README.md
# big-idea
> Generates creative concepts for ads, campaigns, promotions, stunts, taglines, and headlines, worked the way the advertising canon works and tested against its landmark campaigns.
## What it does
`big-idea` treats creative work as a method rather than inspiration. It follows James Webb Young's *A Technique for Producing Ideas*: an idea is a new combination of old elements, so the skill gathers a fact sheet of raw material first (product facts, audience truths, category conventions, culture), then generates widely through a set of lenses, strikes anything a rival agency would also bring, and judges what survives against Ogilvy's big-idea questions and the rest of the canon.
The lenses, tests, and cases draw on Young, Claude Hopkins, Rosser Reeves, Ries & Trout, David Ogilvy, Bill Bernbach, Leo Burnett, George Lois, Mary Wells Lawrence, Dave Trott, Rory Sutherland, Paul Feldwick, James Hurman, Luke Sullivan, Bob Schmetterer, Ed Catmull, Cialdini, the Heath brothers, Jonah Berger, Kahneman, Ariely, Godin, and Mario Pricken. Each concept it delivers names an **ancestor**, a landmark campaign that solved a similar problem with a similar move, and says what the new idea takes from it and where it departs.
## When to use it
- *"Campaign ideas for a regional bank that wants younger customers."*
- *"A launch stunt for our new electric scooter in Lisbon."*
- *"Tagline options for a sleep-tracking ring."*
- *"We're No. 3 in the category. How do we make that work for us?"*
- *"A promotion that gets people to try our oat milk in coffee shops."*
- *"An angle for our launch post that isn't another feature list."*
**Not the right skill if** you need a brand's visual identity (→ [`creative-director`](../creative-director/)), a logo (→ [`logo-studio`](../logo-studio/)), or a shootable script for a concept you already have (→ [`video-script`](../video-script/)).
## Example walkthrough
**Prompt**
> Ideas for a neighborhood bakery that only bakes in the morning and sells out by noon. They want more people to know about them without looking like a chain.
**What the skill does**
1. **Problem:** "The problem is that people who would love this bread arrive after it's gone, and the bakery reads the sell-out as a failure to fix."
2. **Raw material:** the bake starts at 3 a.m.; the sourdough starter is 19 years old; nothing is made after 7 a.m.; the category wallpaper is "artisan," wheat fields, and flour-dusted hands.
3. **Angles:** the sell-out as a virtue (flaw as virtue); the 3 a.m. baker (inherent drama); the bakery against the all-day chain (the enemy).
4. **Generates** 40+ one-line ideas across the lenses, writes the rival's pitch ("artisan, handmade, community"), and strikes what matches it.
5. **Delivers three concepts**, such as:
**Concept: "Gone by Noon"**
> **The idea:** The bakery publishes the time it sells out each day, as a scoreboard.
> **Ancestor:** Guinness, "Good things come to those who wait": the inconvenience turned into the proof of quality.
> **Hero execution:** A chalkboard in the window reads "Yesterday: gone by 11:42." A daily post with the time. Regulars bet on it.
## Installation
```bash
npx skills add thatjuan/agent-skills --skill big-idea
```
## Bundled resources
| File | Purpose |
|------|---------|
| `SKILL.md` | The vocabulary, the seven-step workflow, the selection tests, and the output format |
| `references/canon.md` | What each book and master teaches, as a principle to apply and a question to ask |
| `references/lenses.md` | Forty-odd generative lenses, each with a prompt, its source, and a campaign that used it |
| `references/cases.md` | Landmark campaigns from Schlitz to Draw Ketchup: problem, insight, leap, and why it worked |
| `references/executions.md` | Writing headlines, body copy, taglines, print and outdoor, film, promotion mechanics, and social |
## Tips
- **Give it real facts.** A factory visit, founder notes, reviews, and support tickets are raw material; the best ideas come from details nobody thought were interesting.
- **Name the real constraint.** Budget, channel, and what the brand can actually change shape the idea more than tone words do.
- **Say what's been tried.** Past campaigns and competitors' work go straight into the wallpaper the idea has to break.
- **Ask for the also-rans.** The ideas cut in selection are often the seed of the next round.
- **Push on the strategy before the execution.** If none of the three concepts feels right, the angle is usually what's wrong.
## Related skills
- [`video-script`](../video-script/) — turn a concept's film into a shot-by-shot script.
- [`video-production`](../video-production/) — produce the video.
- [`creative-director`](../creative-director/) — the visual world around the brand.
- [`clean-writing`](../clean-writing/) — tighten long-form copy.
references/canon.md
# Canon
What the books on advertising and creativity teach, condensed to principles you can apply. Each entry gives the source, the principle, and the question it puts to a brief. Masters disagree (Reeves's hard sell against Bernbach's soft persuasion, Hopkins's testing against Feldwick's showmanship), and that disagreement is useful: each angle in step 3 can come from a different school.
## Method
### James Webb Young: *A Technique for Producing Ideas*
- **Principle:** An idea is a new combination of old elements. The talent for combining is the habit of seeing relationships between facts.
- **The five steps:** (1) gather raw material, both specific (product, audience) and general (life, culture); (2) digest it, turning facts over and looking for how they fit together; (3) drop the problem and let the unconscious work; (4) the idea arrives, usually when you are not looking for it; (5) shape the idea and expose it to criticism until it fits real conditions.
- **Ask:** Do I have enough raw material for a combination to happen? What two facts on this sheet have never been put side by side?
### Isaac Asimov: *On Creativity* (essay)
- **Principle:** New ideas come from people who connect things others had not thought to connect. Generating ideas needs freedom from judgment; judging needs a separate pass.
- **Ask:** Am I judging while generating? Which two distant fields does this brief sit between?
### Ed Catmull: *Creativity, Inc.*
- **Principle:** Early ideas are "ugly babies": awkward, unfinished, easily killed. Protect them long enough to develop, then subject them to candid review (Pixar's Braintrust).
