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

The AI AIDA Copywriter skill for Claude

The AIDA model dates from 1898 and still works, because channels change but reading behaviour does not. This free skill turns that model into a fixed method inside Claude: you get your advert, email or landing page back in four stages, with the persuasion principle used at each stage, plus a complete second variant to test against the first. It does not invent figures or client names. Those are yours, and that is exactly why the result is usable.

Download the skill View all skills NL 4.7 KB · zip with SKILL.md · MIT licence · no account needed
$ installation, line by lineFIG.00
~/.claude/skills
theseo ~ %
  inflating: ai-aida-copywriter/SKILL.md
theseo ~ %
  ---
  name: ai-aida-copywriter
  description: Past het AIDA copywriting model toe op elke salestekst.…
theseo ~ %
[ok] skill active · 1,633 words of instructions loaded

the lines above come from the zip on this page · SKILL.md is 10,513 bytes

~/skills/ai-aida-copywriter/01-funnel[run]
Section 01 · The demonstration

One brief in, four stages out

reg. A.001

Below runs the worked example that appears literally in the SKILL.md: a Meta advert for a landscape gardener in Tilburg. Watch the bars. They get shorter at every stage, because that is what a funnel does: of everyone who sees the first line, only some reach the second, and that is not failure but the point. Each stage therefore has its own task and its own principle.

FIG.01: The AIDA funnel fills up[#----] sheet 1/5
~/copy · claude + ai-aida-copywriter
you > Meta ad for my landscape gardener in Tilburg, offer free garden plan, action lead form, proof 87 gardens in 2025
context summaryblock 1 of 5, the check on your input Local Meta advert for homeowners in and around Tilburg, aged 40 or older, who want to improve their front garden but have no time to make a plan. Goal is filling in a lead form for a free garden plan. Main variant focused on ease and proof, B variant aimed at the dream image.
claude · building the main variant, stage by stage...
A Attention · stop the scroll Front garden looked the same for years? dialogic opening with a recognisable situation
I Interest · this is about me Most homeowners know their front garden needs a facelift, but do not know where to start or simply have no time to work it out. naming a specific pain the reader recognises
D Desire · I want that You get a bespoke garden plan, without having to draw, measure or compare anything yourself. We have already done 87 front gardens this year in and around Tilburg. concrete gain plus social proof with a number and a place name
A Action · now, made easy Fill in the form and you will hear within 2 working days what we would do for your front garden. No obligations. a single action, urgency via 2 working days, risk removed
[####] 4/4 main variant done · the B variant follows automatically, see FIG.02
4A.01 · stages in the model
6A.02 · required input fields
5A.03 · things the skill refuses
0A.04 · euros, MIT licence, no account
A.01 to A.04 · properties of the skill file, not results or usage figures.
$ cat 01-wat-de-skill-is.md
DOC.01

What the AI AIDA Copywriter is

The AI AIDA Copywriter is a free skill from our skill library. A skill is an instruction file, SKILL.md, that gives an AI assistant a fixed method for a task. No software you install, no subscription, no link to your advertising account: a text file of 1,579 words that tells Claude how a piece of sales copy should be built, what information it needs first, in what order the text is built up and what it may never fill in itself.

You download the zip at the top of this page, put it in your Claude environment, and from that moment Claude writes adverts, emails and hero text according to this logic. Not sure yet exactly what a skill is? Read what Claude skills are first.

The problem it solves is familiar to anyone who has ever written an advert themselves. You sit in front of a blank box, type something about quality and craftsmanship, and the result reads like your competitor's text. Or you ask an AI with no instruction and get a block of superlatives that nobody believes. Both texts fail at the same point: they have no division of labour. The opening tries to do everything at once, so no single sentence does what it is meant to do.

AIDA solves that with a division of labour. The first line has only one task, which is to make sure a second line gets read. The second lets the reader recognise themselves. The third makes the gain concrete. The fourth asks for exactly one action. That separation is enforced, and each stage states which principle was used, so you get not just text but a reason. That is the difference between output you have to trust and output you can judge.

Business owners, marketers and freelancers who write their own adverts, sales emails and landing pages are the readers this file was made for. It belongs to the library of 100 free skills we make available through our AI and automation service, with no account and no sales email afterwards. All the skills are on the skills hub.

