The AI Switch Framework Change Coach skill for Claude

The problem this skill solves is familiar to anyone who has ever tried to drive a change through. Everyone nods in the meeting. The first week goes well. After three weeks it goes quiet, and the conclusion is that there wasn't enough buy-in. The Heath brothers say that conclusion is almost always wrong. The problem usually lies in an unclear direction, in too little motivation, or in an environment that makes the old behaviour easier than the new one. Three causes, three tracks, and that's exactly why the skill never settles for just one of the three.

This skill is written for anyone who needs to get something moving without having authority over it, or who has the authority and still no result: business owners pivoting their company, leaders who need to change culture, teams stuck in old patterns, and people who want to change a personal habit. Together with the rest of the skill library NL, we make it available for free from our AI and automation service, with no account and no sales email afterwards.

One thing you should know beforehand: the skill doesn't work if you just ask it for advice. The instructions include an explicit rule: no advice before the situation has been gathered. So expect questions before you get anything usable back. The first time round that feels slow, and that's exactly where the gain lies, because a change plan built on a misunderstood situation costs you a month.

The Rider is lost, not lazy. That's how the file opens the first track, and it's the most underrated diagnosis of the three. Ambiguity leads to procrastination. Eating healthier isn't a behaviour. More urgency isn't a behaviour. Being more customer-focused isn't a behaviour. As long as the goal stays abstract, the Rider has to work out afresh what's expected of him in every situation, and that costs exactly the willpower he doesn't have. Hence the technique Script the Critical Moves: describe the desired behaviour so specifically that a teenager could carry it out.

The Elephant doesn't need a plan but a feeling. Change that's only sold rationally gets no energy behind it. The skill puts it more sharply: people aren't lazy, they're tired or afraid. A spreadsheet proving that things need to be different is no answer to tiredness. What does work is shrinking the change so the Elephant isn't afraid of it, and making sure there's a credible first win to be had within a week.

The Path is structurally underrated. According to the file, this is the most neglected track, with a line that sums up the whole framework: change that depends on willpower fails, change that depends on environment succeeds. You don't need to resist biscuits that aren't in the house. You don't need to remember a standup that happens every morning at nine. The dashboard that shows lead time makes slowness visible without anyone having to bring it up.

The pitfall the file explicitly names is tackling the Rider without the other two. Exactly what most organisations do: a clear presentation, a clear goal, a plan with steps. And then nothing happens, because the Elephant feels nothing and the Path still rewards the old behaviour. Never do Rider without Elephant and Path, it says literally, that is exactly why most changes fail.

In diff form, with lines pointing to the examples in the skill: what goes out and what comes back in its place.

Next comes the core idea with the Rider, the Elephant and the Path, including where the metaphor comes from. The skill is careful about this: it credits Rider and Elephant to Jonathan Haidt and The Happiness Hypothesis, and notes that the Heath brothers added the Path and built a change management framework around it. Right after that comes the most important reversal: when people don't change, we look too quickly at resistance or laziness, while the problem usually lies in direction, motivation or environment.

Remarkably, it also states when it should not trigger, which is rare for an instruction file. Not when someone is already in the middle of execution and just needs tactical help. Not for a one-off decision. And not for a conflict in a specific conversation. For that last case, the file points to a negotiation technique, and in our library that's the Negotiator skill.

The method itself is fixed in three phases, in this exact order, because they reinforce one another. Phase 1 is outlining the situation with a maximum of five sharp questions: what change, as concretely as possible in behaviour; who needs to change; what's the current situation and what's already been tried; what does success look like in three months in visible behaviour; and what deadline you're working towards. Then comes a brief reflection, without judgement and without advice. Phase 2 is the three-track analysis shown above in FIG.02. Phase 3 is the 30-day plan.

