Pre-mortem · IN SHORT
The Pre-mortem skill imagines that a plan later failed, then examines plausible reasons. It connects the most significant concerns to early signals, preventive actions and criteria for changing course.
Your brief
A fictional portal pilot launches in six weeks for ten clients. One project lead handles everything, with no backup person or support agreement.
Possible draft
A plausible failure is unanswered questions during that person’s absence. Accumulating unanswered pilot questions are an early signal. A backup and a tested support arrangement could become launch conditions.
01 / THE FOUNDATION
You receive a scored risk list, five critical points with early signals, three proposed adjustments and two stopping criteria to discuss.
02 / SEE HOW IT WORKS
A fictional portal pilot launches in six weeks for ten clients. One project lead handles everything, with no backup person or support agreement.
A plausible failure is unanswered questions during that person’s absence. Accumulating unanswered pilot questions are an early signal. A backup and a tested support arrangement could become launch conditions.
The imagined failure is a thinking exercise, not a prediction. Scores need checking, and invented details about customers, competitors or resources should not make a scenario sound factual.
03 / GET STARTED
Establish the plan, resources and criteria first. Then look back from an imagined failure after the deadline.
Develop at least fifteen possible causes across seven categories. Rank them using estimated likelihood and impact.
Give the top five risks an observable early signal, prevention and mitigation. Agree in advance when to change course or stop.
04 / MAKE IT YOURS
The English ZIP contains the SKILL.md instructions and is free to download without an account. The file declares the MIT licence; retain its source and licence notices when adapting or sharing it. Need help applying this skill? Book a call.
Full informationDownload. Apply. Refine.
File language: English
Explore the details at your own pace.
You put a plan to Claude and it moves you to a moment after the deadline when that plan has failed catastrophically. From there you reason back together: at least 15 concrete failure reasons across seven categories, each scored on likelihood and impact, with early warning signals, kill criteria set in advance and an honest final verdict: go ahead, adjust or stop. That is a pre-mortem analysis, and this skill runs it without a pep talk. Its role is not to motivate you, but to protect you against your own optimism.
the lines above come from the zip on this page · SKILL.md is 7,612 bytes
This is the example given in the SKILL.md itself, spelt out here as a session. The input is a three-sentence launch plan, and that is enough to start: the skill keeps probing until the six flags are sharp. Watch what happens to the expectation of 50 customers. It checks that expectation and turns it into a question instead of an assumption.
The AI Pre-Mortem Analyst is a free skill from our skill library. A skill is an instruction file, SKILL.md, that gives an AI assistant a fixed way of working for one task; what Claude skills actually are NL we explain separately. This one is a file of 1,284 words that tells Claude how to tear a plan apart before it gets carried out. Not afterwards, once the money is already gone, but beforehand, while there is still something you can do about it. You download the zip at the top of this page, put it in your Claude environment, and from that moment you can run every plan through the same mill.
The problem this skill solves is uncomfortable but familiar: the brain that came up with a plan is the worst possible brain to judge that plan. You have put time into it, you want it to go ahead, and every doubt feels like a betrayal of your own work. Dutifully ask yourself what could go wrong, and out comes a shortlist of things like competition, busyness and a disappointing market. Vague enough that you never have to act on it. The pre-mortem turns the question around: the plan has already failed, reconstruct why. That forces stories with causes, data and names, and those you can actually use.
It is meant for anyone facing a decision with real stakes attached: a launch, a pivot, a hire, an investment, a large expense or the step into a new market. The frontmatter names those situations by name as the moments where Claude should pick the skill up on its own. It is part of the skill library we make available for free through our AI and automation service, with no account and no sales email afterwards.
One thing you should know beforehand: the skill only protects you if you give it real input. Anyone who answers the six flags from step 1 vaguely gets a vague pre-mortem back, and the file itself says exactly that: a vague pre-mortem is a worthless pre-mortem.
A standard risk analysis asks the question looking forward: what could go wrong? That question looks critical, but you answer it from a position where you still believe in the plan. Your optimism filters in, your attachment to the investment filters in, and the result is a risk paragraph that mostly proves you thought about it. The SKILL.md describes that mechanism explicitly: the forward-looking question activates your optimism bias, your sunk cost reflex and your commitment.
A pre-mortem asks the question looking backward. It is six months after the deadline, the plan has failed, and you write the report for a friend considering the same thing. According to the file, that reversal bypasses the optimistic filter and activates episodic memory and narrative reasoning: you stop inventing probabilities and start reconstructing a story. And stories need causes, not categories.