- **Ask:** Is the promising-but-ugly idea being cut because it is wrong, or because it is unfinished?
## The hard sell: facts, claims, testing
### Claude C. Hopkins: *Scientific Advertising*
- **Principle:** Advertising is salesmanship in print. Specific facts sell; platitudes slide off. Test everything that can be tested, and use samples and coupons to make response measurable.
- **The preemptive claim:** Schlitz advertised steam-cleaned bottles and water from deep wells. Every brewer did the same, but the first to say it owned it.
- **Ask:** What does this product do that everyone in the category does but nobody says? What is the number, the process, the detail?
### Rosser Reeves: *Reality in Advertising*
- **Principle:** The Unique Selling Proposition has three parts: a specific benefit ("buy this, get this"), one competitors cannot or do not offer, and strong enough to move large numbers of people. Repeat it relentlessly.
- **Example:** M&M's, "Melts in your mouth, not in your hand."
- **Ask:** What is the one benefit only we can claim? Could it be said in seven words?
### Al Ries & Jack Trout: *Positioning*
- **Principle:** The battle is in the prospect's mind, not the product. Be first in a category, or create a new category you can be first in. Own one word (Volvo owns *safety*). Position against the leader when you cannot be the leader.
- **Examples:** 7Up as "the Uncola"; Avis as No. 2.
- **Ask:** What word do we want to own? What is the ladder in the customer's mind, and which rung can we take?
## The creative revolution: craft, honesty, theatre
### David Ogilvy: *Confessions of an Advertising Man*, *Ogilvy on Advertising*
- **Principle:** "We sell, or else." Research the product until you find the fact. Five times as many people read the headline as the body, so the headline carries the sale. Long copy sells when it is interesting. Give the brand a consistent personality (brand image) and build it over years.
- **Story appeal:** The eye patch on the Hathaway shirt man made readers ask who he was.
- **The big idea test:** Did it make me gasp when I first saw it? Do I wish I had thought of it myself? Is it unique? Does it fit the strategy to perfection? Could it be used for 30 years?
- **Ask:** What fact did the research turn up that nobody has used? What would make a reader stop and wonder?
### Bill Bernbach (*Bill's Book*, Bob Levenson; *Think Small*, Dominik Imseng)
- **Principle:** Persuasion is an art, not a science. Honesty is disarming: admit the flaw and the audience believes the rest. Simplicity, wit, and respect for the reader's intelligence. Copywriter and art director work as one team, so word and picture make a single idea.
- **Examples:** Volkswagen "Think Small" and "Lemon"; Avis "We Try Harder."
- **Ask:** What is the product's weakness, and how is it a strength? What would we say if we told the plain truth?
### Leo Burnett
- **Principle:** Find the **inherent drama**: the reason people buy, already present in the product. Warm, folksy, archetypal characters (the Jolly Green Giant, Tony the Tiger, the Marlboro cowboy).
- **Example:** Green Giant peas, "Harvested in the moonlight": a production fact made romantic.
- **Ask:** Where is the drama hidden inside the product itself?
### George Lois: *George, Be Careful*
- **Principle:** The big idea is a single, shocking, simple image-and-word combination that makes people talk. Art direction is a form of argument.
- **Examples:** Esquire covers (Muhammad Ali as Saint Sebastian); "I want my MTV."
- **Ask:** What is the image that would cause an argument at dinner?
### Mary Wells Lawrence: *A Big Life in Advertising*
- **Principle:** Advertising as theatre and as a change to the product itself. She had Braniff's planes painted in bright colors ("the end of the plain plane") rather than only advertising them.
- **Ask:** What could we change in the product, packaging, or experience so that the change is the ad?
### Jerry Della Femina, Phil Dusenberry, Pat Fallon (memoirs)
- **Principle:** The work comes from irreverence, from obsession with the craft, and from treating creativity as leverage: Fallon built a practice on outsized results from smaller budgets.
- **Ask:** If we had a tenth of the budget, what idea would we need?
## Modern strategy: reframing, behavioral science, fame
### Dave Trott: *Predatory Thinking*
- **Principle:** Get upstream of the problem and reframe it. You do not have to outrun the lion, only the other man. Most advertising is invisible, so the first job is to be noticed, the second to be remembered, the third to persuade.
- **Ask:** What is the real problem behind the stated one? What would make this impossible to ignore?
### Rory Sutherland: *Alchemy*
- **Principle:** Logic is a poor guide to human behavior, and the opposite of a good idea can also be a good idea. Changing perception is often cheaper than changing reality. Costly signals create trust.
- **Examples:** Rather than spend billions to make the Eurostar journey shorter, make it so pleasant (supermodels serving free champagne) that passengers would ask for it to be longer. Red Bull's small can, high price, and odd taste signal potency.
- **Ask:** What would we do if this were a psychological problem? What is the opposite of the obvious answer?
### Paul Feldwick: *The Anatomy of Humbug*, *Why Does the Pedlar Sing?*
- **Principle:** The rational models (USP, AIDA) explain less than they claim. Much effective advertising works through **fame** and **showmanship**: entertainment, spectacle, and likability that make a brand famous. The pedlar sings to draw a crowd.
- **Example:** Cadbury Smash's Martians laughing at humans who peel potatoes.
- **Ask:** Would people seek this out? Would they sing it, quote it, retell it?
### James Hurman: *The Case for Creativity* (after Binet & Field)
- **Principle:** Award-winning creative work is measurably more effective. Emotional campaigns outperform rational ones over the long term; fame campaigns perform best of all; split investment between long-term brand building and short-term activation (roughly 60:40).
- **Ask:** Is this idea emotional enough, and famous enough, to build the brand beyond this quarter?
### Luke Sullivan: *Hey, Whipple, Squeeze This*
- **Principle:** Mr. Whipple, who badgered shoppers not to squeeze the Charmin, stands for the advertising everyone hates: loud, repetitive, insulting. Find the tension in the brand. Write hundreds of headlines. Express the strategy as simply as possible, then dramatize it. Your first ideas are everyone's first ideas.
