The AI Inverse Thinker skill for Claude

Why would you think in reverse? Because the normal direction has a blind spot. Anyone making a plan reasons forward along the path where everything goes well, and that path is the only one they see clearly. Ask the same person why their plan failed, and a list suddenly appears: mechanisms, moments, names. People are demonstrably better at explaining something that has already happened than at predicting something that still has to happen, and inversion thinking uses that trait as a tool. You move the failure into the past and harvest the explanations.

It works on business plans, product launches, campaigns and investments, but just as well on career moves and personal goals: should I resign, should I go for this offer, is this investment sensible. The frontmatter also names the sighs Claude picks it up on automatically: everyone on my team is enthusiastic and I find that suspicious, the plan sounds too good, we made exactly the same mistake last time, I do not dare to start and I do not know why.

One thing you should know beforehand: the skill is critical, not cynical. Every danger it names gets a countermeasure you can carry out this week, or an honest note that there is nothing to be done about it. Discouraging without giving you something to act on is literally on its list of refusals. The goal is not that you stop making plans, the goal is that your plans survive the inversion before reality carries it out.

The inversion changes the quality of the answers. Research by Mitchell, Russo and Pennington into what they called prospective hindsight showed that people can name more, and more specific, causes when you present an event as an accomplished fact rather than as a possibility. It is now 31 December and the plan has failed produces different sentences than the plan might fail. That is why the skill requires the past tense: every failure mechanism is written as if it has already happened.

The second problem with the ordinary risk paragraph is one-sidedness: it is almost always only about money. That is why the skill forces the mechanisms to spread across six categories, from demand and market to the silent assumptions nobody has tested. In assessment mode, where you have an existing plan checked, it even explicitly checks which categories are missing entirely, and those are almost always people and assumptions. Anyone who wants to see which thinking errors lie underneath, from optimism to groupthink, can turn to the Cognitive Bias Detector skill.

You see the difference fastest in diff form, with lines from the skill's own example:

Three times the same move: from a possibility with no address to an event with a mechanism inside it. You cannot prepare for the first. You can for the second, and that is exactly what the rest of the analysis does.

After that come seven fixed actions. First your plan is reduced to one testable sentence with a date. It inverts that sentence into the failure question. It generates eight to twelve failure mechanisms, spread across the six categories, each in the past tense. It scores each mechanism on likelihood from 1 to 5 and impact from 1 to 5 and calculates the risk score as the product.

It flags everything with a score of 12 or higher as a primary danger, and separately flags what only becomes visible late, because a risk you only see once it has already happened deserves more attention than the score alone suggests. For each primary danger it delivers one countermeasure that can be carried out this week, with an owner and a day. And it closes with a verdict: is this a plan to press ahead with, with adjustments, or does it contain a mechanism that is a reason not to start at all.

For the scoring, the file leans on the logic of FMEA, failure mode and effects analysis from industry, but without the jargon: likelihood, impact, visibility. The skill also has a block that many risk analyses skip: the earliest alarm. For each primary danger it describes the first signal you would see if the mechanism actually starts to play out, and where you should look for it. In the example: more than six minutes of packing time per box, or a customer who shows interest but will not pay in advance.

There is also an assessment mode for existing work. Hand it a business plan, project plan or campaign brief, and you get an assumption scan with, per assumption, the question that makes it testable, the missing categories, an optimism check on figures with no source and growth that is simply extended in a straight line, ten failure mechanisms the plan itself does not mention, and the irreversible step: which step in the plan cannot be undone, and whether it comes early or late. Irreversible steps belong as late as possible. Anyone who wants to learn to build this kind of instruction file themselves finds the full explanation with template in writing a SKILL.md yourself NL.

The file closes with writing rules and a source list of six titles, from Jacobi to Taleb. More on that below, because the theory is older and better supported than most lists about thinking backwards suggest.

The evidence comes from decision research. Mitchell, Russo and Pennington published their research into temporal perspective in explaining events in 1989, and found that people name more, and more specific, causes when an outcome is presented as an accomplished fact rather than as a possibility. Gary Klein built the pre-mortem on that, described in Harvard Business Review in 2007: the team moves itself into a future in which the project has failed completely and writes down why. That technique has its own version in the library, the Pre-Mortem Analyst skill NL; the inverse thinker uses the same principle but builds the categories, the visibility flag and the countermeasures around it.

The scoring comes from industry. Failure mode and effects analysis, FMEA, was developed within the American defence sector in the 1950s and later standardised in the car industry. The idea that you score likelihood and impact per failure mode, and separately track whether the failure is visible before it causes damage, is daily practice there. The skill translates that to plans: a mechanism that only becomes visible in hindsight, such as customers who do not complain but simply cancel, counts more heavily than its score.

The variants come from Taleb and from entrepreneurial circles. Via negativa, worked out by Nassim Nicholas Taleb in Antifragile, is improving by removing: not asking what should be added, but what can come out without the plan collapsing. The skill uses that form when a plan is already overloaded, and in practice that happens more often than a plan that is too thin. Anyone who wants to train Taleb's broader framework about systems that grow stronger from setbacks finds that in the Antifragile Thinker skill.

And the distinction between reversible and irreversible decisions, known in entrepreneurial circles as doors that swing both ways and doors that do not, determines how heavily the skill commits: a shortened inversion with five mechanisms for a decision you can undo tomorrow, the full analysis for the door that only swings one way. That distinction has its own skill, the Two Way Door Decider NL.

Even without installing anything you can apply the core of it tonight: write down your goal with a date, put underneath it is that date and it has failed, and note down ten reasons in the past tense. The first three are cliches, from number four onwards it gets interesting.

After that, using it is simple: paste your plan and ask for the inversion. The more concrete your goal and your deadline, the sharper the mechanisms; whatever is missing, the skill asks about. New to skills? Read what Claude skills are NL first and the installation guide for Claude, Codex and Cursor NL. The broader explanation of working with AI is in the knowledge base.

If the plan is already overloaded, it switches to via negativa and asks not what should be added but what can come out. For a small or reversible decision, the shortened inversion with five mechanisms is enough, because a full analysis on a decision you can undo tomorrow is wasted effort. For investments above an amount that would actually hurt, a separate financial calculation gets added. And for personal decisions, such as resigning or moving house, the people category weighs more heavily and the skill explicitly asks what you would lose that cannot be expressed in money.

There are also situations where you are better off leaving it alone, and the file itself says so. If a decision has already been made and is irreversible, a failure list is nothing more than self-torment; the skill then shifts to limiting the damage. If you are mainly looking for confirmation or encouragement, this is the wrong skill, and that is not a dig: sometimes gathering courage is the real work, and a failure list does not help with that. And for legal, medical or financial questions it refers you on to people who carry professional liability.

The most honest limit is the same as with every thinking technique: the inversion does not make your plan good, it makes it tested. After the analysis you have mechanisms, alarms and countermeasures, but still no certainty. If you then want to work out what kind of decision you are actually facing and which approach fits it, the Cynefin Decider skill is the logical next step; anyone who, after the failure analysis, looks for calm in what lies outside their control finds the oldest form of negative visualisation in the Stoic Coach skill NL.

The failure question also works on marketing: how do we guarantee that customers never find us? Being unfindable on Google is then failure mechanism number one. Want to know whether that mechanism is already at play for you? The free SEO scan shows in a few seconds where your site stands. In the guide eight decision models compared NL you see how this model relates to the others. And if you want to talk further about what AI can do for your business beyond this, from separate skills to full automation, we simply do that in a conversation.