The AI Hook Model Builder skill for Claude

The problem the skill solves is the best known problem of every digital product: people try it once and do not come back. Your acquisition works, your onboarding is tidy, and after a week your product is forgotten. You do not solve that problem with marketing. Anyone who wants users to come back needs to design something that sets itself back in motion, without you throwing a fresh campaign at it every time.

Nir Eyal described a model for this in 2014 in Hooked: four stages that follow each other in a loop, trigger, action, variable reward and investment, where every round through the loop makes the next round more likely. What you get here is not that general explanation, because there is a book for that. It fills the model in for this specific product, this audience and this core behaviour.

It is written for product managers, founders, designers and marketers working on retention, onboarding or activation. You do not need an existing product: with an idea, an audience and a core behaviour you can already work through the stages. What you do need is one action you want to see more often, not a collection. Core behaviour is singular, and that is the first place the skill corrects you.

And then the part that sets this skill apart from most retention advice you find online: the ethics check is a mandatory step, not a footnote. It tests against Eyal's own Manipulation Matrix, and the outcome is explicit. For anything that causes harm with heavy use, such as gambling or impulse credit, it does not build a loop at all. This skill belongs to our AI and automation service and sits alongside the rest of the skill library NL.

The trigger comes at the wrong moment or is not tied to anything. A notification is only a trigger if it connects to an emotion that is genuinely active at that moment. Boredom, unease, doubt, the fear of forgetting something, guilt over postponed work. If it connects to nothing, it is noise, and noise gets switched off within a week. That is why the skill does not just supply triggers but marks the strongest lever: that one external cue and that one internal emotion that fit together best.

The threshold is too high for the motivation that is there. Of the four, this is the point that gets underestimated most often, and it is worked out in FIG.03. According to BJ Fogg, behaviour only arises when motivation, ability and a prompt come together at the same moment. If one is missing, nothing happens. And because motivation is expensive to build, lowering the threshold is almost always the cheapest fix. Filling in seven fields is not a motivation problem.

The reward does not vary. A predictable reward gets ignored after a while, that is Skinner's point about his variable reinforcement schedules. If your user gets exactly the same message every time, it is no longer a reward but an announcement. Hence the requirement that for each filling you state what varies and what does not. If nothing varies, it is not a variable reward.

The user puts nothing into it. Without investment, your product stays interchangeable. What the user puts into it in data, preferences, content, contacts, structure or time raises the switching cost, but more importantly: it makes the product better for this user. And it loads the next trigger. An investment that does not load a next trigger does not close the loop, and then you do not have a loop but a straight line with an end.

In diff form: the patterns the skill refuses, next to what it puts in their place. This is not a style preference, it is a hard rule in the file.

After that comes a theory chapter that explicitly names four sources and links each to a stage. Eyal's own Hook Model, the Fogg Behavior Model at the action stage, Skinner at the variable reward, and the IKEA effect plus cognitive dissonance reduction at the investment. The ethics check also comes from Eyal, via the Manipulation Matrix. That is not decoration: because the reasoning sits in the file, Claude can explain, at every choice, why that choice is made rather than just what you have to do.

The core is a fixed method of seven steps, with the instruction to work through them in this order, skip nothing and fill in nothing the user has not given. Step 1 is the context stage: product, audience, core behaviour and frequency. Core behaviour is one action and not a collection, and frequency is a number. Without frequency you cannot design a habit, because a habit needs repetition within a short span of time.

Step 2 is the trigger stage, with three to five external and three to five internal triggers and the marking of the strongest lever. Step 3 is the action stage with the Fogg formula and three simplifications. Step 4 is the variable reward, with the explicit requirement that you choose one main type and explain that choice. Step 5 is the investment stage, where the file places a subtle emphasis: describe how the investment raises the switching cost and, more importantly, how it makes the product better for this user.

Step 6 is the synthesis: the complete loop in five lines, plus three experiments you can run in two weeks. For each experiment it must state what you change, which measurement you watch and which outcome would disprove the experiment. That last part is a falsification requirement, and you rarely see that in this kind of advice. Step 7 is the ethics check, worked out in FIG.04.

