SoN 2.42: Turn frameworks like the Eisenhower matrix into an AI skill


VOL 2, ISSUE 42 · NOVEMBER 2026

Frameworks are all around, and they've been in use for ages. Some of my favourites are the five whys, where you ask “why?” until you reach the cause of a problem, and the Eisenhower matrix, which sorts your tasks by how urgent and how important they are. There's no reason why you can't use these in your daily workflows to help you keep organised or to troubleshoot problems.

If you don't know one for your job, ask your AI what established methods exist for it, and pick one that's widely used in business and whose foundations haven't changed.

Here's how you do it. You turn the method into a skill, a set of instructions your AI keeps and follows, so you don't have to explain the method again. These screenshots are from ChatGPT, using the Eisenhower matrix.

1. Find the method's Wikipedia page, start a new chat, and paste in the link with: “I need a skill for this. Ask me questions one at a time before you write it.”

2. Answer each question as it comes, so the AI doesn't make a decision on your behalf.

3. When it has asked its questions, ask it to write the skill as instructions you can paste into a ChatGPT project, a workspace that keeps its own instructions and chats together. To make one, open Projects from the sidebar menu and click Create. Then open the project's settings and paste the instructions into the Instructions box. If ChatGPT says they're over its 8,000-character limit, ask it to shorten them to fit.

4. Start a chat in that project and give it next week's list.

You likely won't get it right first time; it's going to need a little bit of tweaking here and there.

Also in this week's issue: what to ask the companies whose software you rely on, now that OpenAI's new security model has found 81 serious flaws in Firefox, and how to keep your website out of Google's AI summaries.

Your questions are coming in

Some good use cases and questions have been coming in, and I'll be featuring them in an upcoming newsletter. If you haven't filled in the reader survey yet, it asks how you use AI at work and what you're stuck on.

Take the survey →

Working with AI

Create an AI skill from frameworks like the Eisenhower matrix Interactive

Revisit this week's topic in the full post, with step-by-step frames and a click-through comparing one question at a time with all at once.

Read the post →

What to do when Claude says it's fixed, but it isn't Interactive

An AI's fix can work on the examples it was checked on and yet still fail on new ones. A new study shows one reason it happens, and how to test a fix yourself before you rely on it.

Read the post →

Security and Risk

GPT-6 Cyber found 81 Firefox flaws: what to ask suppliers

Your business relies on software that other companies have to patch. OpenAI says GPT-6 Cyber, its new security model, found 81 high-severity flaws in Firefox. Two weeks earlier, attackers were using flaws in PHP, the language a lot of websites run on, within days of the fixes coming out. Part 2 of my series “AI Finds the Flaws. Who Fixes Them?” covers what to ask your suppliers while a fix is on its way.

Read part 2 →

Guides

What is a context window? Claude, ChatGPT and Gemini sizes

When a long chat stops following an instruction you gave it at the start, one possible cause is the context window: how much a single chat can hold. The guide shows the sizes in Claude, ChatGPT and Gemini, what fills them, and what to do when a chat drops an instruction.

Read the guide →
Jim Christian, drawn in ink

Book a discovery session

Just starting out with AI, or trying to find a way into AI enablement inside your organisation? Book a 60-minute AI discovery session at jimchristian.net/discovery and let's have a chat about what you can make possible.

Learn more and book →

The Industry

Keep your site out of Google's AI Overviews and AI training Interactive

Google can both summarise your website in its AI Overviews and use it to train AI. Your site is in both until you change a setting in Google Search Console and add rules to your robots.txt file.

Read the post →

Schools can't turn off Google's AI Overviews without losing Search

Schools that give students Google accounts can't switch off Google's AI Overviews for them without switching off Search. Students still need to learn to check sources: so who teaches them? Plus three questions parents can ask their schools.

Read the post →

Also this week

Claude Code hooks: what they are and when you need one

For Claude Code users: what a hook is, which of your rules need one, and how to set one up. Read it →

Claude Enterprise inference hooks: what they catch and miss Interactive

For companies on Claude Enterprise: what the new security check on each prompt catches, and what it misses. Read it →

Use your Claude, Codex and Cursor usage limits before they reset Interactive

For paid Claude, Codex and Cursor plans: what to hand over while you have allowance left, and what to do when you run short. Read it →

Reader challenge: do you know what lateral reading is?

A

Lateral reading is checking an unfamiliar website by leaving it: you open a new tab and search the open web before spending time on the page.

 

B

Lateral reading is skimming a long document by reading only the first sentence of each paragraph, to get the gist quickly.

See the answer in the glossary →

That's it for this week. If your team is working out what to do with AI, hit reply and tell me where you're stuck.

Jim

Jim Christian - Signal Over Noise

What I care about is helping people bring technology into their lives well — where it's genuinely needed, and where it can do the most good. Not tech for its own sake, not change to look modern. Sometimes that means AI; just as often it means something far simpler.The tech world is accelerating. This is my attempt to slow things down a little: to pick apart the hype and look for the reality and the truth in the messages — primarily around AI, and how it impacts us all.

Read more from Jim Christian - Signal Over Noise
A yellow robot beside an empty desk chair holds up a long paper scroll of numbered question cards looping across the floor, while a green dog trots off with card 7; a tray tagged GROUP 1 sits under a chalkboard that reads THREE AT A TIME.

VOL 2, ISSUE 43 · NOVEMBER 2026 One of my favourite ways of working with AI is to set Claude or ChatGPT a task, or a series of them, before I go and do other jobs around the house. But often when I come back to it, it's waiting on me with a list of questions about details I don't remember discussing. I've spent the last hour on something else, and now it wants answers. I've often typed back something close to this: "These are too many questions. I'm a human. I can't deal with this much...

A boxy yellow robot at a ticket kiosk labelled DATA HUB holds up a paper ticket marked TOKEN, with a canary in a cage and a scruffy green dog by the gate.

VOL 2, ISSUE 41 · NOVEMBER 2026 Part of my daily routine has changed in the last week, in that I'm talking more with Claude in voice mode on my school runs in the mornings. It beats the repetition of listening to the radio station, and it gives me more space to ramble and go down the odd rabbit hole as I question the morning headlines and look for topics of interest. When I get on to something I like and want to follow up on, I ask Claude to make sure that it's saved as a Google Doc that I...

A boxy yellow robot at a drafting table sketches a plan and points to small helpers at a supermarket checkout.

VOL 2, ISSUE 40 · OCTOBER 2026 In the last week I've been doing more hands-on training with teams of software engineers and marketers alike. No matter what your career or your skill level with AI, a lot of the core principles are the same, and many of them come back to breaking a job down before you hand it to AI. In this week's issue: use the biggest model to plan the job and smaller ones to do the work; a guide to how language models predict the next word, using a birthday song and a...