- **Ask:** Would I put this on my wall, or am I settling?
### Bob Schmetterer: *Leap*
- **Principle:** The best creative ideas go beyond advertising and change the business: a new product, service, channel, or behavior ("creative business ideas").
- **Ask:** What if the idea were not an ad at all?
## Persuasion and spread
### Robert Cialdini: *Influence*
Reciprocity, commitment and consistency, social proof, authority, liking, scarcity (and later, unity). Every promotion uses at least one; the best use it as the idea rather than as a footnote.
### Chip & Dan Heath: *Made to Stick*
Sticky ideas are **SUCCESs**: Simple, Unexpected, Concrete, Credible, Emotional, Stories. Use it to sharpen an idea once found: which of the six is it missing?
### Jonah Berger: *Contagious*
Ideas spread through **STEPPS**: Social currency (it makes the sharer look good), Triggers (the environment reminds people), Emotion (high arousal), Public (visible use), Practical value, Stories (the brand rides inside a narrative). Use it to pressure-test a stunt or social idea.
### Daniel Kahneman: *Thinking, Fast and Slow*
Most ad processing is System 1: fast, intuitive, low attention. Framing, loss aversion, anchoring, availability, and the peak-end rule shape choices more than arguments do.
### Dan Ariely: *Predictably Irrational*
People judge by relativity, so a decoy option shifts choice (*The Economist*'s print-only offer priced the same as print-plus-web). FREE is not just a low price; it changes behavior.
### Seth Godin: *Purple Cow*
A brown cow is invisible; a purple cow is remarkable. Being very good is the new boring; safe is risky.
### Malcolm Gladwell: *The Tipping Point*
Connectors, mavens, and salesmen carry ideas; stickiness matters; small changes in context tip behavior.
## History and pattern libraries
Mark Tungate's *Adland*, Kenneth Roman's *The King of Madison Avenue*, Karen Stabiner's *Inventing Desire*, Bart Cummings's *Advertising's Benevolent Dictators*, and the memoirs of Charlie Brower, John Orr Young, Jerry Goodis, and James Webb Young give the case history that [Cases](cases.md) condenses. Mario Pricken's *Creative Advertising* organizes hundreds of campaigns by the creative method behind them, the approach [Lenses](lenses.md) follows.
references/cases.md
# Cases
Landmark campaigns, each broken into the problem it faced, the insight, the leap, and why it worked. Use them in step 4 as fuel (what move solved a problem like this one?) and in step 7 as the **ancestor** for each concept. Take the move, not the surface: a new idea that copies an ancestor's look is a pastiche, while one that reuses its logic on fresh raw material is craft.
Dates and agencies are given where well documented; treat them as context, not as claims to put in client work without checking.
## The creative revolution, 1950s–1970s
**Volkswagen, "Think Small" and "Lemon"** — DDB, 1959–60
- *Problem:* A small, odd-looking German car in an America of chrome and tailfins, fifteen years after the war.
- *Insight:* Americans were tired of being oversold. Honesty would be a novelty.
- *Leap:* A tiny car in a sea of white space with "Think Small." A pristine Beetle headlined "Lemon," because an inspector had rejected it over a blemished chrome strip on the glove compartment.
- *Why it worked:* Admitting the flaw made every other claim credible. Self-deprecating wit respected the reader.
- *Lenses:* Flaw as virtue, Break the wallpaper.
**Avis, "We Try Harder"** — DDB, 1962
- *Problem:* Avis was the distant No. 2 to Hertz and losing money.
- *Insight:* The underdog is more motivated, and people root for the underdog.
- *Leap:* "Avis is only No. 2 in rent a cars. So why go with us? We try harder."
- *Why it worked:* It turned a weakness into a promise of service and gave employees a standard to live up to.
- *Lenses:* Number two, Flaw as virtue.
**Hathaway shirts, "The man in the Hathaway shirt"** — Ogilvy, 1951
- *Problem:* A small shirtmaker with a tiny budget in a category of identical ads.
- *Insight:* A detail that raises a question makes readers stop and supply a story.
- *Leap:* An aristocratic model wearing an eye patch.
- *Why it worked:* Story appeal. The eye patch became the brand's signature for years.
- *Lenses:* Character, Showmanship.
**Rolls-Royce, "At 60 miles an hour the loudest noise in this new Rolls-Royce comes from the electric clock"** — Ogilvy, 1958
- *Problem:* Saying "luxury" and "quality" in a way readers would believe.
- *Insight:* One concrete fact proves more than any adjective.
- *Leap:* A line lifted from an engineering report, followed by long copy full of more facts.
- *Why it worked:* Specificity is credibility.
- *Lenses:* The buried fact.
**Schlitz beer** — Claude Hopkins, early 1900s
- *Problem:* Schlitz was fifth in its market; every brewer claimed "purity."
- *Insight:* Visiting the brewery, Hopkins found steam-cleaned bottles, filtered air, and artesian wells. The brewers considered all of it standard.
- *Leap:* Tell the process in detail.
- *Why it worked:* Standard to the brewer was astonishing to the drinker, and the first to say it owned it.
- *Lenses:* Preemptive claim, The buried fact.
**M&M's, "Melts in your mouth, not in your hand"** — Ted Bates (Rosser Reeves), 1954
- *Problem:* Selling candy-coated chocolate.
- *Insight:* The candy shell was a real, unique benefit.
- *Leap:* The USP in seven words, demonstrated on screen with two hands.
- *Lenses:* The USP in seven words, Demonstration.
**Green Giant, "Harvested in the moonlight"** — Leo Burnett
- *Problem:* Peas are peas.
- *Insight:* The peas were packed quickly after picking, sometimes overnight.
- *Leap:* Turn a logistics fact into romance.
- *Lenses:* Inherent drama.