There's also a chapter on writing style, with six rules you'll see reflected in the output. Always Dutch, unless the user explicitly writes in English. No lists with more than five items. No jargon without explanation. No synergy, alignment or other empty management language. Second person singular and informal, so 'je' rather than the formal 'u'. And being direct without becoming bossy. That last part is no small detail for a change coach: a tone that lectures you makes the Elephant stubborn.

At the end are the sources the skill is allowed to cite and the five things it never does. Those five refusals get their own figure further down this page, because they say more about the quality of the advice than the techniques themselves.

The main source is Switch itself. Switch: How to Change Things When Change Is Hard, by Chip Heath and Dan Heath, published in 2010 by Crown Business. The book isn't a theoretical work but a collection of cases where change did succeed, organised along the three tracks. That also explains the shape of the skill: not a model to fill in, but a series of questions that force you to come up with something concrete for each track.

The metaphor comes from Jonathan Haidt. The Happiness Hypothesis, published in 2006 by Basic Books, introduced the Rider on the Elephant as an image for the relationship between the rational and emotional parts of the mind. The skill explicitly credits the metaphor to Haidt rather than the Heath brothers, which is more accurate than what most summaries online say. The Heath brothers' addition is the Path: the environment as a third lever alongside reason and feeling.

The skill may cite the related titles, not parrot them. Four books are listed that you don't need to read but that it's allowed to mention: Made to Stick from 2007, Decisive from 2013 and The Power of Moments from 2017, all three by the Heath brothers, plus Thinking, Fast and Slow by Daniel Kahneman from 2011. If you want to apply the first of those four directly, there's a separate Made to Stick Coach skill that makes messages sticky, which comes in handy precisely for the Elephant track.

Even without installing the skill, you can take apart any stuck change with these three questions: is the direction concrete enough, does anyone feel anything about it, and does the environment make the new behaviour easier than the old one. If you want to look at the same question through a different model, the Fogg Behaviour Model Coach skill splits behaviour into motivation, ability and trigger, and the Atomic Habits Coach skill works the Path track out into a system of habits.

After that, using it is simple: describe the change you want to make and answer the phase 1 questions honestly, including the question of what you've already tried. Those failed attempts are especially useful, because they usually show which track you've skipped so far. If you're new to this kind of file, read what Claude skills are NL first and then how to install Claude skills NL. If you want to write one yourself, for example for the changes that keep recurring in your organisation, writing a SKILL.md NL explains how to go about it.

The skill is just as clear about when not to use it, and there are three situations. The first: you're already in the middle of execution and just need tactical help. Then a complete change plan costs you time and delivers nothing. The second: it's a one-off decision. A choice between two options isn't a change project, and a decision framework helps better there, for example the Pre-mortem Analyst skill NL, which lets a plan fail in advance to see where it breaks. The third: it's a conflict in a specific conversation. For that, the file points to a conversation technique, which you'll find in the Nonviolent Communication Coach skill.

There's another boundary the file doesn't spell out in so many words but does enforce through the first phase: the skill can only work with what you tell it. Describe the situation in abstractions and you get abstract actions back. The five questions in phase 1 exist precisely to prevent that, and they're meant to feel uncomfortable. The question of what success looks like in three months, in visible behaviour, is the hardest one for most people, and at the same time the most useful.

One more honest limit: Switch designs change, it doesn't guarantee it. The framework raises the odds that a change sticks by forcing you to address all three angles, but some changes shouldn't succeed. If the direction itself is wrong, or if the team is right and you're not, then a better change plan is the wrong tool. That's why phase 1 also asks what's already been tried, because that's often where the answer lies to whether it was the approach or the plan itself that was at fault.

A change inside your business only helps if there's something to show for it on the outside. If the flow of new business is drying up, the real work isn't more urgency in the team but being found by the people looking for you. The free SEO scan shows in a few seconds where your site stands. If this kind of thinking works for you, take a look at what else is ready in the library of 100 free skills NL we make available with no account needed. And if you want to talk further about what else AI can do for your business, from individual skills to full automation, we're happy to do that in a conversation.