The AI SCAMPER Innovation Coach skill for Claude

The problem the skill solves shows up in almost every ideas session. Someone says: we need something new. Five suggestions come in, three of them everyone already knew, the fourth is too big to do and the fifth is really a complaint. After an hour there is a list with no owner and no first step. SCAMPER tackles exactly that by turning the problem around: not searching for inspiration, but systematically working through seven fixed angles on something you already have. The question changes from where do we find a good idea to what happens if we replace this part, and everyone can answer that second question.

It is written for entrepreneurs stuck with their product, marketers who need new campaigns and teams who want to run an ideation session. That is stated in the file's frontmatter, so that is also exactly when Claude picks it up. It is part of the skill library NL that we make freely available through our AI and automation service: 100 skills, with no account and no sales email afterwards.

One honest warning up front: SCAMPER renews something that already exists. The method needs an object, a product, service, process or idea that you can describe in words. For the question of which problem you should even be solving in the first place, this is not the right lens, and the skill itself does not pretend otherwise.

Free thinking runs along familiar paths. Ask a team for ideas for an existing product and you get variations on what already exists. That is not a lack of creativity but a consequence of how memory works: the first association blocks the second. Seven compulsory lenses break that pattern, because the sixth lens asks a question nobody would ask on their own.

The session stops at the keyword. Most flipcharts carry loose terms: subscription, community, new audience. That is not an idea, that is a category. The file is strict about this: every proposal must be concrete and actionable, with a short explanation for each idea of why it works or which problem it solves. The difference between those two forms is the difference between a session and a decision.

No choice gets made. A list of thirty ideas is a list of thirty ways to do nothing. That is why choosing is built into the skill as a separate step, with three criteria fixed in advance, so the choice does not go to the idea with the loudest voice behind it.

Nobody tests the assumption. Every idea rests on something that has to be true before it works. The example in the SKILL.md makes that explicit: for the Sunday brunch idea, the assumption is that Sunday foot traffic in the area is high enough. Without that sentence it is a plan, with that sentence it is a test.

In diff form, with lines from the example in the skill: what ends up on the board in an ordinary session, and what the skill turns it into.

After that comes the historical grounding, in two sentences. SCAMPER was developed by Bob Eberle in 1971, building on the brainstorming work of Alex Osborn, the inventor of brainstorming. The letters stand for seven specific lenses you run an idea through to find variations and improvements that would otherwise stay invisible. Each letter then gets its own block with a short explanation and a central question, exactly as shown in FIG.02 above.

The execution part consists of four steps. Step 1, understand the object. If it is not clear exactly what is being analysed, the skill first asks: what is the core product or core service, who is the current target audience, what is the current price or cost model, and what is the biggest pain point or limitation right now. There is a limit built straight into this that you rarely see in prompts: ask a maximum of three questions at once and then move on. So you get no questionnaire, at most a short round of questions.

Step 2, apply all seven lenses. Each letter is worked through systematically with three to five concrete, actionable ideas. Even the format is fixed: per lens the letter with its name and the Dutch translation, then the central question tailored to your object, then numbered ideas where each idea is followed by a short explanation of why it works or which problem it solves. No vague statements, only concrete proposals: that is what it literally says.

Step 3, select the top three. After the seven lenses, the skill picks the three strongest ideas from all the variants, on three criteria: high impact on the user's main KPI such as revenue, retention or margin, realistic feasibility within 90 days, and differentiation from competitors. For each chosen idea it delivers four things: which SCAMPER lens it is, the idea in one sentence, the first three action steps to test it, and which assumption needs to be validated before you move on.

Step 4, suggest a combination. According to the file, the strongest innovation often comes from stacking two SCAMPER ideas, so it closes with an example where two letters come together. In the pizzeria example those are Eliminate and Substitute, combined into a subscription with three options that change weekly.

Finally there is a Tone and rules block with six points, four of which explicitly forbid something. Clear language and no jargon. No emoji bullets, just normal bullet points. Concrete and businesslike, not woolly. Show that the object is genuinely understood by echoing specific words from your input. Challenge the assumption and do not flatter. And: if an idea is stupid or risky, say so. That last point is the most interesting one, because it stops the skill from being a yes-man.

Eberle, 1971. SCAMPER: Games for Imagination Development, published by D.O.K. Publishers. This is the source of the acronym itself. Bob Eberle devised it as a tool for developing imagination, originally in education, and that explains its shape: seven questions simple enough to ask anyone.

Eberle, 1996. Scamper On: More Creative Games and Activities for Imagination Development, from Prufrock Press. The follow-up title, and the reason the method appears twice under the same author in the reference list: it is not a one-off invention but a fully developed practice.

Osborn, 1953. Applied Imagination: Principles and Procedures of Creative Problem Solving, from Charles Scribner's Sons. This is explicitly named as the original brainstorming technique that SCAMPER builds on. Osborn is the inventor of brainstorming, and his core rule, generate first and only judge afterwards, shows up in the split between step 2 and step 3 of the skill.

Michalko, 2006. Thinkertoys: A Handbook of Creative-Thinking Techniques, from Ten Speed Press. The file refers specifically to the chapter on applying SCAMPER. This is the practical side: how you use the lenses in a real session without it turning into a fill-in-the-blanks exercise.

Even without installing the skill you can get further with these principles: take something you already have, work through the seven questions without skipping one, force yourself to write down at least three concrete proposals per lens, and only choose afterwards. If you want to approach the creative phase before that more broadly, the Design Thinking Coach skill connects directly to it, and for separating dreamer, realist and critic there is the Disney Method Coach skill.

After that, using it is simple: describe in a few sentences what you want to renew and ask for a SCAMPER analysis. The more concrete your object, the more useful the ideas. If you are new to this kind of file, first read what Claude skills are NL and then the step by step explanation of installing Claude skills NL. If you want to adapt the skill to your own sector or your own KPI, writing a SKILL.md NL explains how to do that without wrecking the structure. For the broader context on working with AI there is the knowledge base.

There are also situations where you are better off leaving it aside. The first is an empty starting point: if you do not yet have a product or service, there is nothing to substitute, combine or eliminate. In that case start with the question which problem you are solving, for example with the Jobs to be Done Analyst skill. The second is a choice between alternatives that are already on the table: SCAMPER generates variants, but it does not weigh existing options against each other. There the Six Thinking Hats Analyst skill is more logical, since it does exactly that from six thinking modes.

The third limit is validation. It comes up with variants and states, for each chosen idea, which assumption has to be true first, but it does not check that assumption itself. It does not know your figures, your market or your capacity. What comes out is material to test with, not proof that something works. Anyone who ignores that difference mistakes a well structured list for a business plan.

One more honest limit follows from the frontmatter itself: the file names design thinking as one of the triggers. That means the skill often activates on questions that are actually broader than SCAMPER. If you get a SCAMPER analysis back when you were really looking for user research, that is not a fault of the skill but of the question. In that case, state explicitly which framework you want.

A better product variant only helps if someone comes across it. If the flow of new customers is lagging, the real work sits before the ideas round: being found by the people looking for you, in Google and in AI answers. The free SEO scan shows in a few seconds where your site stands. And if you want to talk further about what AI can do for your business beyond that, from separate skills to full automation, we simply do that in a conversation.