**De Beers, "A Diamond Is Forever"** — N.W. Ayer, 1947
- *Problem:* Making diamonds an expected part of an engagement.
- *Leap:* Four words linking the stone to permanence and love.
- *Why it worked:* It built a ritual, not a sale, and implied a diamond should never be resold.
- *Lenses:* Cultural artifact, Own a word.
**Braniff, "The End of the Plain Plane"** — Wells Rich Greene, 1965
- *Problem:* A regional airline indistinguishable from the rest.
- *Leap:* Paint the planes in bright colors and dress the crew in designer uniforms.
- *Why it worked:* The product change was the ad.
- *Lenses:* Change the product, Break the wallpaper.
**Cadbury Smash, the Martians** — BMP, 1974
- *Problem:* Instant mashed potato looked like a lazy compromise.
- *Leap:* Robot Martians laughing hysterically at primitive Earthlings who peel, boil, and mash potatoes by hand.
- *Why it worked:* Entertainment made the brand famous; the joke reframed the old way as the absurd one.
- *Lenses:* Showmanship, Character, The opposite.
**I ❤ NY** — Wells Rich Greene with Milton Glaser's logo, 1977
- *Problem:* New York had a reputation for crime and decline.
- *Leap:* A declaration of love anyone could wear.
- *Why it worked:* Simple enough to become a cultural artifact, copied worldwide.
- *Lenses:* Cultural artifact, Identity.
**Pepsi Challenge** — 1975
- *Problem:* No. 2 to Coca-Cola.
- *Leap:* Public blind taste tests, filmed.
- *Why it worked:* The promotion was a demonstration, and the leader could not answer it in kind.
- *Lenses:* Blind test, Number two, Demonstration.
## The 1980s and 1990s
**Apple, "1984"** — Chiat/Day, directed by Ridley Scott, 1984
- *Problem:* Launching the Macintosh against IBM.
- *Insight:* Frame computing as freedom against conformity.
- *Leap:* An Orwellian film in which a runner smashes Big Brother's screen; it aired nationally once, during the Super Bowl.
- *Why it worked:* An enemy, a metaphor, and a single event that became news in itself.
- *Lenses:* The enemy, Metaphor, One shot only.
**Wendy's, "Where's the beef?"** — Dancer Fitzgerald Sample, 1984
- *Leap:* An elderly woman peering at a giant bun with a tiny patty.
- *Why it worked:* Attacks rivals on a concrete fact, and the line entered politics as a catchphrase.
- *Lenses:* The enemy, Character.
**The Economist, red posters** — Abbott Mead Vickers, from 1988
- *Leap:* White type on red, one witty line: "'I never read The Economist.' Management trainee. Aged 42."
- *Why it worked:* A fixed template that flatters the reader's intelligence; each poster is an event.
- *Lenses:* Format serial, Identity.
**Nike, "Just Do It"** — Wieden+Kennedy, 1988
- *Problem:* Reaching beyond hardcore athletes.
- *Insight:* Everyone has a voice telling them not to bother.
- *Leap:* Three words addressed to anyone, inspired by a condemned man's last words, "Let's do it."
- *Why it worked:* It made the customer the hero and became a personal motto.
- *Lenses:* Customer as hero, Unsaid truth.
**Absolut Vodka, the bottle series** — TBWA, from 1980
- *Leap:* Every ad is the bottle shape plus a two-word headline: "Absolut Perfection," then cities, artists, puns.
- *Why it worked:* A template that ran for decades and became collectible.
- *Lenses:* Hero the product, Format serial, Visual pun.
**California Milk Processor Board, "Got Milk?"** — Goodby Silverstein & Partners, 1993
- *Problem:* Milk consumption was falling, and "milk is good for you" was ignored.
- *Insight:* People think about milk only when they run out of it.
- *Leap:* Deprivation: a history buff who could win a radio contest but can't say "Aaron Burr" through a mouth full of peanut butter.
- *Lenses:* Deprivation, Loss frame.
**Apple, "Think Different"** — TBWA\Chiat\Day, 1997
- *Problem:* Apple near collapse; the brand needed to remind people what it stood for.
- *Leap:* Portraits of Einstein, Gandhi, Picasso, and others: "Here's to the crazy ones."
- *Why it worked:* It sold identity, not specs, to employees as much as customers.
- *Lenses:* Identity, The enemy (conformity).
**Guinness, "Surfer"** — AMV BBDO, 1999
- *Problem:* The slow pour annoyed drinkers in busy pubs.
- *Insight:* Waiting builds anticipation.
- *Leap:* "Good things come to those who wait," with surfers waiting for the perfect wave of white horses.
- *Lenses:* Flaw as virtue, Showmanship.
**Hotmail, "PS: I love you. Get your free email at Hotmail"** — 1996
- *Leap:* A line appended to every email users sent.
- *Why it worked:* Every user became a channel. Free plus visible use.
- *Lenses:* The free thing, Media as message.
## The 2000s
**BMW Films, "The Hire"** — Fallon, 2001
- *Leap:* Short films by major directors, released online, with the car as co-star.
- *Why it worked:* Content people sought out, years before branded content was a category.
- *Lenses:* Showmanship.
**Dove, Campaign for Real Beauty** — Ogilvy, from 2004
- *Insight:* Very few women described themselves as beautiful.
- *Leap:* Real women in ads; later "Real Beauty Sketches" (2013), in which a forensic artist draws women as they describe themselves and as strangers describe them.
- *Lenses:* Challenge a belief, Break the wallpaper.
**Dos Equis, "The Most Interesting Man in the World"** — Euro RSCG, 2006
- *Leap:* An absurdly legendary gentleman: "I don't always drink beer. But when I do, I prefer Dos Equis."
- *Lenses:* Character, Exaggeration.
**Apple, "Get a Mac"** — TBWA\Media Arts Lab, 2006
- *Leap:* Two men personifying Mac and PC in conversation.
