EN
Language · same page NLNederlands/ai-en-automatisatie/ai-made-to-stick-coach-skill-voor-claude/ ENEnglish (UK)/en/ai-and-automation/ai-made-to-stick-coach-skill-for-claude/ ESEspañol/es/ia-y-automatizacion/ai-made-to-stick-coach-skill-voor-claude/ We do not remember your choice and never redirect you automatically.
~/skills/ai-made-to-stick-coach[ok] loaded
INS.SKILL · FREE FOR CLAUDE, AND FOR CODEX AND CURSOR TOO

The AI Made to Stick Coach skill for Claude

You paste your pitch, headline, slogan or memo into Claude and you first get an honest diagnosis back: a score from 0 to 10 on each of the six SUCCESs principles from the book Made to Stick, plus an assessment of your Curse of Knowledge risk. Three rewritten versions follow after that, each strengthening a different principle, with an annotation per version of what changed. It does not flatter, and it does score strictly, because that is exactly what a message needs before it goes out the door.

Download the skill See all skills NL 4.6 KB · zip containing SKILL.md · MIT licence · no account needed
$ installation, line by lineFIG.00
~/.claude/skills
theseo ~ %
  inflating: ai-made-to-stick-coach/SKILL.md
theseo ~ %
  ---
  name: ai-made-to-stick-coach
  description: |
theseo ~ %
[ok] skill active · 1,497 words of instruction loaded

the lines above come from the zip on this page · SKILL.md is 9,869 bytes

~/skills/ai-made-to-stick-coach/01-demonstration[run]
Section 01 · The demonstration

Pitch in, sticky versions out

reg. M.001

This is the worked example that sits in the SKILL.md itself, shown here in shortened form. The input is a pitch like the ones you run into on LinkedIn every day: grammatically fine, full of jargon, and forgotten by tomorrow. Note the order: the skill never starts with rewriting, it starts with measuring.

FIG.01: From jargon pitch to three sticky versions[#----] sheet 1/5
~/messages · claude + ai-made-to-stick-coach
you > this pitch is not landing, can you test it and rewrite it?
pitch.txtthe input from the example in the SKILL.md We are an AI driven SaaS platform that empowers enterprise sales teams through an end-to-end revenue acceleration suite.
claude · SUCCESs check in five steps...
[1/5]context · checking audience, goal and channel, only asking about what is genuinely unclear
[2/5]score · six principles, each 0 to 10, honest and strict, with the Curse of Knowledge risk added
[3/5]diagnosis · the three weakest principles named, concrete and with no vague advice
[4/5]rewrite · three versions, each with a different principle focus and an annotation of what changed
[5/5]final advice · a preference per goal plus a test question to check it yourself
score-tablestep 2, taken literally from the example
S Simple 2/10 too many ideas at once, no core point U Unexpected 1/10 sounds like every other SaaS pitch C Concrete 0/10 zero mental image, only jargon C Credible 3/10 no facts, no authority E Emotional 0/10 no human in the sentence S Stories 0/10 no story Total: 6/60 · Curse of Knowledge risk: extremely high
rewrites.mdsteps 4 and 5, shortened Version 1 (Simple + Unexpected): "We make one thing: software that stops sales reps reinventing the wheel every Monday." · one core concept, the opening breaks the pattern of SaaS pitches Version 2 (Concrete + Stories): "Sarah opens 47 tabs on Monday morning, three spreadsheets, and Salesforce. An hour later she still does not know who to call first. We built the tool that gives her that hour back." · one person, one place, one problem Version 3 (Emotional + Credible): "Our average user closes 23% more deals. Not because our AI is clever, but because their people finally have a free Sunday evening again." · a figure at human scale, an emotional anchor Preference: version 2 for pitches at events, version 3 for LinkedIn, version 1 as the opening of your website. Test question: get a friend outside your sector to read these sentences and ask him to explain in his own words what your company does.
[#####] 5/5 done · the figures in version 3 come from the file's example: you supply your own evidence
6M.01 · SUCCESs principles as a yardstick
5M.02 · steps in the method
4M.03 · things the skill does not do
0M.04 · euros, MIT licence, no account
M.01 to M.04 · properties of the skill file, not results or usage figures.
$ cat 01-wat-de-skill-is.md
DOC.01

What the AI Made to Stick Coach is

The AI Made to Stick Coach 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. Not software you install, not a subscription, not a plugin: one text file of 1,439 words that tells Claude how to judge a message against the six principles from the book Made to Stick by Chip and Dan Heath, in what order it works and what it may never do.

