I sat down to help a teammate fix her workflow. She ended up fixing mine. You've seen the follow-up email skill I built. Last week a sales director reached out to sharpen hers. Generic emails, a few bullets pasted from the call, nothing a busy clinic owner would actually read. But she knew something I'd half-missed: ProShort (call recording tool) pushes all the call data into HubSpot's structured fields. Turns out we were both underusing the same data, from opposite ends. She was pulling a fraction of those fields. I was manually copy-pasting context that was already sitting in them. 95% of my manual step, gone. One conversation. Her output picked up my case study library and copywriting skill. My build dropped the copy-paste it never needed. I was too heads-down in my own version of the problem to see it. Took someone solving it from a different angle to surface the blind spot. ⸻ If you want the build side, here's how it actually works. Two skills, split on purpose. One fetches, one writes. The email skill you saw before is the writer. It takes the deal context and turns it into a case-study-anchored follow-up. But it was only ever as good as what I pasted into it by hand. The new piece I'm sharing below, deal context, is the fetcher. It pulls the call notes straight from the CRM, finds the right one, strips the duplicate copies and the empty stubs, and hands the writer a clean, structured intake. No paste. Why split them instead of one big skill? Leverage. The fetcher is shared infrastructure. The email skill uses it today; re-engagement and day-prep use the same one next. Build the context layer once, every writer on top of it gets smarter. It also makes them easy to fix. Last week I caught a bug in how it resolved "wrap Friday" — it pulled the wrong day. Fixed it in the fetcher alone, never touched the email skill. One job per skill means when something breaks, you know exactly where to look. A fetcher that gets the context right. A writer that does one thing well with it. That's the whole idea.

I’ve managed to convince one of my closest friends @David Chalk to come join us and learn stuff. I’m saying he’s player 2, because I was totally here first, but in real life where we’re pretty similar he keeps reminding me he is the original… Some of you may remember him as my friend who gives me “frank facts”. 🤣 I have promised to help build an ICM system to help him with some things and encouraged him to get some information directly from the source… because he’s totally going to want this built in a way that works for him. So, short version, please be kind to him and help me say hi. I am willing to open predictions on how long it takes for him to come up with good sim racing use cases for ICM while hanging out with this community… I don’t think it will take very long. Also… are we actually some kind of AI cult? Asking for a friend.

We talk about folders all day, but the folders are FOR something. I want to know what... 🎖️Bonus points: comment with the single most painful manual process in your industry. The best comp entries come from exactly those answers.

I demo'd the case study email skill I built with Claude in one of my company's Slack channels — the one running on +61 case studies and 5 competitor battle cards in Notion. One colleague immediately put time on my calendar: "I need to understand what you're doing with Claude because you're absolutely killing the game." Another wanted in. This morning, the VP of AI engineering commented on the Slack message. He asked if I'd shared it with the full sales team — told me to make it compatible with Gemini and GPT too. 1 hour later, my director of sales shouted me out on the weekly sales team meeting. Said he wanted me to train the whole team on it because he checked out my outreach and likes what I've been sending to prospects. Attaching the SKILL.md and the examples.md file below. Company-specific data is stripped — you can see what it references, not what's inside it. Genuinely curious: how are you building queryable databases for customer-facing interactions?

Hello Clief Notes Family! You may have noticed that I have not been posting as much. Some of that has been intentional, I was posting a lot and being number 1 feels good, but seeing others who work so hard to bring knowledge and value to our community shining feels good also! Another big portion of why I have not been posting is that I have been chasing my dream, I have applied to many ambassador programs and I have been ghosted or I have not been the right fit for them. This does not mean I was not the right fit to be an AI ambassador! I wanted to share, that today is different, today I have won, I have been accepted as Generative AI Ambassador in the company I work for! I will be giving workshops, writing articles and sharing my knowledge with my colleagues everyday, I will be Teaching about AI, 2 of my passions in one place! Teaching and AI. I wanted to thank you all for being one of the most supportive, inspiring, and impactful forces in my life. You have all given me the confidence, the energy, and the care I needed to keep pushing for this. We truly learn, grow, and win together 🤓💪🏆 With all of my heart! THANK YOU 🙏