You see the difference most sharply in the wording. A risk analysis accepts a line like the market could disappoint. That kind of sentence does not survive the pre-mortem, because in a reconstruction you have to say how the market disappointed, when you could have seen it and why you did not. A hard language rule in the file covers exactly that: no vague risks, always specific, with the example that a competitor might do something is banned and competitor X launches a comparable feature in Q3 because they are already investing in it is the minimum.
In diff form, with the launch plan from FIG.01 as the case: what the vague version says and what the pre-mortem makes of it.
That is exactly why this technique also works so well as a skill. The reversal is simple, but keeping it up consistently is not: after three failure modes your brain wants to go back to defending the plan. Claude does not have that problem. It works through the seven categories, including the uncomfortable ones, and keeps going until the list is complete.
Step 3 of the skill generates failure modes across seven fixed categories. That list is the skeleton of every session: it forces you not only to find the failure points you already suspected, but also to work through the categories you would rather not look at. The mono lines below explain why each category is on the list.
A skill is only as good as its instructions, so we simply describe them here. The file opens with a frontmatter that determines when Claude picks up the skill. Not just on the word pre-mortem or risk analysis, but also on phrases like check this plan, what could go wrong, do a reality check, stop me doing something stupid, red-team this and I have doubts. Anyone who says something like that to Claude while the skill is installed gets it automatically. The frontmatter also explicitly rules something out: do not use it for post-mortems, because by then it has already failed.
After that the file defines the role in one sentence: tear a plan apart before it gets carried out. The core is a fixed eight-step way of working. Step 1 maps the plan across six flags: the decision in one sentence, the timeline, the resources going into it, the definition of success, the definition of failure and the stakeholders. If a flag is vague, Claude has to push for specificity. Step 2 is the time travel: a mandatory sentence spelt out in full, with the date and a concrete consequence built on your own stake in it. The file calls this the critical emotional trigger: you are meant to read it and pause for a moment.
Step 3 generates at least 15 failure modes across the seven categories from FIG.02, with at least two per category that fit your plan specifically. Step 4 scores each failure mode on likelihood and impact, both from 1 to 5, and sorts by the product of the two.
Step 5 is, according to the file, more important than the failure points themselves: for each critical risk an observable early signal, a metric to track and a threshold at which you step in. Step 6 sets prevention alongside mitigation for each risk, with the honest note that external shocks can only be dampened, not prevented. Step 7 sets kill criteria: the points agreed in advance at which you stop. And step 8 closes with a report in a fixed shape: the plan in one sentence, the five biggest risks, the five early signals, three recommended adjustments, two kill criteria and an honest verdict: go ahead, adjust or stop.
What stands out is how many rules are about tone. The instruction prescribes: cold and concrete, no pep talk, no this is a great plan. The role is not to motivate the user but to protect the user against their own optimism, and if the plan is bad that has to be stated. The language rule is hard too: short sentences, no vague risks, always specific enough to act on. The file closes with five things the skill explicitly does not do, more on that in section 04, and with the example you saw worked out in FIG.01.
If you want to learn to build a file like this yourself, the full explanation with template is in writing your own SKILL.md NL.
Fifteen failure modes with no ranking is a list to feel defeated by. That is why step 4 scores each failure mode on likelihood and impact, both from 1 to 5, and sorts by the product. The top 5 as it might look in a session with the launch plan from FIG.01: a schematic example, the scores come from the session and not from research.
The pre-mortem is not something this skill invented. The technique comes from decision psychologist Gary Klein, who researched how people decide under pressure and gathered his findings in Sources of Power (1998); he described the pre-mortem itself in 2007 in Harvard Business Review. The figure of roughly 30 percent that appears in the SKILL.md comes from earlier work: Mitchell, Russo and Pennington (1989) found that looking back from an imagined future increased people's ability to name reasons for a future outcome by roughly thirty percent. That was about the way the question was framed, not about teams with and without a pre-mortem, and it is not a measurement of ours.
The second name in the file is Daniel Kahneman, who cites the pre-mortem in Thinking, Fast and Slow. His point, as the skill summarises it: it is one of the few techniques that genuinely counters overconfidence while staying practical enough to run within half an hour. Overconfidence here is not a character flaw but a systemic one: planners structurally underestimate how long things take and what they cost, and more experience barely fixes that. A procedure that forces you to look back from the failure does, at least partly.
