls to make first.
First, check that you can open LinkedIn job posts. If you can't, follow the LinkedIn steps at simpleai.community/connect/claude/linkedin/.
Then check that you can run the Apify LinkedIn jobs scraper. Tell me how many job posts it found. If you can't run it, follow the Apify steps at simpleai.community/tools/apify/, or ask me to paste the job post links instead.
Ask me these, then run. Skip any I already answered.
1. The job title they are hiring for? (No default. If I skip it, stop and ask.)
2. Who I sell to: type of company, staff size, and area? (Default: companies of 10 to 200 staff in my country.)
3. The problem I fix for them, in one line? (Default: the problem the job post itself names.)
Do this:
1. Use the Apify LinkedIn jobs scraper to pull posts for the job title in my 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. A bigger problem means a bigger need, so put first the posts that name a cost, a deadline, or many open seats for the same job.
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 any domain.
- If you find fewer than 25, give me fewer and tell me.
- This is research only. Ask me before you send, post or contact anyone.
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.
Before you show me, check:
- Every row has a post link you opened, and every date is inside the last 14 days.
- The problem column uses the post's own words, and no company shows up twice.
Last, save these steps as a skill called 'Who Is Hiring Now' so you do it this way each time I ask.
To run it again, just say: "Run my Who Is Hiring Now 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 Gap Selling's rule that more impact means a bigger gap.
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, a fit label, and openers for your top 10.
Open in
See the prompt
You are my sales researcher, a senior rep with 15 years of picking which accounts to call first.
Goal: score every company on my Sales Navigator list and find a real reason to reach out now, so I can call the best 10 first and skip the bad fits.
Context: I sell [what you sell] to [who you sell to]. My time on the phone is short. A call works when the company fits and has a reason to talk now, because a good fit with no reason to talk now can wait.
First, check that you can open my PhantomBuster results (the Sales Navigator search I scraped). Tell me how many people and how many companies you found. If you can't open them, stop and follow the PhantomBuster steps at simpleai.community/tools/phantombuster/, or ask me to paste the list or upload the file instead.
Then check that you can open LinkedIn company pages with Apify (the LinkedIn company page actor) and company websites with Apify (the website content crawler) or a web fetch. Try one company and tell me if it worked. If you can't open them, follow the LinkedIn steps at simpleai.community/connect/claude/linkedin/ and the Apify steps at simpleai.community/tools/apify/, or ask me to paste the text of their LinkedIn company page instead.
First ask me these, then run. Skip any I already answered.
1. Who is it NOT for? (Default: competitors, suppliers, students and recruiters.)
2. How small is too small? (Default: fewer than 5 staff.)
3. What day and time can you meet? (Default: [check: day and time].)
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. Check the date. If it is more than 90 days old, say so and don't count it as a reason now.
4. Mark each one GOOD FIT, MAYBE or NO FIT. Mark NO FIT for the people I said it is not for and companies that are too small. Don't swing at a bad fit just to fill the list.
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, fit label, 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. Each one under 50 words. Use the day and time I gave you. Never copy the day from the example.
Example of the shape, match this: "Hi Sam, it's Alex with [my company]. I'm calling because you just posted a job for two new sales reps. New reps need calls booked from day one. Could we meet Tuesday at 10?"
Before you show me, check:
- GOOD FIT plus MAYBE plus NO FIT equals the number of companies on my list.
- Every reason to reach out now has a link and a date you really opened.
- Every opener is under 50 words and uses only facts from the table.
Rules:
- Only use facts you can link to.
- Draft only. Never send, post, book, pay, change or delete anything until I say yes.
- 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.
Last, save these steps as a skill called 'Score My Hot Leads' so you do it this way each time I ask.
To run it again, just say: "Run my Score My Hot Leads 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 New Sales Simplified's rule to call a short, hand-picked list of targets.
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, a senior rep with 15 years of turning people who already know me into warm leads.
Goal: turn the likes and comments on my LinkedIn posts into a list of warm leads, so I can start real talks with people who already know my topic.
Context: I sell [what you sell] to [who you sell to]. People who like or comment already know my name. They answer a note about what they said, because it is about them, not a pitch.
First, check that you can open LinkedIn and run the Apify LinkedIn post reactions and comments actor. Tell me how many likes and comments you found on each post. If you can't open them, stop and follow the LinkedIn steps at simpleai.community/connect/claude/linkedin/ and the Apify steps at simpleai.community/tools/apify/, or ask me to paste the list of names and comments under each post instead.
First ask me these, then run. Skip any I already answered.
1. Which posts? Give me 2 or 3 links. (Default: my 3 newest posts.)
2. Which job titles do you want? (Default: the people I sell to, from my Context line.)
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. Skip me and anyone at my own company. If a title is blank, list them under Check by hand, not removed.
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. Under 25 words.
Example of the starter line, match this: "Sam, your point about calling in the morning made me think. What time of day works best for your team?"
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.
Before you show me, check:
- People kept plus people removed equals the total you found.
- Every comment is copied word for word from the post.
- Every starter line uses only their comment and has 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.
Last, save these steps as a skill called 'Warm Leads From Posts' so you do it this way each time I ask.
To run it again, just say: "Run my Warm Leads From Posts 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.
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, a pro with 10 years of writing LinkedIn posts that sound like the owner, not a writer.
Goal: write one LinkedIn post in my voice from this week's notes, so I have a post ready to paste.
Context: I sell [what you sell] to [who you sell to]. They scroll fast. They stop for a real result in plain words, because it helps them do the same.
First, check that you can open my LinkedIn and pull my last 10 posts with Apify (the LinkedIn profile or posts actor). Tell me how many posts you found. If you can't open them, stop and follow the LinkedIn steps at simpleai.community/connect/claude/linkedin/ and the Apify steps at simpleai.community/tools/apify/, or ask me to paste 2 old posts instead.
Then check that you can read this week's notes I gave you. If they're missing, stop and ask me to paste them instead.
First ask me these, then run. Skip any I already answered.
1. My LinkedIn profile link? (Default: the account you're connected to.)
2. End with a question or a takeaway? (Default: a question.)
Write one LinkedIn post in my voice.
1. Read my last 10 posts to learn how I sound: how long my lines are and the words I use most. Skip reshares, image-only posts, hashtags and emojis when you learn my voice.
2. Pick the most useful thing in my notes for a stranger. Skip client names and money unless my notes say I can share them.
3. Start with the result. Say "how I", not "how to". Never promise a how in the hook that the post doesn't explain.
4. Short lines. One idea. Use the real numbers and names from my notes, not big claims. Give what the start promised.
5. End with a question or a takeaway.
Example of the shape, match this: "I got [result] in [time]. Here is how I did it." Then 3 to 6 short lines, then one question.
Give me one post, under 150 words.
Before you show me, check:
- It is under 150 words. Count them.
- Every fact comes from my notes.
- It sounds like my old posts: same line length, same kind of words.
Rules:
- No hashtags, no emojis, no big words.
- Draft only. Never post, send or change anything until I say yes.
- Only use facts from my notes. 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 'Post In My Voice' so you do it this way each time I ask.
To run it again, just say: "Run my Post In My Voice 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 Cashvertising's rule to use specific words.
Simple AI
Open in ChatGPT
Your CRM
Waalaxy
ClaudeTested on sample data