Alongside the seven steps, the file contains an eight-point input checklist, with the instruction to only ask about what is missing, and the rule that a missing figure about current usage is noted as [FILL IN] rather than measured itself. The output format has eight parts and ends with the ethics check with an explicit outcome. After that come the shortened example from FIG.01, seven things the skill never does, five honest limits of the framework, and a source list of seven titles.

If you want to write a file like this yourself, or adapt this one to your own product, that is exactly the point: it is released under the MIT licence. Writing a SKILL.md NL explains how to build a file like this, from frontmatter to refusals block.

Nir Eyal laid the model down. Hooked, written with Ryan Hoover and published in 2014, describes the four stages and the way they reinforce each other. Eyal also wrote Indistractable in 2019, and that book is not there by accident: it describes the other side, how users arm themselves against loops. Anyone who reads both designs more carefully.

The action stage comes from BJ Fogg. His Behavior Model, presented at the Persuasive conference in 2009, states that behaviour arises when motivation, ability and a prompt come together: B = M x A x P. Fogg also wrote Tiny Habits in 2019, and that is in the list for linking new behaviour to existing routines. That explains why the input checklist explicitly asks whether there is an existing routine the behaviour can latch onto.

The variable reward comes from B.F. Skinner. His work on reinforcement schedules from the 1950s, collected in Schedules of Reinforcement from 1957, showed that a reward that varies in size or kind holds attention for longer than a predictable one. This is the best researched part of the whole model, and the file itself says something honest about it that you rarely read: variable reinforcement is well researched, but the four stages as a whole are an organising model and not a measured law.

The investment leans on Norton, Mochon and Ariely. Their 2011 paper on the IKEA effect showed that people place more value on what they built themselves. Together with cognitive dissonance reduction, that explains why the investment stage works: you do not want to throw away what you put into it. That is exactly where the ethical line sits too, because you can use that effect to make something better, or to trap someone.

The context comes from Wood and Neal. Their 2007 paper in Psychological Review describes habit formation as context driven behaviour: the environment sets the action in motion, not a conscious choice. That is why the skill asks for the exact moment and channel for every external trigger. A trigger without context is an idea, not a trigger.

Anyone who wants to apply this way of thinking more broadly than a product can put the Atomic Habits Coach skill alongside it for habits in people rather than in products, or the Fogg Behaviour Model Coach skill for the formula from FIG.03 on its own, apart from the Hook Model. And for the persuasion side of the same question there is the Cialdini Persuasion skill.

After that, using it is simple: describe your product in one sentence, name your core behaviour and the frequency you want to see, and the skill works through the seven steps. It only asks about what is missing from the eight-point checklist. If you do not have a figure for current usage, that is not a problem: it puts [FILL IN] there and carries on. If you get stuck on the installation itself, the full route is in installing Claude skills NL. If you want to learn how to set this kind of work up with your team, that is the subject of our AI training NL.

There are also situations where you are better off leaving it alone, and the file names them itself. For pure acquisition and advertising questions this is the wrong model: that is about the first visit, and the Hook Model is about return visits. And for products that cause harm with heavy use, it refuses to serve.

Then the honest limits of the framework itself, because they are all in there. The model describes behaviour that recurs often, in a short cycle. For products you use twice a year, such as a tax return or a mortgage, it is not the right model. There the cycle is too long to form a habit, however good your trigger is.

The evidence is partly practical observation and partly laboratory research. Variable reinforcement is well researched, but the four stages as a whole are an organising model and not a measured law. It is a good way to structure the conversation, not a law of nature you can invoke.

A habit only forms if the product already delivers value on its own. This is the limit that gets skipped most often and is the most expensive to ignore. The model reinforces existing usefulness, it does not replace it. If you doubt whether the underlying usefulness is there, the work starts somewhere else: with testing the assumption itself, for instance with the Mom Test Coach skill for your customer conversations.

Measurements take weeks to months. A two-week experiment gives direction, not proof. And what reads as a friendly reminder in one country or segment feels pushy elsewhere. Test triggers with real users before rolling them out: it is tempting to finish a notification strategy on paper, but it is the cheapest way to lose a user.

A good loop brings people back, but someone still has to come in first. If the inflow lags behind, the real work sits in front of this page: getting found by the people looking for you, in Google and in AI answers. The free SEO scan shows in a few seconds where your site stands. And if you want to talk through what else AI can do for your business, from individual skills to full automation, we simply do that in a conversation.