Why the reversal works, Klein described using what researchers call prospective hindsight: acting as if a future outcome is already certain makes it easier to find explanations for it. Ask what could go wrong, and your brain has to weigh probabilities, and it does that badly the moment it believes in something. Ask why it went wrong, and your brain gets to do what it is good at: reconstructing a story. What the file automates is exactly that shift, including the mandatory sentence that forces it.
Anyone who wants to put this kind of counter-thinking to broader use finds three neighbours in the library. The Red Team Analyst skill actively attacks your plan instead of reconstructing it. The Inversion Thinker skill starts from the question of how you would guarantee failure and works back to what you therefore need to avoid. And the SWOT analysis skill sets the risks in the wider context of strengths, weaknesses and opportunities. Same family, different angle of attack.
Even without installing the skill, you can run the ritual with your team tonight: write the time-travel sentence on a board, give everyone ten minutes to write down failure reasons in silence, and only collect them afterwards. With the skill it becomes more thorough and more repeatable, but the technique is and remains everyone's.
The SKILL.md lists what the skill explicitly does not do, and fixes its tone in rules that leave no room for flattery. In conversation, those limits play out like this: each line is a request you might make, with the response the skill gives according to its own instructions.
The zip contains one file, SKILL.md, and that is the complete skill. Installing is a matter of putting the file in the right place, and that place differs per environment. SKILL.md has been an open standard since December 2025, so the same skill also works in Codex, Cursor and Gemini CLI. So you are not downloading a Claude file but a working instruction any modern AI assistant can read.
~/.claude/skills/ai-pre-mortem-analyst/ (or .claude/skills/ in your project)./ai-pre-mortem-analyst..agents/skills/ in your project, or into ~/.agents/skills/ for all your projects.AGENTS.md or refer to it from that file. That is no longer necessary.After that, using it is simple: paste your plan and ask for a pre-mortem. The more honest the input, the harder the analysis. If you are new to skills, read what Claude skills are NL first and the installation guide for Claude, Codex and Cursor NL; if you want to build your own variants after that, writing your own SKILL.md NL will help you on your way. The wider explanation of working with AI is in the knowledge base.
This skill is at its strongest right before a decision that is hard to reverse: a launch, a pivot, hiring a key person, an investment, a large expense or a step into a new market. Those are exactly the situations the frontmatter names as automatic triggers. A big quote you are about to send is also a good moment: better to discover now which assumption could break your proposal than during the conversation with the client. And the combination with plans you made using the Working Backwards Coach skill NL is almost literally the mirror image: first write the press release of the success, then the reconstruction of the failure.
There are also situations where you are better off leaving it alone. Small, reversible everyday choices are one: working through eight steps for a decision you can undo tomorrow for free is overhead with no payoff. A project that has already failed is a second: that is post-mortem work, and the file explicitly rules it out. And the skill is no substitute for due diligence, legal advice or an accountant: it finds the weak spots in your reasoning, not the mistakes in a contract.
One more honest limit: a pre-mortem does not make your plan better, it makes the weak spots visible. What you do with that is up to you. Anyone who waves away every risk found has lost half an hour; anyone who reads every session as advice to stop never launches anything again. The tool works for people willing to adjust their plan and then still go ahead. The go/no-go structure is deliberately built on that: adjust is the middle answer, and in practice also the most often useful one.
This skill is the free do-it-yourself version of analysis work we also deliver as a service. It stays complete and with no catches, but be aware of what a skill is: it teaches your AI how to do something, while every new session starts empty. So it is not the engine and it is not the memory. You prompt, you supply the context again every time, you check. Anyone who wants it differently has two next steps: hand over the engine, or sort out the memory.
Step 3 deserves more than a paragraph, because with pre-mortems especially, memory is half the work. A kill criterion nobody remembers does not exist. Jarvis is the organisation's brain: it remembers what your AIs need to know, divides up the work and keeps track of what happened. You notice it first at the start of a new session.
We have been running on this system ourselves for months. Every agent session, every task and every decision is logged in it and can be read back. A new session therefore does not start blank: it first pulls up the recorded decisions, the running projects and the latest changes, and carries on where the previous one stopped. So we are not describing a promise but the way of working we operate in ourselves every day.
See the four plans at jarvis/pricing NL. Through the waiting list NL you only pass on your preferred plan, without obligation. That does not create an account, an order or a payment obligation. We discuss custom business arrangements first.