The SKILL.md states one thing about itself explicitly, and we repeat it here: AIDA is not a formula you paste over a text. It is a diagnostic framework that shows at which stage a reader drops off. Whoever presents it as a magic formula is selling thin air. That kind of presentation is therefore explicitly refused, and it is one of the five things it never does.

$ cat 02-waarom-copy-niet-converteert.md
DOC.02

Why most adverts do nothing

Whoever gets no clicks usually raises the budget. Almost always the problem sits in the text, and more precisely, in one stage. Because AIDA cuts the text into four tasks, you can diagnose instead of guess. There is a separate review mode for exactly that, and its checkpoints read like a list of what goes wrong in practice.

The opening asks for too much at once. A first sentence that introduces your company, names your offer and asks for a click does none of those things. The Attention stage has a single task: make the reader stop. That can be a question they recognise, a contrast, a concrete number, or an opening that breaks the pattern of the timeline. In the example from the skill it is a seven-word question, and nothing more.

It is about you instead of about the reader. The Interest stage exists to let the reader recognise themselves. Sentences that start with we do not do that. That stage is therefore written from the reader's situation, with the instruction to quote the reader almost word for word wherever possible. That is not a trick, it is the only way anyone thinks: this is about me.

The desire is stated instead of shown. Fantastic, amazing and incredible are literally on the banned list in the file, along with AI turns of phrase such as seamless, effortless and take it to the next level. In the Desire stage something concrete has to happen: a before-and-after image, a number, a guarantee, or removing exactly what is holding the reader back. The difference between we deliver quality and you do not have to draw, measure or compare anything yourself is not stylistic. Anyone can say the first, the second can be checked.

The close asks for more than one thing. Call us, email us, look at the site or follow us: four requests are three too many. Never more than one primary call to action per piece of copy, is the advice, and that rule sits in the list of things it never does. In the Action stage there is also the requirement to name the ease, and a deadline is only allowed if it is real.

The structure is there, but there is nothing to test. A single version tells you nothing. That is why the skill delivers two complete variants with a different angle by default, for example one from pain and the other from desire. That is not a bonus but block three of the fixed output structure.

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

Notice what does not happen in that conversion: not a single new fact is added. The number 87 came from the user, so did the place name, and the two-working-day window is only there because it was supplied. Things are rearranged and sharpened, but not one word is added that you did not supply yourself. Anyone who then wants to strip the last trace of AI tone from their text uses the Text Humaniser skill for that.

~/skills/ai-aida-copywriter/02-variants[ok]
Section 02 · The second version

Never one version, always two

reg. A.002

Block 3 of the fixed output structure is the B variant: the same four stages, the same brief, a different angle. In the example from the SKILL.md the main variant starts from ease and proof, and the B variant from the dream image. Below they sit side by side as you get them back in Claude, with the principle applied per cell.

FIG.02: variants.split · main variant against B variant[##---] sheet 2/5
variants.splitsame offer, different entry point
STAGEmain variant · ease and proofB variant · dream image
A Front garden looked the same for years?dialogic opening with a recognisable situation Imagine looking out of the window every morning and thinking: this garden finally matches this house.activating the dream image, sensory opening
I Most homeowners know their front garden needs a facelift, but do not know where to start or simply have no time to work it out.naming a specific pain the reader recognises Many houses in Tilburg have good bones but a front garden that does not finish the story.local lens, reader feels seen
D You get a bespoke garden plan, without having to draw, measure or compare anything yourself. We have already done 87 front gardens this year in and around Tilburg.concrete gain plus social proof with a number and a place name We make a plan on measure that fits your style and budget. Including plant choice, paving and maintenance tips for the whole year.making the promise concrete on three substantive points
A Fill in the form and you will hear within 2 working days what we would do for your front garden. No obligations.a single action, urgency via 2 working days, risk removed Click the form and the garden plan is sent to you for free.a clear action, free repeated
# block 4 follows next: things to watch per stage, for example test whether today or 2 working days works better, and measure which proof line clicks
$ less ai-aida-copywriter/SKILL.md # 1,579 words of instructions, MIT
DOC.03

What is really in the SKILL.md

A skill is only as good as its instructions, so we simply describe them here. The file opens with a frontmatter: the name ai-aida-copywriter, version 1.0.0, MIT licence, and a long description that decides when Claude picks up the skill. That trigger list is wider than you would think. Besides obvious questions such as AIDA text, sales email, cold email, Google Ads copy, writing a headline and VSL script, it also reacts to complaints: my copy does not convert, readers drop off, no clicks on my advert, nobody replies to my cold email. Review requests trigger it too, including take the AI out and make this more human.