- *Lenses:* Identity, The enemy, Character.
**Blendtec, "Will It Blend?"** — 2006
- *Leap:* The founder blends phones, marbles, and rakes on camera.
- *Why it worked:* A torture test as an entertaining online serial on almost no budget.
- *Lenses:* Demonstration, Torture test, Format serial.
**Burger King, "Whopper Sacrifice"** — Crispin Porter + Bogusky, 2009
- *Leap:* A Facebook app: unfriend ten friends, get a free Whopper, and the unfriended were notified.
- *Why it worked:* It measured exactly what a friendship was worth.
- *Lenses:* Persuasion principle as idea, The free thing.
**Domino's, "Pizza Turnaround"** — Crispin Porter + Bogusky, 2009–10
- *Problem:* Customers said the pizza tasted like cardboard.
- *Leap:* Rebuild the recipe and broadcast the brutal focus-group feedback.
- *Why it worked:* Honesty plus a real product change.
- *Lenses:* Upstream, Honest apology, Change the product.
## The 2010s and after
**Old Spice, "The Man Your Man Could Smell Like"** — Wieden+Kennedy, 2010
- *Insight:* Women bought much of their partners' body wash.
- *Leap:* A one-take spot addressed to women, then hundreds of personalized video replies to people online within days.
- *Lenses:* The real buyer, Exaggeration, Character.
**Snickers, "You're not you when you're hungry"** — BBDO, 2010
- *Leap:* Hungry people turn into someone else (Betty White playing American football).
- *Why it worked:* A universal truth with an endlessly casting-flexible template.
- *Lenses:* Unsaid truth, Exaggeration, Format serial.
**Patagonia, "Don't Buy This Jacket"** — 2011
- *Leap:* A Black Friday full-page newspaper ad asking customers to buy less.
- *Lenses:* The opposite, Costly signal.
**Coca-Cola, "Share a Coke"** — Ogilvy Sydney, 2011
- *Leap:* Popular first names printed on the bottles.
- *Why it worked:* The pack became personal, giftable, and shareable.
- *Lenses:* Change the product, Reflect them back.
**Metro Trains Melbourne, "Dumb Ways to Die"** — McCann Melbourne, 2012
- *Problem:* Rail safety messages were ignored.
- *Leap:* A catchy song with cute characters dying in silly ways, ending at the trains.
- *Lenses:* Cultural artifact, Showmanship.
**Volvo Trucks, "The Epic Split"** — Forsman & Bodenfors, 2013
- *Leap:* Jean-Claude Van Damme doing the splits between two reversing trucks, demonstrating dynamic steering precision.
- *Why it worked:* A B2B demonstration turned into spectacle.
- *Lenses:* Demonstration, Torture test, Showmanship.
**Always, "#LikeAGirl"** — Leo Burnett, 2014
- *Leap:* Asking people to "run like a girl," then asking young girls the same.
- *Lenses:* Challenge a belief.
**Spotify Wrapped** — from 2016
- *Leap:* Each user's year in listening, made shareable.
- *Why it worked:* Users advertise the brand while talking about themselves.
- *Lenses:* Reflect them back, Format serial.
**State Street, "Fearless Girl"** — McCann New York, 2017
- *Leap:* A bronze girl facing Wall Street's Charging Bull, promoting gender diversity on boards.
- *Lenses:* Cultural artifact, Media as message.
**KFC, "FCK"** — Mother London, 2018
- *Problem:* UK restaurants closed by a chicken shortage.
- *Leap:* An empty bucket with the letters rearranged, in a full-page apology.
- *Lenses:* Honest apology.
**Burger King, "Whopper Detour"** — FCB New York, 2018
- *Leap:* Whoppers for one cent, ordered in the app within 600 feet of a McDonald's.
- *Lenses:* Judo, Media as message.
**Burger King, "Moldy Whopper"** — 2020
- *Leap:* A time-lapse of a Whopper rotting, to prove the removal of artificial preservatives.
- *Lenses:* Costly signal, Demonstration, The opposite.
**Heinz, "Draw Ketchup"** — Rethink, 2021
- *Leap:* People around the world asked to draw ketchup; nearly all drew a Heinz bottle.
- *Lenses:* Let people make it, Hero the product.
references/executions.md
# Executions
How to write the pieces once the idea exists. The idea decides what to say; this file covers how each medium says it.
## Headlines
The headline does most of the selling (Ogilvy: five times as many people read it as the body). Write at least 40 for any headline that matters, and expect the best to come late.
- **Specific beats general.** A number, a name, a detail ("the loudest noise… comes from the electric clock") beats an adjective.
- **Promise or provoke.** A headline either offers a benefit the reader wants or opens a question they need closed.
- **Pair it with the visual.** In Bernbach's teams, word and picture make one idea; the headline says what the picture can't, and the reverse. A headline that describes its own picture is wasted.
- **Read it aloud.** Rhythm, plain words, and conversational syntax.
Headline types worth trying, one or more each:
| Type | Shape |
|------|-------|
| News | "Introducing…", "At last…", what is new and why it matters |
| Fact | The buried fact, verbatim |
| Question | One the reader can't answer without reading on |
| How / why | "How a…", "Why…" with a specific outcome |
| Testimonial | A real or archetypal voice, in quotes |
| Command | An imperative that tells the reader to do or think something |
| Contrast | Two halves that collide ("Think small." against a culture of big) |
| Admission | The flaw, said plainly |
| Twist | A familiar phrase with one word changed |
| Understatement | Saying less than the claim deserves, so the reader supplies the rest |
## Body copy
- Open with the most interesting sentence you have; the reader decides in one line whether to go on.
- One idea per paragraph, facts over adjectives, short sentences mixed with long ones.
- Write to one person, in the second person, the way you would talk to them across a table.
- Answer the objections the reader is forming.
- End on the action you want and the reason to take it now.
- Long copy works when every sentence earns the next; short copy works when the idea is already complete in the headline and visual.
