Feynman technique · IN SHORT
The Feynman Technique skill helps you examine a subject through a plain-language explanation and probing questions. It waits for your answers before refining the explanation into short and longer versions.
Your brief
A fictional user knows a cache stores information temporarily but cannot explain when it becomes outdated. A desk holding frequently used information can provide an initial analogy.
Possible draft
The question “How do you know the copy is still correct?” reveals a gap about refreshing the information. The analogy is a starting point; it does not answer that question by itself.
01 / THE FOUNDATION
You get an initial explanation and visible knowledge gaps. After you answer the questions, the skill develops one-minute and three-minute versions.
02 / SEE HOW IT WORKS
A fictional user knows a cache stores information temporarily but cannot explain when it becomes outdated. A desk holding frequently used information can provide an initial analogy.
The question “How do you know the copy is still correct?” reveals a gap about refreshing the information. The analogy is a starting point; it does not answer that question by itself.
An appealing analogy can still be technically misleading. Verify subject facts and make clear where the analogy stops applying.
03 / GET STARTED
Define the particular idea and who needs to understand it.
Read the simple explanation and answer six questions yourself; missing knowledge is not filled in on your behalf.
Use your answers and test analogies before producing the short and in-depth versions.
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 name a subject you want to be able to explain, and Claude runs four fixed steps: it frames what exactly you want to understand, writes an explanation of no more than 250 words without jargon, interrogates that explanation with six questions a curious child would ask, and then builds a final version with at least three analogies and one memorable metaphor. The odd part is step three: the skill points at the gaps in your knowledge and deliberately does not fill them in. That is not a limitation, that is the method.
the lines above come from the zip on this page · SKILL.md is 7,773 bytes
This is the example that sits in the SKILL.md itself: someone wants to be able to explain mortgage interest to a younger brother who is buying his first house. The questions Claude asks, the ban on the word amortisation and the analogy with hiring are written into the file. The working out around them is ours, and therefore a schematic example. Watch the yellow line halfway down: that is where the skill stops and it is your turn.
The AI Feynman Technique Coach is a free skill from the library we keep ourselves. A skill is an instruction file, SKILL.md, that gives an AI assistant a fixed way of working for one task. No software to install, no subscription, no integration with anything: a text file of 1,196 words that tells Claude how to walk you through the feynman technique, which questions to ask, which words it may not use and at which moment it has to stop and wait.
The problem the skill solves is the illusion of understanding. You read an explanation, you nod, you think you have it. And then someone asks you about it and you hear yourself using words you cannot unpack. That happens to everyone preparing for a pitch, an exam, a client conversation or an explanation to family. Feynman's method puts a hard test against that: if you can explain it to a twelve year old without jargon, you understand it. Fail that test and you know immediately where your knowledge is thin.
Written for anyone who has to hand something over: business owners who want to make their own service understandable, advisers explaining a complex recommendation to a board, students preparing for an exam, and marketers who have to describe a technical product in human language. The frontmatter of the file names exactly those moments, with the phrases people actually use: explain this, help me understand this, I want to really get this, make this simple, I need to be able to pitch this, explain this for a layperson. And the reverse question too: check whether I really understand this, test my understanding, where are the gaps in my knowledge.
One thing is worth knowing up front, because it decides whether you will like this skill or not. It does not do the work for you. In step 3 it marks the weak spots in your explanation and asks you to fill them, with an explicit ban on answering on your behalf. Anyone after a finished text is in the wrong place. Anyone who wants the subject genuinely in their head is exactly right. It belongs to the AI and automation service and sits alongside the rest in the skill library (in Dutch), with no account and no sales email afterwards.
When an explanation does not land, people usually look for the cause in the listener. Almost always it sits in the explanation itself. The rules the skill imposes in step 2 read like a list of exactly those mistakes, and that is no accident: they were written to make each of them impossible.
Jargon papers over the gap. A technical term is an abbreviation of an idea. Use it while your listener does not have the idea, and you have said nothing. Worse: technical terms feel like knowledge to the speaker, while they often mark the exact point where the thinking stopped. So the file bans jargon, technical terms and buzzwords in the first explanation, and adds that a term you genuinely cannot avoid is explained straight away with a comparison.
The sentences are too long. There is a hard limit in the file: fifteen words per sentence at most in the explanation for a twelve year old. That is not a style preference but a thinking test. A long sentence can glue three half ideas together without anyone noticing that the middle one is missing. Cut it into three and the missing link stands out immediately.