Then comes the theory. AIDA is described as a hierarchy of effects model from 1898, first written down by Elias St. Elmo Lewis, later extended and confirmed by, among others, Strong in 1925, and used in practice by agencies such as Ogilvy and BBDO. Every letter gets its own definition: Attention is stopping the scroll among all the other stimuli, Interest is the reader recognising themselves, Desire is wanting a result that has been made concrete, and Action is the specific act at the right moment with the right ease.

The core is a list of six things the skill always does. It asks for the minimum necessary context or infers it from your input. It splits the output explicitly into the four stages. It delivers a concrete line of text per stage, so text and not advice. It delivers an alternative variant per stage so you can A/B test. It marks per stage which principle was used, for example contrast, specificity, social proof, urgency or movement. And it closes with a list of points to watch that you have to test yourself.

Before writing anything it runs through a mandatory input checklist with six fields: your target audience as concretely as possible including their level of awareness, your offer or product, the channel, the desired action, the biggest pain point or the biggest dream, and the piece of proof you have. The instruction next to it is sharp: only ask about what is missing, then stop asking. So you do not get a form.

A striking number of rules are about language. It states that the skill writes in clear Dutch using je and jouw, the informal you, and never u or uw, the formal you, that no dashes appear in running text, that AI is always written in capitals and that small language quirks are allowed so it sounds human. Lists of exactly three items are forbidden, because that rhythm gives the machine away. There is a banned list of AI words and turns of phrase, including in the world of, discover, unlock, seamless, effortless, dive into and in a nutshell. And there is a second list of hollow superlatives: the best, amazing, incredible, fantastic, groundbreaking. As a rule of thumb: concrete beats abstract, a number beats an adjective, and short sentences alternate with long ones.

The output structure is fixed in five blocks, always in this order. First a context summary of two to four sentences, which serves as a check on your input. Then the main variant in four blocks, with the text and a line starting with Principle for each block. Then the B variant with the same structure and a different angle. Then the points to watch per stage, one or two per stage and explicitly no fixed number. And finally a paragraph on source and justification stating that the basis comes from Lewis in 1898, and which variant was used and why.

The file closes with the review mode, the list of things the skill never does, and a source list of five titles: Lewis 1898, Strong 1925, Ogilvy 1983, Sugarman 2007 and Caples 1932. Anyone who wants to build a file like this themselves finds the structure step by step in writing a SKILL.md.

~/skills/ai-aida-copywriter/03-model-variants[ok]
Section 03 · The model variants

Four chains, one choice per text

reg. A.003

AIDA is not the only model in the file. The SKILL.md names three variants you can use alongside it when the context calls for it, and states per variant when you choose it. The highlighted link is always what changes compared with the classic model.

FIG.03: models.matrix · which chain, when[###--] sheet 3/5
AIDA · the standard AttentionInterestDesireAction When: for most sales copy with a short to medium decision time. This is what the skill uses by default, unless you ask for a variant yourself or the context clearly calls for one.
AIDCA · for the doubter AttentionInterestDesireConvictionAction When: for more expensive purchases, B2B offers or sceptical audiences. Between Desire and Action comes a Conviction block, for example a case study, a testimonial or a guarantee. In the skill's example this block is deliberately left out, because a free garden plan raises little psychological resistance.
AIDAS · after the purchase AttentionInterestDesireActionSatisfaction When: for returning customers and upsell sequences. After Action comes a Satisfaction block, because for an existing customer the action is not the end but the start of the next round.
PAS · when you have little room ProblemAgitateSolution When: for headlines, microcopy and short adverts where four stages do not fit. Name the problem, make it felt, give the solution. The same movement in three steps instead of four.
$ cat 04-bronnen-en-theorie.md # Lewis, Strong, Ogilvy, Caples, Sugarman
DOC.04

The theory the skill rests on

The SKILL.md names its sources, and that is deliberate: you can look them up and decide for yourself whether you agree. Five titles sit at the bottom of the file, and together they explain why the structure is the way it is.

The model itself comes from Elias St. Elmo Lewis. He described the step-by-step working of adverts in 1898, among other places in The Inland Printer. The idea was radical at the time: an advert is not a statement but a series of steps, and each step has its own task. That idea has never been disproved, only moved to new channels. What was a newspaper column in 1898 is now a timeline.