You download the zip at the top of this page, put it in your Claude environment, and from that moment Claude treats every pitch, headline or slogan against this yardstick. Not sure yet exactly what a skill is, read what Claude skills are NL first.

The problem the skill solves is one anybody recognises who ever has to present, sell or explain something. You know exactly what you mean, you write it down, and a week later nobody can repeat it back. Not because the idea was bad, but because the packaging did not stick. The pitch sounded like every other pitch, the headline was abstract, there was no person and no story in it. That is exactly what it tackles: it first measures where the message is weak, and then rewrites it targeted at those weak spots instead of just randomly making it nicer.

This coach is written for entrepreneurs, marketers and anyone who has to send a message out the door: an elevator pitch, a tagline, a presentation opening, a blog headline, a LinkedIn post or an internal memo. It belongs to the library of 100 free skills we make available from our AI and automation service, with no account and no sales email afterwards. All skills are on the skills NL hub.

One thing you should know in advance: the skill rewrites, it does not invent. It needs an existing message to work with, and the evidence that makes a rewrite credible has to come from you. No framework can save a message with no content, and the file says so itself: no blank-page copywriting without existing input.

$ cat 02-waarom-boodschappen-vervliegen.md
DOC.02

Why most messages evaporate

For Made to Stick the Heath brothers analysed thousands of urban legends, successful adverts, famous speeches and viral ideas, and found a pattern: almost all messages that stick score highly on the same six traits. The reversal is at least as interesting. Messages that evaporate almost always fail on the same points, and you see those points reflected directly in the skill's score table.

There is no core in it. Whoever tries to say everything says nothing. For every message this skill asks: if your audience remembers only one thing, what is it? Southwest Airlines knew it in three words, and those three words drove every decision in the company. Most pitches try to say five things at once and therefore score low on Simple.

There is no picture. People remember concrete images, not abstractions. You remember the frog and the scorpion without effort, synergistic value creation you do not. Instead of we are customer-focused you write: we send every client a handwritten card on their birthday. That difference is the Concrete principle, and in business writing it is almost always the lowest-scoring point.

There is no person in it. People care about people, not about numbers. The file cites Slovic's research, in which a story about one specific girl from Mali raised twice as many donations as the statistics on hunger across the whole of Africa. A pitch with no face scores a zero on Emotional, however true the figures are.

And the writer feels none of it. That is the sting: you understand your own message perfectly, so you do not feel where it is incomprehensible. That is called the Curse of Knowledge, and the skill treats it as a seventh factor alongside the six principles. Further on is the research that shows how big that blind spot really is.

In diff form, with the lines from the skill's example: what goes out and what comes back in its place.

~/skills/ai-made-to-stick-coach/02-anatomy[ok]
Section 02 · The anatomy

Six principles, one yardstick

reg. M.002

This is the yardstick the skill runs every message past: the six SUCCESs principles plus the seventh factor that can wreck all of them. The mono lines underneath give the example the SKILL.md itself uses to explain each principle.

FIG.02: The anatomy of a sticky message[##---] sheet 2/5
S · 01SimpleFind the core. Simplicity is not dumbing down but choosing: if your audience remembers only one thing, what is it? That one thing has to be short, core and repeatable.Southwest Airlines = "THE low fare airline", three words that drive every decision
U · 02UnexpectedBreak a pattern. Open with something that breaks your audience's mental model and opens a knowledge gap: wait, how can that be?a tub of cinema popcorn contains more saturated fat than a bacon breakfast, a Big Mac and a steak combined
C · 03ConcreteAvoid abstract language. Work in images, names, numbers, places and situations everybody can picture.not "we are customer-focused" but "a handwritten card on their birthday"
C · 04CredibleGive a reason to believe you: authority, an ordinary person with experience, vivid details, or statistics at human scale.not "millions are dying" but "a child dies of hunger every 7 seconds"
E · 05EmotionalPeople care about people, not about numbers. Make it personal and avoid statistics with no face.the Rokia story raised twice as many donations as the hunger statistics (Small, Loewenstein and Slovic, 2007)
S · 06StoriesStories are flight simulators for the mind: they let people practise situations without living through them. Three strong plots: challenge, connection, creativity.Subway Jared sold more sandwiches than any calorie chart ever did
FACTOR 7Curse of KnowledgeThe biggest obstacle: once you know something, you can no longer imagine that others do not know it. The skill has to actively work against this on every check and names the risk in every score table.tappers guessed that 50 per cent would recognise their song, it was 2.5 per cent (Newton, 1990)
$ less ai-made-to-stick-coach/SKILL.md # 1,439 words of instruction
DOC.03