## Taglines
A tagline compresses the proposition into words people can repeat. Strong ones do one of these:
- **State the proposition** — "We try harder."
- **Command** — "Just do it." "Think different."
- **Ask** — "Got milk?"
- **Hold a truth** — "You're not you when you're hungry."
- **Promise a feeling** — "Good things come to those who wait."
Test: would someone say it in conversation, with or without the brand name? Does it still make sense on the side of a truck, on its own?
## Print and outdoor
- One idea, one image, as few words as possible. Outdoor gets about three seconds.
- Leave the empty space that makes the one thing seen (Think Small used most of the page for white space).
- For a serial format (Absolut, *The Economist*), define the template's fixed parts and write at least five fills to prove it has legs.
- Consider the location as part of the ad: what does it mean to put this here?
## Film
Describe the hero film as a story in three to six sentences: the opening image, the turn, the ending, and where the brand enters. Name the length and channel. For a full shot-by-shot script, hand the concept to the `video-script` skill.
## Promotions and stunts
A promotion is an idea with mechanics. Write it as a sequence:
1. **Hook** — what the audience first sees or hears, and where.
2. **Ask** — what they have to do. The smaller the ask, the bigger the participation.
3. **Reward** — what they get, and why it is worth it to them, not just to the brand.
4. **Story** — what they tell other people afterward, and the screenshot, photo, or line they share.
5. **Proof** — how the brand's proposition is demonstrated by the act of taking part.
6. **Rules and risk** — limits, cost exposure, legal needs (sweepstakes law varies by region), how it could be gamed or mocked.
Mechanics to choose from, each strongest when the mechanic itself proves the proposition:
| Mechanic | Use when |
|----------|----------|
| Sampling or free trial | The product wins once tried (Hopkins) |
| Challenge or head-to-head test | The product beats a rival in a fair comparison (Pepsi Challenge) |
| Personalization | Names, data, or creations make the product personal (Share a Coke, Wrapped) |
| Trade or sacrifice | A playful cost that reveals value (Whopper Sacrifice) |
| Location or geofence | Place makes the joke or the point (Whopper Detour) |
| Limited edition or scarcity | Rarity creates urgency and collectors |
| Collect and complete | Repeat purchase over time (game pieces, stamps) |
| User creation | The audience makes the content (Draw Ketchup) |
| Public demonstration | A live act proves the claim (Epic Split, Will It Blend?) |
| Costly gesture | Giving something up proves sincerity (Don't Buy This Jacket) |
## Social and earned
Check the idea against STEPPS (Berger): does sharing it make the sharer look good, does something in daily life trigger it, does it provoke high-arousal emotion, is participation visible, is there practical value, does the brand travel inside a story? An idea that fails all six depends on paid media to be seen.
Write the shareable artifact explicitly: the post, the screenshot, the sound, the format others can copy.
references/lenses.md
# Lenses
A lens is a generative move. Point it at the fact sheet and an angle, answer its prompt, and write each answer as a one-line idea. Run every lens in step 4; a lens that yields nothing for this brief has still been tried. Each lens names its source in the canon and a campaign that used it.
## Product lenses
| Lens | Prompt | Source | Used by |
|------|--------|--------|---------|
| **The buried fact** | Which fact on the sheet would surprise a customer? Make it the headline. | Ogilvy, Hopkins | Rolls-Royce electric clock |
| **Preemptive claim** | What does the whole category do that nobody says? Say it first. | Hopkins | Schlitz steam-cleaned bottles |
| **Inherent drama** | Where is the romance, tension, or wonder inside how it is made or used? | Burnett | Green Giant, "Harvested in the moonlight" |
| **Demonstration** | How could we prove the claim in one image or act, live, with no words? | Reeves, Hopkins | Volvo Trucks "Epic Split"; Blendtec "Will It Blend?" |
| **Torture test** | What extreme would the product survive that rivals would not? | Reeves | Volvo Trucks "Epic Split" |
| **The USP in seven words** | What single benefit only we can claim, put so plainly a child could repeat it? | Reeves | M&M's "Melts in your mouth, not in your hand" |
| **Flaw as virtue** | What is the product's weakness? Why is it secretly the point? | Bernbach | VW "Think Small"; Guinness "Good things come to those who wait" |
| **Hero the product** | Could the product itself, or its shape, be the whole ad, endlessly varied? | TBWA | Absolut bottle series |
| **Change the product** | What could we change in the product, pack, or experience so the change is the ad? | Wells Lawrence, Schmetterer | Braniff painted planes; Share a Coke |
## Audience lenses
| Lens | Prompt | Source | Used by |
|------|--------|--------|---------|
| **Deprivation** | What happens when they don't have it? Show the absence. | Goodby Silverstein | "Got Milk?" |
| **Unsaid truth** | What do they think but never say out loud? Say it for them. | Sullivan, Trott | Snickers "You're not you when you're hungry" |
| **The real buyer** | Who actually makes the purchase decision, and what do they want? | Wieden+Kennedy | Old Spice "The Man Your Man Could Smell Like" |
| **Customer as hero** | Make the audience the protagonist and the brand the enabler. | Nike | "Just Do It" |
| **Identity** | What does using this say about the user? Give them a badge or a tribe. | Apple, Berger | "Think Different"; "Get a Mac" |
| **Reflect them back** | Show people their own data, words, or behavior in a way they want to share. | Berger (social currency) | Spotify Wrapped; Share a Coke |
| **Challenge a belief** | Which belief the audience holds about itself is quietly harmful? Overturn it. | Dove, Always | Dove "Real Beauty Sketches"; Always "#LikeAGirl" |
## Competitive and category lenses
| Lens | Prompt | Source | Used by |
|------|--------|--------|---------|
| **Break the wallpaper** | List the category's conventions. Do the opposite of each one. | Bernbach, Godin | VW against 1950s Detroit; Dove against beauty advertising |
| **The enemy** | Who or what do we stand against: a rival, a habit, a convention, an idea? | Ries & Trout | Apple "1984"; 7Up "the Uncola" |
| **Number two** | If we are not the leader, how is that our advantage? | Ries & Trout, Bernbach | Avis "We Try Harder" |
| **Own a word** | Which one word could we own in the customer's mind? | Ries & Trout | Volvo, *safety* |
| **New category** | Can we invent a category we are first in? | Ries & Trout | 7Up "the Uncola" |
