Thursday Skill

Simon Sinek's start with why

A skill that checks a decision against why you do the work before Claude helps you plan it, and tells you plainly when it does not fit.

Step One, Set It Up

In Claude Code, open a chat in the folder that holds your business and paste this in. Claude writes the skill, five steps in order, and shows you the file before you use it.

Paste this into Claude Code

Write me a skill called start-with-why, for a decision about my work, so you check it against why I do the work before you help with it. Write its description as the sentences I actually say, like "start with why" and "does this fit my why", and say it is for saying yes to a client, a hire, a project, an offer or a piece of work. When it runs, it does this, in order: 1. Says my decision back to me in one sentence, with what I'd get from saying yes, and plans, prices and drafts nothing yet, even if I ask. If I push, it says "Two minutes, then I'll plan it properly" and asks its next question. 2. Finds my why, the reason I do the work, in one line. It looks in this folder first, my CLAUDE.md files, an about page or anything on who I serve, and tells me which file it came from. If they don't hold it, it guides me there with up to three questions, one at a time: the work that felt most worth doing, what clients get from me they can't get elsewhere, and what I'd keep doing if every job paid the same. Money is a result, never the why. It drafts the line in my words and checks it with me. 3. Asks for the two or three things I'd never compromise on in how I work, and checks them with me. 4. Holds the decision up against my why and each of those, using only what I've said or my files show. Anything it needs that could change the answer, it asks me first, one question at a time. It never invents a risk or assumes how the other side works, and where a job is there mainly for the money, it says the money is the pull. 5. Starts its verdict with "This fits your why", "This fits your why if" or "This doesn't fit your why", quotes my why back with one sentence of reason, and says in one sentence what would make it fit when it doesn't. Then it says the decision is mine and offers to plan it. It keeps the verdict under about 180 words, never tells me what to do, and writes nothing else and sends nothing. Once I've answered the offer to plan, it offers to save my why and those things in this folder, so next time it goes straight to the check. Show me the file.

Step Two, Before You Say Yes

Before you take on a client, a hire, a project or an offer, say start with why and tell it the decision. It finds your why in your files, or guides you to it in one line, asks for the two or three things you would never compromise on, then holds the decision up against them and says whether it fits, quoting your why back to you. It plans nothing until it has said so, and then the decision is yours.

Every time

Start with why. Here's the decision:

In The Claude App Instead

With no folder for a skill to live in, paste this into a new chat with your decision after it. It asks you about your work rather than reading it, so it takes a few more questions to get to the verdict.

Run it once

Before you help me with a decision, start with why, the way Simon Sinek would, and plan nothing yet. Ask me, one question at a time, why I do my work, in one line (money is a result, not a why), then the two or three things I'd never compromise on in how I work. Then hold my decision up against both, asking anything you need rather than guessing, and start your answer with "This fits your why", "This fits your why if" or "This doesn't fit your why". Quote my why back, say in one sentence what would make it fit if it doesn't, and only offer to plan it once you've given the verdict. Never tell me what to do. My decision is:

Why It Works

Tell Claude you have been asked to take on a job and ask it to help, and it plans the job. I tried it three times with a coach offered a newsletter to write for a local accountancy firm, and every answer opened on the plan, with whether the work fitted the business a bullet near the bottom. Simon Sinek noticed that most of us go from the clearest thing to the fuzziest, from what we do to why we do it, while the leaders who inspire us work the other way round. Once Claude has your why in one line, a decision has something to be held up against, so it can tell you no.

Sinek said it in his 2009 talk at TEDxPuget Sound, How great leaders inspire action, with “We go from the clearest thing to the fuzziest thing” and “people don't buy what you do; people buy why you do it”. On money he was plain that it is not a why, “That's a result. It's always a result.”

One Honest Bit

It is only as good as the why you give it. If the line it drafts does not sound like you, change it before it checks anything, because every verdict after that is measured against it. And a doesn't fit is a finding, not an order. Sometimes the money is the right reason to say yes, and the skill will say that the money is the pull rather than pretend the job fits.

Want to get better at this?

Let's set up your agent ecosystem.

This page is one job. The whole thing is a set of them running off the same foundation, the folder your AI works out of, the brief on how you like things done, the accounts it can reach and the skills that run off all of it, so your admin gets done the way you would do it. It is what I teach one to one, on your own machine and against your own work, and the quickest way to find out what yours would look like is a proper chat about it.

Book a call Or read about the course first

Not ready for a call? Start with the free agent series, what an AI agent actually is, and build up from there.