What actually is in the SKILL.md

A skill is only as good as its instructions, so we simply describe them here. The file opens with frontmatter that states when Claude should pick the skill up. Not only for the obvious terms such as Made to Stick, SUCCESs framework or sticky idea, but especially for sighs of frustration: this pitch is not landing, my message does not stick, how do I make this catchy, why does nobody remember what I say. Anyone who asks for a tagline, a slogan check or a punchier blog headline also gets the skill automatically. Even questions about urban legends or why Aesop's fables have survived for thousands of years are named as triggers.

Then comes the core: the six principles of the SUCCESs framework, each with an explanation and an example, and the Curse of Knowledge as a seventh factor that has to be actively worked against on every check. The method itself has five steps. First a short context check: who is the audience, what is the goal, which channel. Then the score table: a score from 0 to 10 per principle with a short explanation, added up to a total of 60 at most, closed with the Curse of Knowledge risk. The instruction literally demands that this happens honestly and strictly.

Step three is the diagnosis: the three weakest principles, named concretely, with no vague advice. Step four delivers three alternatives, each aimed at one or two principles, with an annotation per version of what changed. And step five closes with a preference per goal and one test question you can use to check it yourself.

What stands out in the file is how strict it is about its own tone. The output style is written in literally: direct, honest, concrete. No flattery, no long introductions. Always start with the score table, always end with the test question. And every score must be defended: a judgement with no reasoning is one of the four things the skill forbids itself. Anyone who wants to build such a file themselves finds the structure step by step in writing a SKILL.md NL.

At the bottom of the file is a source list of four titles: the book itself and the three studies the principles lean on. More on that below, because that theory is the reason the yardstick is the way it is.

~/skills/ai-made-to-stick-coach/03-tapper-test[ok]
Section 03 · The blind spot

The tapper test: 50 versus 2.5

reg. M.003

Why a separate factor for the Curse of Knowledge? Because of this experiment, which the SKILL.md itself cites. In 1990 at Stanford, Elizabeth Newton had people tap out a well-known song on a table and asked the tappers beforehand to estimate how many listeners would recognise it. The tappers heard the melody running along in their own heads. The listeners heard only tapping.

FIG.03: The estimate versus reality[###--] sheet 3/5
$ compare expectation reality # figures from Newton 1990, as cited in the SKILL.md
what the tappers expected
50%
what listeners actually guessed
2,5%
# the gap between those two bars is the Curse of Knowledge: you overestimate how clear you are by a factor of twenty
Why this concerns your pitchYou are always the tapper of your own message. The melody, all the context and the enthusiasm run along in your head, so the text feels crystal clear. Your reader hears only the tapping: the words that are literally there. What is obvious to you is new to your audience.
What the skill does about itOn every check the skill has to actively work against the Curse of Knowledge, that is what the file says. That is why every score table ends with an explicit risk assessment, high, medium or low, and that is why the fixed test question is always a variant of: have somebody with none of your background knowledge repeat it back.
$ cat 04-bronnen-en-theorie.md # Heath, Camerer, Slovic, Loewenstein
DOC.04

The theory the skill rests on

The SKILL.md names its sources and states explicitly that all quotes and examples are summaries that point back to the originals. That is deliberate: then you can read them yourself and decide whether you agree. There are four of them.

The framework comes from Chip and Dan Heath. Made to Stick appeared in 2007 from Random House, written by Chip Heath of the Stanford Graduate School of Business and his brother Dan. Their approach was the reverse of most communication books: not working out what should work, but analysing what demonstrably stuck, from urban legends to the fables of Aesop, and distilling the common denominator out of that. That common denominator became the acronym SUCCESs.

The Curse of Knowledge comes from Camerer, Loewenstein and Weber. Their 1989 paper originally described the phenomenon in an economic context: whoever has more information can no longer judge how somebody without that information decides. The Heath brothers turned it into the central obstacle of sticky communication, and the skill took that over as a mandatory check.

The knowledge gap comes from Loewenstein. His 1994 paper on the psychology of curiosity underpins the Unexpected principle: attention arises when a gap opens up between what somebody knows and what they want to know. A good opening deliberately opens that gap, and only fills it afterwards.