The explanation is about the theory instead of about the world. What it asks for is concrete examples from daily life, and there is even a rule about conjunctions: avoid "because" followed by a technical reason, use "because" with human logic. That sounds like a detail, but it forces you off the layer of definitions and onto the layer of causes someone recognises.
The length is unlimited. Given an explanation without a bound, everyone fills the uncertainty with more text. So there is a ceiling of 250 words on the first explanation. Whatever does not fit is probably something you do not yet understand well enough to leave out.
The tone is model tone. Rule 3 in the file literally bans the stock sentences language models warm up their answers with, from "it is important to understand that" to "let us take a look at". It also says the skill gives no empty compliments: not "great question" first, but straight to the substance. That makes the answer shorter and the conversation more honest.
In diff form, using the mortgage example from the file: what goes out and what comes back in its place.
These are the four steps as they stand in the SKILL.md, with the rule the file itself attaches to each one. The yellow row between them is not a fifth step but the pause that is written into the output structure: the skill waits until you have filled the gaps it found. That moment of waiting is the difference between this skill and an ordinary summary.
# The gate is the only point where the skill stands still: it does not fill your knowledge gaps, because then you would skip the learning.
# The ring is the shape of the method, not a timeline: how long a round takes depends on the subject and is nowhere in the file.
A skill is only as good as its instructions, so here they are, in the order they appear in the file. At the top sits the frontmatter with the name ai-feynman-technique-coach, version number 1.0.0, the MIT licence and a long description that decides when Claude picks the skill up. That description is written in a strikingly practical way: it lists the phrases people use when they ask for an explanation, right down to asking whether something can be put in plain English. Say something like that to Claude while the skill is loaded and you get it automatically, without a command.
This is the top of the file, so you can read it before you download anything:
--- name: ai-feynman-technique-coach version: 1.0.0 license: MIT description: "Applies the Feynman Technique to any subject you genuinely want to understand. Forces you to explain a complex concept so simply that a child gets it, finds the gaps in your knowledge and fills them with sharp analogies. ALWAYS use this skill when someone says 'explain this', 'help me understand this', 'I want to really get this', 'make this simple', ..." ---
Then comes the goal in two lines: take the user past surface knowledge, build real understanding by forcing simplicity, finding gaps and using analogies that stick. After that the core: four steps that according to the file have to be followed strictly. Step 1 frames with four questions and produces a working definition of one sentence. Step 2 writes the explanation for a twelve year old, with five hard writing rules and a fixed format of four headings. Step 3 finds the gaps with six Socratic questions and a three line marking per weak spot. Step 4 rewrites everything with at least three analogies, a metaphor and two lengths.
Then the output structure is written out in full, including the order in which the blocks come back: working definition, explanation for a twelve year old, knowledge gaps found, then the wait line, and only after that the final explanation with the elevator version, the in-depth version and the memorable metaphor. That fixed format is the reason two sessions with this skill look alike and can be put side by side to see whether your understanding has grown.
Under the steps sit five rules about tone and honesty. Be honestly hard when the explanation is vague. No compliments without content. Avoid the stock sentences of language models. Point at your source and say when you are not certain, with a reference to Feynman's well known line about fooling yourself most easily. And fifth: two iterations at most, because if it has not landed after two rounds the problem runs deeper than a better wording.
It closes with three parts you do not see on many skills. A worked example, the mortgage conversation you see in FIG.01 above. A source list with three titles by Feynman himself and two books for further reading. And a short list of the situations where you should not use the skill.
According to the file itself step 3 is the most important step, and it is the step that separates this skill from any summarising prompt. The four question openings come straight from the SKILL.md; two of the six questions below are in it as examples and are marked as such. The rest is a schematic example in the same shape, carried through on the mortgage conversation.
The SKILL.md names its sources, and that is deliberate: you can read them and decide for yourself whether you agree with the approach. The method is named after Richard Feynman, who lived from 1918 to 1988, physicist, Nobel laureate and known by the nickname The Great Explainer. There are three titles by the man himself: Surely You Are Joking, Mr. Feynman from 1985, What Do You Care What Other People Think from 1988, and The Feynman Lectures on Physics, published between 1963 and 1965. For further depth the file names two books about learning: Make It Stick by Peter Brown, Henry Roediger and Mark McDaniel, and A Mind For Numbers by Barbara Oakley.