| **Judo** | How could a rival's size, ad, or presence become our weapon? | Trott | Burger King "Whopper Detour" |
| **Blind test** | Where would a fair head-to-head comparison favor us? Stage it publicly. | Hopkins (testing) | Pepsi Challenge |
## Reframing and behavioral lenses
| Lens | Prompt | Source | Used by |
|------|--------|--------|---------|
| **Upstream** | What is the problem behind the problem? Solve that one. | Trott | Domino's "Our pizza sucks" turnaround |
| **Perception, not reality** | What if we changed how it feels rather than what it is? | Sutherland | Eurostar champagne thought experiment |
| **The opposite** | What is the opposite of the obvious answer, and could it also be right? | Sutherland | Patagonia "Don't Buy This Jacket" |
| **Costly signal** | What act would cost us enough that people believe us? | Sutherland | Burger King "Moldy Whopper"; Patagonia's Black Friday ad |
| **Reframe the price** | Change the frame: per day, per use, against what it replaces, with a decoy. | Ariely, Kahneman | *The Economist* subscription decoy |
| **Loss frame** | What do they lose by not acting? People weigh losses roughly twice as heavily as gains. | Kahneman | "Got Milk?" |
| **The free thing** | What can we give away that costs us little and changes behavior? | Ariely, Hopkins (sampling) | Hotmail's footer; product sampling |
| **Persuasion principle as idea** | Build the whole idea around one of Cialdini's principles: scarcity, social proof, reciprocity, commitment, authority, liking. | Cialdini | Burger King "Whopper Sacrifice" (cost of friendship) |
| **Honest apology** | Where have we failed? Own it, with wit. | Bernbach, Trott | KFC "FCK" |
## Form and fame lenses
| Lens | Prompt | Source | Used by |
|------|--------|--------|---------|
| **Showmanship** | What spectacle would draw a crowd, a story people seek out rather than skip? | Feldwick | BMW Films "The Hire"; Cadbury Smash Martians |
| **Character** | What recurring character could personify the brand for years? | Burnett, Feldwick | Dos Equis "Most Interesting Man in the World" |
| **Exaggeration** | Push the benefit to absurd, literal extremes. | Pricken | Old Spice; Snickers |
| **Metaphor and analogy** | What does the product resemble in another world? Swap it in. | Pricken | Apple "1984" (Orwell's Big Brother) |
| **Visual pun / combination** | Merge the product with an unexpected object to form one image. | Pricken, Lois | Absolut city executions |
| **Cultural artifact** | Could the work become a song, a game, a statue, a meme, a ritual? | Feldwick, Berger | Metro Trains "Dumb Ways to Die"; "Fearless Girl" |
| **Let people make it** | Hand the idea to the audience and let them produce it. | Berger | Heinz "Draw Ketchup" |
| **One shot only** | What would we do if we could run it once, on the biggest stage? | Chiat/Day | Apple "1984," aired nationally once |
| **Media as message** | Could where or when it runs be the idea itself? | Schmetterer | Burger King "Whopper Detour" (geofence); "Fearless Girl" (location) |
| **Format serial** | A fixed template with endless fills, so each new execution is an event. | AMV BBDO | *The Economist* red posters; Absolut |
## Forced combination
After the lenses, take three random pairs from the fact sheet (a product fact with an audience truth, a cultural current with a category convention, a fact with a lens it has not met) and write one idea per pair. Young's whole method lives in this step: the combinations nobody thought to make.
SKILL.md
---
name: big-idea
description: "Generate creative concepts for ads, campaigns, promotions, stunts, taglines, headlines, and copy angles, worked the way the advertising canon works (Young, Bernbach, Ogilvy, Reeves, Trott, Sutherland, Feldwick) and tested against its landmark campaigns. Use when the user wants an ad or campaign idea, a promotion or launch stunt, a tagline or headline, or a fresh angle on a product, brand, or message."
---
# Big Idea
The **big idea** is Ogilvy's term for the one thought that carries a campaign for years: Think Small, We Try Harder, Got Milk?, Just Do It. This skill finds big ideas by method. The first competent idea is the category average, the one every rival agency also brings. The method is built to get past it.
The method comes from James Webb Young: an idea is a **new combination of old elements**, and the skill of combining is the skill of seeing relationships between facts. So the work is raw material in, many combinations out, then ruthless judgment. Most weak ad ideas fail at the first stage, from too little raw material, rather than at the combining.
## Vocabulary
These words are used precisely throughout the skill and its references.
| Word | Meaning |
|------|---------|
| **Raw material** | Specific facts about the product, truths about the audience, the category's conventions, and the culture around them |
| **Insight** | A truth the audience recognizes the moment they hear it, which nobody in the category has said |
| **Proposition** | The single thing the audience should believe or feel afterward. One thought, single-minded |
| **Idea** | The surprising, ownable form that dramatizes the proposition. Fits in one sentence and generates many executions |
| **Execution** | One concrete piece: a print ad, a film, a stunt, a promo mechanic, a headline |
| **Lens** | A generative move that turns raw material into ideas, drawn from the canon ([Lenses](references/lenses.md)) |
| **Ancestor** | A landmark campaign that solved a similar problem with a similar move ([Cases](references/cases.md)) |
| **Wallpaper** | What every brand in the category says and shows. The idea breaks it |
## Pick the path
| Request | Path |
|---------|------|
| Campaign, ad concept, brand platform | Full workflow, three concepts |
| Promotion, stunt, launch, activation | Full workflow; executions are mechanics (who does what, what they get, why they tell people) |
| Tagline, headline, slogan, subject line, name | Steps 1–2 lightly, step 4 with the copy lenses, 40+ lines written, best 8–12 delivered grouped by angle |
| Copy for an existing idea | Read [Executions](references/executions.md) and write |
| Non-ad writing that needs an angle (launch post, talk title, pitch) | Same method; the proposition is what the reader should take away |
## Workflow
### 1. Brief
Extract the product, audience, business problem, channel and budget signals, tone, and mandatories. Then restate the problem in one sentence that begins *"The problem is that people…"*. The stated brief often hides the real problem; Dave Trott's predatory thinking starts by reframing it, and Rory Sutherland asks whether it is a problem of perception rather than of product.