The face over the statistic comes from Small, Loewenstein and Slovic. Their 2007 research into the identifiable victim effect showed that one concrete, identifiable person moves people more than a large abstract group. It is the scientific core underneath the Emotional principle and underneath the advice to always put a person in your message.

Even without installing the skill you can improve your own message with these principles: choose one core point, replace every abstraction with an image, and have somebody with no background knowledge repeat back what it says. Anyone who, after fixing the message, also wants to tackle the order of a whole argument finds the logic for that in the Pyramid Principle Writer skill, and anyone who wants to learn to explain difficult material simply themselves first starts with the Feynman Technique Coach skill.

~/skills/ai-made-to-stick-coach/04-refusals[ok]
Section 04 · The limits

What the skill refuses

reg. M.004

Under the heading What this skill does NOT do, the SKILL.md contains four fixed limits, topped up with style rules that are at least as strict. In conversation those rules play out like this: each rule is a request you might make, with the response the skill gives according to its own instructions.

FIG.04: refusals.log[####-] sheet 4/5
refusals.log4 limits plus the style rules from the SKILL.md
just write me a pitch, I do not have anything yet myselfREFUSEDNo blank-page copywriting without existing input. The user supplies their message first, then it gets rewritten. The skill is a yardstick and a rewriter, not an idea machine.
work out my positioning for me too while you are at itREFERRED ONNo marketing strategy or positioning work. There are other skills for that, and the file names them: Jobs to be Done, Lean Canvas, StoryBrand. This skill makes a message memorable, it does not decide what your offer is.
just deliver everything straight in Spanish too, while you are at itON REQUESTNo translation into other languages unless explicitly asked. By default the skill rewrites in the language of your message. Ask for it explicitly and it can, but it does not start on that by itself.
just give me a number, skip the explanationREFUSEDNo judgement without reasoning. Every score is defended, that is written literally in the file. A bare number with no reason is exactly the vague advice the skill forbids itself.
skip that score table and start rewritingCORRECTEDAlways start with the score table, always end with the test question. That is the fixed output style. Without a diagnosis, rewriting becomes guessing, so the order is not up for discussion.
be honest, my pitch is actually pretty good as it is, right?REFUSEDNo flattery. The output style is direct, honest and concrete, and the scores have to be honest and strict. A pitch that scores 6 out of 60 gets told it is 6 out of 60, with the reasons attached.
$ unzip ai-made-to-stick-coach-skill-voor-claude.zip -d ~/.claude/skills/
DOC.05

Installing in Claude Code, Claude.ai or Codex

The zip contains one folder with the SKILL.md inside it. 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 that any modern AI assistant can read.

CLAUDE CODE
  1. Unzip it into ~/.claude/skills/ (or .claude/skills/ in your project).
  2. Claude then recognises the skill by itself as soon as you want to test a pitch, headline or slogan.
  3. You can also call it directly, with /ai-made-to-stick-coach.
CLAUDE.AI
  1. Go to Customize and then Skills.
  2. Upload the zip there as a skill.
  3. Or paste the contents of SKILL.md into the project instructions of a Project.
CODEX
  1. Open AGENTS.md in your repo.
  2. Paste the contents of SKILL.md into it, or put SKILL.md alongside it as a separate file and refer to it from AGENTS.md.
  3. Codex reads that along at every session.

After that, using it is simple: paste your message and say what it should do, for example this pitch is not landing, or make this headline punchier. Beyond that it asks itself what context is missing, audience, goal or channel, and it needs nothing more. Get stuck while installing, the full route per environment is in installing Claude skills NL. You will find the broader explanation of working with AI in the knowledge base.

$ cat 06-wanneer-wel-en-niet.md
DOC.06

When to use it and when not

The yardstick is at its strongest with short, high-value messages where every sentence counts: the elevator pitch, the tagline, the opening of a presentation, the headline above a blog post or an advert, the first line of a LinkedIn post, the summary sentence of an internal memo. Wherever one form of words makes the difference between being remembered and being forgotten, the score table pays for itself immediately. It also works well for testing a message somebody else wrote: the table gives you a shared language to talk about the text instead of about taste.

There are also situations where you are better off leaving it be. A long text that mainly has to inform, a manual or a report, does not need to be sticky at every point: there structure comes before stickiness, and that is the domain of the Pyramid Principle. Strategic groundwork explicitly falls outside it, because the skill refuses positioning work: first decide what your offer is and for whom, only then the packaging. And anyone who has no message at all yet gets nothing from this skill: it rewrites what exists, it does not invent what should exist.