Worth knowing: the four steps as they stand here are not a method Feynman himself wrote down in this form. They were derived later by others from the way he worked and taught, and that is exactly how the skill presents them: as a technique named after him that rests on his starting point. That starting point is his, and it is sharp: if you cannot explain something to a twelve year old, you do not really understand it yourself.
Why does that starting point work so well? Because it is the one test you can run on yourself without an expert in the room. You cannot hear yourself say you understand something and check it. You can hear yourself stumble the moment you take the technical term out. Three extra tests are built on top of that. The writing rules of step 2, which strip the jargon. The six questions of step 3, which point at the gap as soon as your explanation thins out. And the follow-up test of step 4, which asks whether your analogy survives ten questions or falls apart at the third.
That last point is underrated. A good analogy does more than illustrate: it carries the structure of the idea across, so your listener can think onwards by themselves. A bad analogy only pretends, and breaks at the first follow-up question, after which your audience not only fails to grasp the idea but stops trusting your explanation. So the file demands three from different domains, from sport, cooking, driving, nature, children or money: what falls away in one analogy becomes visible in the next.
And then the honesty rule the file adds itself: if the explanation is uncertain, that has to be said. Rule 4 refers to Feynman's well known line that you are the easiest person to fool. For an AI skill that is more than a nice sentiment. A language model effortlessly produces a fluent explanation of something it is not sure about, and that fluency reads as reliability. The instruction to name what is uncertain is therefore not modesty but a correction mechanism.
There is no separate heading for refusals, but eight of them are in there: five under the heading important rules and three under the heading when not to use this. In conversation they play out like this: every rule is a request you could make, with the response the skill gives according to its own instructions.
The zip is 3.6 KB and contains one folder, ai-feynman-technique-coach, with the SKILL.md inside it. Installing means putting that file in the right place, and the right 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. You are not downloading a Claude file but a working instruction that any modern AI assistant can read.
~/.claude/skills/ for all your work, or .claude/skills/ inside one project./ai-feynman-technique-coach..agents/skills/ in your project, or ~/.agents/skills/ for all your projects.AGENTS.md in your repository and paste the contents of SKILL.md into it.Once it is in place, using it is simple: name the subject and say who you have to explain it to. Allow fifteen to thirty minutes, because that is the time the file itself names for a full cycle. Most of that is you typing in step 3, and that is not a design flaw but the point.
It is at its strongest when you shortly have to explain something out loud to someone who knows nothing about it. An investor, a board, a client, a family member, an examiner. In all of those cases recognising the material is not enough: you have to produce it, in your own words, under follow-up questions. That is exactly what the four steps train.
It is also useful as a self-test on something you think you have mastered. Pick a subject from your own field and let the skill break your explanation open. The six questions of step 3 are uncomfortable precisely because you no longer ask them yourself: about your own field you have stopped looking naively.
And there is a third use that is less obvious: getting your own offer sharp. Cannot explain your own service in 250 words without jargon? Then your client does not understand it either. The jargon ban of step 2 works there the same way it does in physics. Write the description out first and the padding shows up on its own, usually as adjectives that nobody would miss if you cut them. What is left once you remove the fine words is what you actually sell.
There are limits too, and they are simply in the file. The first: pure fact lookup. For a date or a definition, searching is faster than a four step cycle. The second: fast task execution. The method costs fifteen to thirty minutes, so if you need something finished within ten, this is the wrong instrument. The third: subjects you are already expert in and only want a second opinion on. You get an explanation at beginner level back, and that is an answer to a question you did not ask.
We add one honest limit the file does not name. It tests whether your explanation is internally consistent and whether you see the gaps yourself, but a fact check it is not. If your explanation contains an error that is carried through consistently, it will happily build three analogies for it. If you are about to explain something that carries weight, such as medical, legal or financial material, check the facts with a real source or a colleague in the field before you pass it on.
Looking for something else, then the library probably has a better fit. If the problem is not understanding a subject but keeping the practice up, the AI Atomic Habits Coach is the one to read next. To strip a subject down to its building blocks rather than explain it, the First Principles Thinker skill is the logical choice. For reaching insight through questions instead of through explanation, the Socratic Method Coach skill does that systematically.