A pre-mortem never stands alone: a decision precedes it and course correction follows it. These skills from the same library each cover a different part of that chain.
Three ways to attack your own plan before reality does.
Red Team AnalystActively attacks your plan as an opponent, where the pre-mortem reconstructs it as a failure.SKILL Inversion ThinkerStarts from how you would guarantee failure and works back to what you therefore need to avoid.SKILL SWOT analysisSets the risks in the wider context of strengths, weaknesses, opportunities and threats.SKILLThe pre-mortem is one step in a decision. These three cover the rest of the process.
Cynefin DeciderFirst determines what kind of problem you are facing, before you let an approach loose on it.SKILL WRAP DeciderThe full decision process; its last step, being prepared to be wrong, is where the pre-mortem begins.SKILL NL OODA Loop DeciderFor course-correcting afterwards: observing and deciding as soon as your early signals go off.SKILLAnyone who writes out the success and searches through the causes gets more out of the failure beforehand.
Working Backwards CoachThe mirror image: first write the press release of the success, then the pre-mortem of the failure.SKILL NL 5 Whys AnalystWhen an early signal goes off: ask why five times until you reach the real cause.SKILL WOOP Method CoachThe personal variant: wish, outcome, obstacle and plan for goals of your own.SKILL NLWhere this skill comes from and what else there is.
The whole skill libraryAll free skills in one place, sorted by topic.HUB AI and automationThe service behind it: from stand-alone skills to working automation in your business.SRV AI trainingIf your team wants to learn to set this kind of work up itself.SRV What are Claude skills?New to skills? The complete explanation in plain language, with examples.DOC NLNothing. The skill is free, falls under the MIT licence, and you do not have to create an account or leave an email address. You download a 3.8 KB zip containing a folder and a single file, SKILL.md, and that is the complete skill. There is no paid version and no sales email follows.
A pre-mortem analysis is the reverse of a post-mortem. You do not wait until a plan has failed to investigate why, you act as if it has already failed before you begin. You move yourself to a moment after the deadline, establish that the plan has run aground and reason back to the causes. That reversal produces more concrete risks than the standard question of what could go wrong, because your optimism filters through it less.
Yes. SKILL.md has been an open standard since December 2025, so the same file also works in Codex, Cursor, Gemini CLI and other tools that follow the standard. In Codex you unzip it into .agents/skills/ in your project, or into ~/.agents/skills/ for all your projects; Codex has supported SKILL.md directly since the open standard of December 2025. Putting the contents of SKILL.md into your AGENTS.md still works too. The instructions are plain readable text, so any AI assistant that accepts instruction files can handle it.
Reckon on half an hour to an hour for a thorough session. In step 1, the skill keeps asking questions until the six flags are sharp: decision, timeline, stake, definition of success, definition of failure and stakeholders. The sharper you can answer those, the faster it goes. It can go faster, but a vague pre-mortem is a worthless pre-mortem, and the file says so itself too.
The failure modes are scenarios about the future, so nobody knows them for certain. That is why the skill explicitly scores every failure mode on likelihood and impact, from 1 to 5, and presents nothing as fact. It rejects vague risks: a failure mode has to be specific enough that you can attach an early signal and a threshold to it. The final verdict is advice, go, adjust or stop, and the decision stays yours.
Yes. The skill is written for any plan with real stakes attached: a launch, a pivot, a hire, an investment, a large expense, a new market or a big quote you are about to send. For writing that quote itself there is a separate skill, the AI Quote Writer. For small everyday choices, the overhead of eight steps is too much.
If it has already failed, this is the wrong skill: a pre-mortem only works ahead of the facts, and that is stated literally in the file too. If the project is still running, you can apply the skill to the next decision still open, for example a go/no-go moment or a follow-on investment. The kill criteria from step 7 exist for exactly that: setting in advance when you stop, before sunk costs cloud that decision.
A common failure mode in marketing plans, incidentally, is one you can already measure today: the plan leans on a website nobody can find. The free SEO scan shows in a few seconds where your site stands, before you build a launch on top of it. In the guide eight decision models compared NL you can see how this model relates to the others. And if you want to talk further about what else AI can do for your business, from stand-alone skills to full automation, we are happy to do that in a conversation. Feel free to give that conversation a pre-mortem first too; the Quote Writer skill stands ready for what hopefully comes after.