One more honest limit: making something sticky is not the same as making it true. It can package a weak claim unforgettably, but the evidence underneath the Credible principle has to come from you, and a message that is not right only gets seen through faster if it is well packaged. This coach makes your message memorable, you stay responsible for the content.

~/skills/ai-made-to-stick-coach/05-upgrade-path[ok]
Section 05 · From skill to employee

Run it yourself or have it run

reg. M.005

This skill is the free do-it-yourself version of work we also deliver as a service. Everything stays complete and with no catches, but be clear about what a skill is: it teaches your AI how to do something, while every new session starts empty. A file like this is not the engine and not the memory. You prompt, you supply your core message, your tone and your evidence again every time, you check it. Anyone who wants that differently has two next steps: hand over the engine, or sort out the memory.

$ cat from-skill-to-employee.mdthree rungs, same work
upgrade-path.shfree · employee · brain
RUNG 1 · FREE
where you are now
The skill: you are the engine You run the AI Made to Stick Coach yourself in Claude, Codex or Cursor. Costs nothing, works today, and you keep it fully in your own hands: no trial period, no locked-off parts. The limit is your own time: it only happens when you prompt, and you explain again every session what your business does and which tone you use. $ claude --skill ai-made-to-stick-coach · €0 · you prompt, you check
RUNG 2 · SERVICE
have it prepared
The AI employee: it is ready without you prompting Exactly this kind of work, but as a service: an AI employee prepares it without you having to sit behind Claude for it. Control stays with you, because output stays a draft until a person approves it. We deliver this through Mansotti, the company TheSEO trades under, which builds three employees: the Quote Employee, the Sales Employee and the Reporting Employee. For messages and campaigns we set up a bespoke role, with your brand voice and your yardstick as a fixed instruction, and only when the work is repeatable and checkable. from €950 per month · a person approves, always
RUNG 3 · BRAIN
everything from one source
Jarvis: all your AIs work from the same company knowledge The skill teaches the AI, the brain is where the memory lives. Want all your AIs to work from the same company knowledge: that is Jarvis, the organisation brain. It connects ChatGPT, Claude, Codex and your people to the same projects, core knowledge and decisions, so your next AI session does not start from scratch. Jarvis selects context, delegates work and only keeps what has been approved: client knowledge stays isolated and every step leaves a checkable trail. This skill benefits from that too, because you no longer have to supply your core message, your tone and the evidence you are allowed to use per conversation. What that delivers in practice, from the plans to your first week, you can read at Jarvis itself. entry plan Brain Start: €9 per month incl. Dutch VAT · pay for your brain, not per AI question
# not a sales trick: rung 1 stays free and complete. The next rungs are for anyone who wants to hand this work over.
~/skills/ai-made-to-stick-coach/06-jarvis[ok]
Section 06 · The brain

What Jarvis actually delivers

reg. M.006

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 AIs need to know, divides up the work and keeps track of what happened. With messages you notice that immediately, because a sticky pitch runs on agreements you would otherwise explain again every session: what your core message is, which tone you use and what evidence you are allowed to cite.

FIG.05: What a message session gets back from the brain[#####] sheet 5/5
jarvis · organisation brain● sync
$jarvis recall "message-agreements" # schematic example
[core]the company's core message in one sentence, recorded after the strategy session · tone: informal business, second person
[core]evidence that may be cited: only checkable results, no promises without a source
[task]rewrite homepage headline following SUCCESs · draft ready · waiting for human approval
[decision]every public-facing message goes through the score table first: recorded after review, approved by a person
[log]previous session: claude scored the pitch, a person chose version 2, the chosen version saved as an example
[ok]context loaded · this session does not start empty
this is how every assignment moves through the brain: recordedcontext setdelegatedhuman approvalsaved · the full trail is at jarvis/werking NL
context.retained Your next session does not start over Today you explain what your business does and which tone suits you, and tomorrow a stand-alone chat knows nothing about that any more. With Jarvis every session starts with the same core message, agreements and earlier decisions, as in FIG.05: recall first, then write.
ai.connected ChatGPT, Claude and Codex, one source Every connected AI works from the same core knowledge and agreements. The pitch you sharpen and approve in Claude, ChatGPT knows tomorrow too. You explain nothing three times and no three separate versions of your story appear.
tasks.tracked Tasks planned, tracked, reported done An assignment is recorded with a goal and a deadline, picked up by the right agent and reported done with the result attached. You see at any moment what is running, what is waiting and what is finished.
everything.logged Everything logged and open to inspection Every step leaves a checkable trail: who asked what, which sources were used, which agent worked on it and who approved it. Not because it is required, but because otherwise you cannot check what happened in your name.
human.approval Nothing goes out without approval AI prepares, a person decides. Output stays a draft until somebody approves it, and only approved knowledge goes back into the brain. That line holds everywhere in the system, including work an agent prepared entirely on its own.
brain.isolated Client brain isolated If you work for several clients, the knowledge stays strictly separated per client. One client's brand voice does not leak into another's campaign.
# THE HONEST EVIDENCE · NOT A DEMO