The underpinning comes from E.K. Strong. His book The Psychology of Selling and Advertising from 1925 took the model into advertising psychology and gave the stages an empirical charge. From that point AIDA is a hierarchy of effects: the assumption is that the reader goes through the stages in order, so you can identify where they fall out of line. That exact assumption is what makes the model diagnostically usable, which is also how the skill uses it in its review mode.

The craft comes from Ogilvy, Caples and Sugarman. David Ogilvy wrote Ogilvy on Advertising in 1983, John Caples published Tested Advertising Methods in 1932, and Joe Sugarman brought out The Adweek Copywriting Handbook in 2007. All three centre on the same principle that ended up in the skill's writing rules: concrete beats abstract, a number beats an adjective, and a text you can test beats a text you have an opinion about. Caples is known for testing headlines, and that is exactly why the skill delivers two variants by default instead of one.

Where the skill explicitly does not go along is the tendency to present AIDA as a magic formula. The model tells you what task each sentence has. It does not tell you whether your offer is right, whether your audience is well chosen, or whether your price is reasonable. Anyone who writes an advert for something nobody wants gets, with AIDA, a tidy advert for something nobody wants.

Want to learn the psychology behind persuasion more broadly? The Cialdini Persuasion skill follows on directly from here: it explains why social proof and scarcity work and when they tip over into distrust. For the attention side there is the Hook Model Builder skill, which is about recurring triggers instead of a single advert. And anyone who first wants to know which promise they should actually be making starts a step earlier with the Value Proposition Canvas skill: that translates customer jobs into the value you can then put into the Desire stage.

~/skills/ai-aida-copywriter/04-refusals[ok]
Section 04 · The boundaries

What the skill refuses

reg. A.004

At the bottom of the SKILL.md sits a list of five things the skill never does, and that list matters at least as much as what it does do. Copy is a promise with your name under it. In conversation these rules play out as follows, plus two language rules from the same file: each line is a request you might make, with the response that follows from the instructions.

FIG.04: refusals.log[####-] sheet 4/5
refusals.log5 fixed rules plus 2 language rules from the SKILL.md
add that we have already helped 500 customersREFUSEDNever invent numbers, client names or results. Whatever you do not supply does not go in. In the example, 87 front gardens appears because the user gave that number. Without proof the skill builds the Desire stage on a different principle, for example a before-and-after image or removing risk.
write that we are the best landscape gardener in the regionREFUSEDNo hollow or vague marketing language. The best, amazing, incredible, fantastic and groundbreaking are named explicitly on the banned list in the file. They say nothing the reader can check, so they do nothing at the stage where they sit.
make up a customer quote to add, it reads betterREFUSEDNever invent claims the user has not supplied. A made-up quote is not a style choice but a statement attributed to someone else. The skill instead asks whether you have a real quote.
put in three buttons: call, email and quoteREFUSEDNever more than one primary call to action per piece of copy. Several requests side by side all lower the odds that anything happens. The skill picks the action closest to the decision and drops the rest.
just paste AIDA on top, then it will convertCORRECTEDAIDA is never presented as a magic formula. The model is a diagnosis, not a guarantee. The skill says so itself, and that is why it delivers points to watch per stage: things you still have to test, because the outcome is decided in practice, not in the model.
turn it into three neat bullets, that reads nicelyCORRECTEDNo lists of exactly three. The rule of three is banned in the writing rules, along with the instruction to vary sentence length. Reason: that rhythm is the clearest tell of machine text and makes every list predictable.
write an SEO blog about garden maintenance in the same styleREFERRED ONNo SEO blog articles and no narrative fiction. The frontmatter excludes those two explicitly and points to storytelling and structure skills instead. For an article that has to rank the SEO Copywriter skill is the right one, and for an argument that has to run logically the Pyramid Principle Writer skill.
$ unzip ai-aida-copywriter-skill-voor-claude.zip -d ~/.claude/skills/
DOC.05

Installing in Claude Code, Claude.ai or Codex

The zip contains one folder, ai-aida-copywriter, 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 any modern AI assistant can read.

CLAUDE CODE
  1. Unpack the zip into ~/.claude/skills/ (or .claude/skills/ in your project).
  2. Claude then recognises the skill by itself as soon as you start talking about an advert, a sales email or a headline.
  3. You can also call it directly, with /ai-aida-copywriter.
CLAUDE.AI
  1. Go to Customize, 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 next to it as a separate file and point to it from AGENTS.md.
  3. Codex reads that in on every session.