Ask questions only when a missing answer changes what kind of idea is needed (for example, whether the goal is trial or loyalty). Otherwise state the assumption and continue.
### 2. Raw material
This is Young's first step, and the one most often skipped. Build a **fact sheet**:
- **Product: at least 12 specific facts.** How it is made, what is in it, numbers, origin, the founder's obsessions, the odd details, what it does that nobody mentions. Claude Hopkins sold Schlitz on steam-cleaned bottles and artesian wells, a process every brewer used and none had told the public about. Ogilvy found the Rolls-Royce clock in an engineering report. When the product is real, search the web for facts and cite what you find.
- **Audience: at least 5 truths.** Behaviors, small rituals, tensions, the thing they would never say out loud, the moment the product matters most.
- **Wallpaper: the category's conventions.** The claims, images, tone, and colors every competitor uses.
- **Culture: 2–3 live currents** the brand could join or push against.
Done when each product fact is specific enough that a competitor could not claim it word for word, or is marked as category-generic (generic facts can still win, as preemptive claims).
### 3. Strategy
Write three distinct strategic angles, each as an insight plus a proposition. Make them differ in strategy, not wording: one from a product fact (USP or inherent drama), one from an audience tension, and one from positioning against the category or a rival (an enemy, a flaw turned into a virtue, a word to own). The canon behind each move is in [Canon](references/canon.md). Carry the two or three strongest forward.
### 4. Generate wide
Run every lens in [Lenses](references/lenses.md) against the fact sheet and the angles. Write each idea as one line, fast and without judging. Aim for 40 or more raw ideas; quantity is the method here. Then **force combinations**: pair an unrelated product fact with a lens, or an audience truth with a case's move, and write what comes out.
Mark the first five or so ideas you wrote as the **baseline**: the obvious answers. They stay in the pile only if they survive step 6 against everything else.
### 5. The rival's pitch
Young's step three is incubation, setting the problem aside so the mind can recombine it. The agent version: write the three concepts a competent rival agency would bring to this brief. Strike your own ideas that resemble them. What remains is unexpected by definition.
### 6. Select
Score the survivors against the tests below and keep three concepts that answer different strategic angles.
| Test | Passes when |
|------|-------------|
| **One sentence** | The idea fits in one sentence a stranger would repeat |
| **Ownable** | Swap in a competitor's name and it breaks |
| **Gasp** | Ogilvy's questions: did it make me gasp, and do I wish I had thought of it? |
| **On strategy** | It dramatizes the proposition; the audience walks away believing it |
| **Branded** | The product is the hero of the idea and not a sign-off, so nobody remembers the ad and forgets the brand |
| **Legs** | It yields three or more executions across different media; could it run for years? |
| **Fame** | People would retell it unprompted (Feldwick's showmanship, Berger's social currency) |
| **Truth** | The product lives up to it. Bernbach: a great campaign makes a bad product fail faster |
### 7. Develop
Build each concept to the output format below. Write the hero execution in enough detail to see or hear it: the actual headline and visual, the film's story in a few sentences, the stunt's mechanics from first touch to the moment someone shares it. Write the copy to [Executions](references/executions.md). Name an ancestor from [Cases](references/cases.md) for each concept and say what this idea takes from it and where it departs.
Done when each concept has an insight, a proposition, a one-sentence idea, a hero execution, three or more extensions, and an honest risk, and the three concepts would lead to three different campaigns.
## Output
```markdown
# [Brand / product]: concepts
## The problem
[One sentence: "The problem is that people…"] plus any assumptions.
## Raw material
[The fact sheet, condensed to the facts the concepts use, plus the category wallpaper.]
## Concept 1: [Name]
**The idea:** [One sentence.]
**Insight:** [...]
**Proposition:** [...]
**Ancestor:** [Campaign]: what this takes from it, and where it departs.
**Hero execution:** [Headline and visual / film story / stunt mechanics, written out.]
**Extensions:** [3+ executions across media: print or OOH, film, social, promotion, retail, PR.]
**Lines:** [2–4 tagline or headline options.]
**Why it works:** [The principle at work, in a sentence or two.]
**Risk:** [What could go wrong, and what would have to be true for it to work.]
## Concept 2 … Concept 3
## Recommendation
[The one you would take into the room, and why.]
## Also ran
[Strong ideas cut in selection, one line each.]
```
For tagline and headline requests, replace the concepts with lines grouped by angle, each group headed by its insight, with your recommendation first.
## Related skills
- `video-script` turns a chosen concept's film into a shootable script.
- `creative-director` builds the visual identity around a brand.
- `clean-writing` tightens long copy.
## Reference documents
| Reference | Use during |
|-----------|-----------|
| [Canon](references/canon.md) | Steps 1, 3, and 6: what each master taught, as a principle you can apply and a question to ask |
| [Lenses](references/lenses.md) | Step 4: the generative moves, each with its prompt and a campaign that used it |
| [Cases](references/cases.md) | Steps 4 and 7: landmark campaigns broken into problem, insight, leap, and why it worked |
| [Executions](references/executions.md) | Step 7: headlines, body copy, taglines, print and outdoor, film, promotions and stunts, social |