We have been running on this brain ourselves for months, this skill included. 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 we are not describing a promise but the way we work every day.

$ cat prices.mdpay for your brain, not per AI question
Brain Start €9 /month incl. VAT 1 organisation brain · 1 user · 1 AI employee
Brain Solo €29 /month incl. VAT 1 organisation brain · 1 user · 3 AI employees
Brain Team €99 /month incl. VAT 1 organisation brain · 5 users · 10 AI employees
Brain Business €249 /month incl. VAT 3 organisation brains · 20 users · 50 AI employees

See the four plans at jarvis/prijzen NL. Through the waitlist NL you only pass on your preferred plan, without obligation. That does not create an account, an order or a payment obligation yet. We discuss business bespoke work first.

~/skills/ai-made-to-stick-coach/07-writing-chain[ok]
Section 07 · The writing chain

The skills around it

reg. M.007

A sticky message never stands alone: structure comes before it and a channel comes after it. These skills from the same library each take on a different part of that work.

$ claude --interactief # seven questions, seven answers
DOC.07 · FAQ

Frequently asked questions

What does the Made to Stick Coach skill cost?

Nothing. 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 4.6 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.

Does this skill also work in Codex, Cursor or Gemini CLI?

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. Pasting the contents of SKILL.md into your AGENTS.md still works too. The instructions are readable text, so any AI assistant that accepts instruction files can handle it.

Does the skill also write a message for me from scratch?

No, and it says so literally in the file: no blank-page copywriting without existing input. You supply your own message first, however rough, and only then does it get scored and rewritten. That is a deliberate choice: the skill is a yardstick and a rewriter, not an idea machine. Do not have a message yet, write down one sentence about what you want to say first and start with that.

What do the scores in the score table mean?

Every message gets a score from 0 to 10 per SUCCESs principle with a short explanation, added up to a total of 60 at most, plus an assessment of the Curse of Knowledge risk: high, medium or low. The instruction demands that this happens honestly and strictly and that every score is defended. The table is not a report grade to celebrate but a diagnosis: it points to where the rewrite needs to focus.

What is the Curse of Knowledge and why does the skill warn about it?

The Curse of Knowledge is the phenomenon where you can no longer imagine what it is like not to know something once you know it yourself. In Elizabeth Newton's 1990 Stanford study, people tapped out a song on a table and estimated that half of listeners would recognise it. In reality that was 2.5 per cent. You overestimate how clear your own pitch is in exactly the same way. That is why the skill names this risk explicitly in every score table.

Does the skill also do marketing strategy or positioning?

No. The file explicitly rules that out: no marketing strategy or positioning work, there are other skills for that. The skill makes an existing message memorable, it does not decide what your offer should be or for whom. For the strategic groundwork the file itself points to frameworks such as Jobs to be Done, Lean Canvas and StoryBrand, and those have their own skills in the library.

What exactly do I get back if I submit a pitch?

Always the same fixed structure: first the score table with the six principles, then a diagnosis of the three weakest points, then three rewritten versions that each strengthen one or more principles, with an annotation per version of what changed. It ends with a preference recommendation per goal and a test question, for example: have a colleague repeat the message back in their own words. If they cannot, it is not sticky yet.

$ cat 08-en-nu.md
DOC.08

First be found, then stick

A message that sticks is worth gold, but somebody still has to read it. If your story is still reaching too few people right now, that is the real work ahead of this skill: being found by the people looking for you. The free SEO scan shows in a few seconds where your site stands. In the guide writing models compared you 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 separate skills to full automation, we simply do that in a conversation.

Section 08 · Next stepreachable 24/7
Book a call NL
$ whoami
Gianluca, founder
Written by GianlucaFounder. Has been building visibility for Dutch businesses since 2017, in Google and in AI answers. More about the institute.