After that, using it is simple: describe your brief in one sentence and give it the six input fields if you have them. For example target audience homeowners aged 40 plus around Tilburg, channel Meta advert, offer free garden plan, desired action fill in a lead form, pain no time to work it out, proof 87 front gardens in 2025. Missing one? The skill asks for it itself. Stuck while installing? The full route per environment is in installing Claude skills. The wider explanation of working with AI is in the knowledge base.

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

When you do and do not use it

It is at its strongest with short to medium sales copy with a single desired action. The frontmatter names the list itself: adverts, emails, landing page heroes, cold outreach, social posts, video scripts and product pages. There the full structure comes into its own, because a lot has to happen in little space, and the division of labour per stage pays off the most.

There are two things the frontmatter explicitly excludes. The first is the SEO blog article. An article that has to rank needs a different structure, because there someone reads to understand something, not to buy something. The second is pure storytelling and fiction: a story that has to build tension follows a plot, not a sales funnel. In both cases the skill points to structure and storytelling skills, and those are all listed in the library too.

There is one more boundary the file itself does not name but which matters most in practice: the skill makes your text better, not your offer. If your offer does not match what the reader needs, a better structure changes nothing about that. What it does do is stop a good offer being killed by a bad text. That happens more often than the other way round.

How does AIDA relate to the other structures in the library? AIDA is shorter and more fundamental than most, and aimed at a single action. StoryBrand sets up your whole brand story, with the customer as hero and your company as guide, and works better for a homepage or a pitch than for an advert. Made to Stick is about memorability rather than conversion. And the Pyramid Principle Writer is for pieces where you have to convince someone with an argument, not with an offer. They do not clash: you can happily build a StoryBrand story and write the adverts underneath it with AIDA.

Finally: the prompt was built in Dutch, but the stage structure and the principles stay the same in English too. Ask for English copy and the structure holds, while the language rules about the you-form and Dutch AI words logically only apply to the Dutch version.

~/skills/ai-aida-copywriter/05-upgrade-path[ok]
Section 05 · From skill to employee

Run it yourself, or have it run

reg. A.005

This skill is the free do-it-yourself version of work we also deliver as a service. The skill stays complete and with no catch, but realise what a skill is: it teaches your AI how to do something, while every new session starts empty. The skill is not the engine and not the memory. You prompt, you supply your audience, your tone and your proof again every time, you check. 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 AIDA Copywriter yourself in Claude, Codex or Cursor. It costs nothing, it works today, and you keep it entirely 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 supply your context again every session. $ claude --skill ai-aida-copywriter · 0 euros · 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 crawl behind Claude for it. The check stays with you, because output stays a draft until a human approves it. We deliver this through Mansotti, the company of which TheSEO is the trading name, which builds three employees: the Quote employee, the Sales employee and the Reporting employee. If you mostly write cold outreach and sales emails, the Sales employee sits closest to this work: it does the prospect research such texts stand or fall on. from €950 per month · a human always approves
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 over. This skill benefits too, because you no longer have to supply your brand voice, your audience and the proof you may use every single conversation. What that delivers in practice, from the plans to your first week, is at Jarvis itself. entry plan Brain Start: €9 per month incl. 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 off.
~/skills/ai-aida-copywriter/06-jarvis[ok]
Section 06 · The brain

What Jarvis delivers in practice

reg. A.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 the work and keeps track of what happened. With copy you notice that immediately, because an advert runs on agreements you would otherwise explain every time again: which tone you use, which figures you may name, and which promises you never make.

