The Dieter Rams
Framework
Ten Principles of Good Design
Dieter Rams believed that form must answer to constraints: material, site, brief, budget. Dieter Rams's design philosophy captures the specific questions they asked before drawing a single line, captured in this framework as mental models, decision heuristics, and the signature questions they would ask.
The ten principles of good design framework distils Dieter Rams's documented approach into a .md skill file you can load into Claude, ChatGPT, or any LLM in seconds.
Where most AI personas generate generic output, this framework is grounded in real documented work: interviews, writing, published frameworks, and the specific decisions Dieter Rams made when it mattered. Use it for decision-making, writing, strategy, or any situation where you want your AI to think with Dieter Rams's distinctive patterns rather than a default model voice.
A glimpse of Dieter Rams's thinking.
Good design is as little design as possible—it concentrates on the essential aspects and eliminates the superfluous. Design must be honest about a product's function and never manipulate users through false promises. The best products become invisible tools that enhance human capability without creating dependency or confusion.
- 01
- 02
- 03
- 04
- 05
Five specific models, each named and explained with concrete examples, unlocked with purchase.
Does this design make the user more capable or just more impressed?
4 more questions in Dieter Rams's voice are unlocked with purchase.
Full list of anti-patterns unlocked with purchase.
The full framework adds: detailed explanations of all five mental models with real-world examples, the decision heuristics Dieter Rams actually used, remaining signature questions, the complete list of anti-patterns, a copy-paste activation prompt, and a worked example.
Unlocked the moment you purchase. ~2,000 words total. Delivered as a Claude Skill and plain .md within 60 seconds of checkout.
- ✦Core philosophy: 2–3 sentences grounded in Dieter Rams's documented worldview
- ✦Five signature mental models: each named, with concrete examples from their work
- ✦Decision heuristics: the concrete rules they actually used
- ✦Signature questions: five questions that sound like Dieter Rams, not a generic MBA
- ✦What they would NOT do: the anti-patterns this framework rejects
- ✦Copy-paste activation prompt: drop straight into Claude or ChatGPT
- ✦Worked example: the framework applied to a realistic scenario
- →dieter-rams.zip: a native Claude Skill. Upload to Settings → Skills in Claude, or unzip to
~/.claude/skills/ - →dieter-rams-framework.md: plain markdown. Works in ChatGPT Custom GPTs, Gemini, Claude Projects, agent system prompts, anywhere
What it does with a real question.
A founder is deciding whether to take a large but difficult client.
Take the client only if you can still describe your company in one sentence afterward. A large, difficult client behaves like an ornament on a product: it looks impressive, and the cost shows up later in every part of the business that has to bend around it. The revenue is real. So is the way a demanding account quietly rewrites your roadmap, your hiring, and what your team believes the company is for.
Apply an honesty audit to the deal. Strip away the logo and the contract size, then ask whether this client wants the thing you already make or something you would have to become to satisfy them. If their requests are harder versions of your core function, say yes, because they will sharpen you. If they require features, processes, or promises that exist only for them, you are building a custom object for one owner, and the rest of your customers will pay for it in neglect.
Difficulty itself is not the disqualifier. Difficulty that arrives through unclear scope and shifting demands is. Difficulty that arrives through high standards is a gift.
Your next move is concrete: write down, before the next call, the three things this client will ask for that you would never build for anyone else. Put them to the client plainly and watch the response. If they accept boundaries, proceed with a fixed scope and a clear exit clause. If they treat boundaries as negotiable, you have your answer, and it cost you a conversation instead of a year.
The full framework carries five models, decision heuristics, signature questions and a worked example.
Written by claude-sonnet-5-5 with this framework loaded, 2026-10-11. Checked automatically for length and for copied framework text.
Save up to 40% with a bundle
Works as a Claude Skill (.zip) and as a plain .md for ChatGPT, Gemini & every LLM
Delivered to your email within 60 seconds · Secured by Stripe
Price includes UK VAT where applicable
Inspired by the documented thinking of Dieter Rams. A mental-model toolkit, not a literal representation. Delivered as a .md file compatible with Claude, ChatGPT, Gemini, and any LLM.