AIMM Session — October 23, 2025: Claude Skills Launch and the Maintenance Cost Framework

30-Second Summary

Session centered on Claude Skills, Anthropic’s newly released format for packaging and deploying reusable AI capabilities. Lou walked the group through building a complete multi-role writing team — researcher, strategist, writer, editor, publisher, orchestrator — all housed in a single skill with self-evolving memory layer. Sharp discussion about when to adopt new tools, landing on: factor in the full maintenance cost before you commit.

Claude Skills: Build Once, Deploy Everywhere

Skills are a folder structure with a skill.md file containing front matter plus supporting instructions. You zip it up, drop it into Claude’s Capabilities settings, and Claude treats it as a system-wide plugin.

One practical gotcha: you can only have one skill per zip file.

The Real Question: Why Did This Go Viral?

Lou and Donald both had the same reaction: “is that it?” Practitioners who’ve been building with Claude Projects and custom GPTs for two years have essentially been doing skills all along.

Hot take: Skills are less about new capability and more about making prompts first-class citizens of the Claude OS. It’s the App Store play.

The Self-Evolving Writing Team

Lou had built an “AIM Writing Team” skill that chains six sub-roles: Researcher, Strategist, Writer, Editor, Publisher, and an Orchestrator that sequences them. Each role scores its own output, passes a summary to the next stage, and writes improvements to a persistent JSON memory file so the skill gets better with each run.

The live demo: ask it to produce a 1,000-word article and it runs the full pipeline unprompted. Call a specific sub-role by name and the orchestrator routes to just that one.

The Maintenance Cost You’re Not Calculating

Lou invoked T. Harv Eker’s rule: add 30–40% annually on top of any purchase price for maintenance, downtime, integration work. Warren Buffett’s frame: that $100K purchase, compounded at 20% over 10 years, is actually a $2M decision.

Applied to AI tooling: “If I’m a solopreneur, the question is always — if I were to call a client to make an offer instead of spending my time on this, what’s going to be better for my business? And 90% of the time, it’s talk to the client.”

Mazie (Johnson & Johnson background): “If the line was working and producing what it was supposed to produce, you didn’t touch it.” Kasimir backed it up with a Nokia story — a printer driver update for a label-making machine stopped an entire phone factory.

Framework: be an eager early adopter for experimentation, but a deliberate late adopter for deployment.

Community Corner

Bally kicked off with a story: a woman named Wendy — an English coach in Thailand — uses only GPT-4o custom GPTs, refuses to engage with prompt engineering, and charges £600/month recurring to clients. Six months in, she has recurring clients and a portable business. “She’s kicking ass — and what we’re doing here is so much more than that.”

The story landed as a grounding reminder. You don’t need the full stack to build a valuable, repeatable service. Someone simpler than you is already charging for it.

Try This Week

Build your first Claude Skill as a personal prompt library entry. Pick one task you do repeatedly — a weekly report, a client proposal, a content outline — and package it as a skill. Write a skill.md file with front matter and your best prompt as the instruction body. Zip the folder, upload it in Claude’s Capabilities settings, then start a fresh chat and see if Claude activates it without being told to.

Time investment: 30 minutes. The real test: does Claude trigger it correctly on a follow-up session?