This skill is the free do-it-yourself version of work we also deliver as a service. It stays complete and without catches, but be clear about what a skill is: it teaches your AI how to do something, while every new session starts empty. It is not the engine and not the memory. You prompt, you supply the context again every time, you fill the gaps. Want that differently, and there are two next steps: hand the work over, or sort out the memory.
Rung 3 deserves more than a paragraph, because this is the difference between a clever chat and a system you can build on. Jarvis is the organisation brain: it remembers what your AI tools need to know, splits up the work and keeps a record of what happened. With a learning skill that stands out. A knowledge gap you filled last month is only a gain if it stays somewhere; otherwise you start every quarter at the same question.
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 fetches the recorded decisions, the running projects and the latest changes, and carries on where the previous one stopped. So this is not a promise we are describing but the way we work every day.
Amounts are in euros and include Dutch VAT. All plans are listed at jarvis/prijzen (in Dutch). Paying online opens once the last checks are finished; until then we set your account up on request, so write to sales@theseo.nl. For business arrangements and bespoke work there is a conversation.
Understanding is one link in a chain: a way of thinking comes before it, and remembering and passing it on come after. These skills from the same library each take a different piece of that chain.
Once you have understood it, it still has to stick with someone else.
Socratic Method CoachReaches insight by asking questions instead of by explaining.SKILL Pyramid Principle WriterPuts the conclusion first and the argument underneath, for anything you have to write down.SKILLFeynman tests your explanation. These two take the subject itself apart.
First Principles ThinkerStrips a problem back to the building blocks with nothing underneath them.SKILL 5 Whys AnalystDigs down to the cause, with the same stubborn question a twelve year old asks.SKILLTwo skills that test a plan rather than an explanation.
Pre-Mortem AnalystAssumes the plan has already failed and asks why, before you start. Also known as premortem.SKILL Six Thinking Hats AnalyserLooks at the same decision from six fixed angles, one at a time.SKILLWhere this skill comes from and what else there is.
AI and automationThe service behind it: from single skills to automation that runs.SRV Ikigai CoachFor the question underneath the work: what you are for, in four circles.SKILL The whole skill libraryAll 100 free skills in one list, sorted by subject. Page in Dutch, downloads are language neutral.HUB AI trainingIf your team wants to learn how to set this kind of work up themselves.SRVNothing. You download a 3.6 KB zip containing one folder and a single file, SKILL.md, and that is the complete skill. The frontmatter says license: MIT, so you are free to use and adapt it. You do not have to create an account or leave an email address, and there is no paid version this leads to.
Yes. SKILL.md has been an open standard since December 2025, so the same file works in Codex, Cursor and Gemini CLI. 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. Pasting the contents of SKILL.md into your AGENTS.md still works too. The instruction is plain readable text with no code in it, so any assistant that accepts instruction files can handle it.
Four, and the file states that they have to be followed strictly. Frame the subject, explain it as if you were talking to a twelve year old, find the gaps in your knowledge, and then simplify with analogies. Between step 3 and step 4 there is an explicit pause: the skill only carries on once you have filled the gaps it found.
Because step 3 explicitly forbids it. The file says the skill gives no answer on behalf of the user, with the reason attached: the whole point of this method is that you discover for yourself where your knowledge is thin. Let an AI fill the gaps and you have a nicer text and exactly as much understanding as before.
The file says 15 to 30 minutes, and lists that under its own limits: the skill is not meant for fast task execution. It also sets an upper bound of two iterations. If you still do not understand after two rounds, the skill advises a different kind of source, such as video or a mentor.
The file names three situations where you are better off not using it: pure fact lookup, where searching is faster, fast task execution, because the cycle takes time, and subjects you are already expert in and only want a second opinion on. In that last case you get an explanation back at a level you passed long ago.
Frontmatter with the name, version 1.0.0, the MIT licence and the phrases that make Claude pick the skill up, then the goal, the four steps with their rules, the fixed output structure, five important rules about tone and honesty, a worked example about mortgage interest, the sources, and a short list of when not to use it. The English file comes to 1,196 words.
Download the skill, pick the subject you have to talk about next week and see whether you can get it round in 250 words without technical terms. It costs half an hour and nothing at all, and you know straight away where your explanation wobbles.
The same test works on working with AI itself: ask someone to explain what they asked the AI and why, and within a minute you can hear whether they understand it or are only clicking along. Should your team practise that way instead of watching a demo, that is what the AI training does. And if you are looking for more instruments of this kind, the rest are in the library of 100 free skills (page in Dutch).