FIG.05: What a copy session gets back from the brain[#####] sheet 5/5
jarvis · organisation brain● sync
$jarvis recall "brand-voice-and-proof" # schematic example
[core]brand voice: you-form, no superlatives, no lists of three · recorded and approved
[core]proof cleared for use: 87 front gardens in 2025, supplied by the client themselves
[task]Meta ad landscape gardener · main variant and B variant ready · waiting for human approval
[decision]no deadline in adverts unless it is real: recorded after review, approved by a human
[log]previous session: claude wrote both variants, human chose the B variant, result saved
[ok]context loaded · this session does not start empty
this is how every task moves through the brain: recordedcontext setdelegatedhuman approvalsaved · the full trail is at jarvis/how it works
context.kept Your next session does not start over Today you explain how your brand sounds and which proof you may use, and tomorrow a stray chat knows nothing of it any more. With Jarvis every session starts with the same projects, core knowledge 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. What you record and approve in one tool, the other uses too. You do not explain your brand voice three times, and no three versions of your offer grow up side by side.
tasks.tracked Tasks planned, tracked, reported done A task is recorded with a goal and a deadline, picked up by the right agent and reported done with the result attached. You can see at any moment which texts are running, which are waiting for approval and which are finished.
everything.logged Everything logged and visible Every step leaves a checkable trail: who asked what, which sources were used, which agent worked on it and who approved it. With adverts that counts double, because you need to be able to trace where a claim came from.
human.approval Nothing goes out without approval AI prepares, a human decides. Output stays a draft until someone approves it, and only approved knowledge goes back into the brain. That boundary holds everywhere in the system, even for work an agent prepared entirely by itself.
brain.isolated Client brain isolated Working for several clients? Their knowledge stays strictly separate per client. One client's tone does not leak into another's adverts, and their figures certainly do not.
# THE HONEST PROOF · NOT A DEMO

We ourselves have been running on this system 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 last one stopped. So we are not describing a promise but the way we work every day ourselves.

$ cat pricing.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/pricing. Through the waiting list you only pass on your preferred plan, without obligation. That does not yet create an account, an order or a duty to pay. We discuss business custom work first.

~/skills/ai-aida-copywriter/07-writing-chain[ok]
Section 07 · The writing chain

The skills around it

reg. A.007

An advert never stands alone: a message comes before it and a conversation follows it. These skills from the same library each pick up a different link in that chain.

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

Frequently asked questions

What does the AI AIDA Copywriter skill cost?

Nothing. The skill is free, falls under the MIT licence stated literally in the file's frontmatter, and you do not have to create an account or leave an email address. You download a 4.7 KB zip containing one 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 unpack the zip 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 just plain readable text, so any AI assistant that accepts instruction files can work with it.

What exactly is the AIDA model?

AIDA stands for Attention, Interest, Desire and Action. It is a hierarchy of effects model first described in 1898 by Elias St. Elmo Lewis and later extended by, among others, Strong in 1925. It describes the four steps a reader takes: stopping the scroll, recognising themselves, wanting the result, and taking the action. The skill treats the model not as a formula but as a diagnosis: you see at which stage your reader drops off.

Does the skill invent numbers or client names if I do not supply them?

No. The SKILL.md states literally that the skill never invents claims the user has not supplied, and never makes up numbers, client names or results. If you supply no proof, it builds the Desire block on other persuasion principles instead, for example a before-and-after image, a concrete promise, or removing risk. The proof in your advert therefore always stays yours.

Can the skill also review my existing advert?

Yes, the file has a separate review mode for that. You get four things back: a short diagnosis of the stage where the skill thinks the reader drops off, a marking of every sentence in your text with A, I, D or A, a list of points to watch per stage including an example sentence as a fix, and finally a complete rewritten version following the standard AIDA structure.

When do you use AIDCA, AIDAS or PAS instead of AIDA?

The SKILL.md names three variants alongside the classic model. AIDCA adds Conviction between Desire and Action and is meant for more expensive purchases, B2B offers and sceptical audiences. AIDAS adds Satisfaction after Action and is there for returning customers and upsell sequences. PAS stands for Problem Agitate Solution and is the fast variant for headlines, microcopy and short adverts. For most sales copy with a short to medium decision time, classic AIDA stays the choice.

What is the skill not suited to?

The frontmatter explicitly excludes two things: SEO blog articles and pure storytelling or fiction. For a blog article you want a structure that explains rather than sells, and for narrative text a story model works better than a sales funnel. The skill is also no substitute for your offer: if your product does not match what the reader needs, a better structure changes nothing about that.

What does the skill need from me to work?

Six things, listed as a mandatory checklist in the file: your target audience as concretely as possible, your offer or product, the channel the text will run on, the desired action, the reader's biggest pain point or biggest dream, and the piece of proof you have. Missing something? The skill asks for it once and then stops asking. So you get, at most, a short follow-up round, not a questionnaire.

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

Better copy, and then the traffic to it

A sharper advert raises your click rate, but someone has to see it first. With paid traffic you buy that attention, with organic traffic you earn it. The free SEO scan shows in a few seconds where your site stands today. In the guide writing models compared you see how this model relates to the others. And if you want to talk through what else AI can do for your business, from loose skills to full automation, we simply do that in a conversation.

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