The Carl Sagan
Framework
Wonder, Skepticism & Communication
Carl Sagan advanced human understanding by treating curiosity as a daily discipline. Carl Sagan's method of inquiry, captured in this framework as mental models, decision heuristics, and the signature questions they would ask.
The wonder, skepticism & communication framework distils Carl Sagan'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 Carl Sagan made when it mattered. Use it for decision-making, writing, strategy, or any situation where you want your AI to think with Carl Sagan's distinctive patterns rather than a default model voice.
A glimpse of Carl Sagan's thinking.
The universe is vast and beautiful, deserving both our deepest reverence and our most careful scrutiny. Extraordinary claims demand extraordinary evidence, yet we must never lose our sense of awe at the cosmos. Science is not just a body of knowledge but a way of thinking—one that must be shared with humanity, not hoarded by experts.
- 01
- 02
- 03
- 04
- 05
Five specific models, each named and explained with concrete examples, unlocked with purchase.
What would it mean if this were true, and what evidence would convince me?
4 more questions in Carl Sagan'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 Carl Sagan 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 Carl Sagan'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 Carl Sagan, 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
- →carl-sagan.zip: a native Claude Skill. Upload to Settings → Skills in Claude, or unzip to
~/.claude/skills/ - →carl-sagan-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.
Treat the client's promise as a claim that has to earn its evidence. A large, difficult client arrives wrapped in a story: this account will make the company, the pain is temporary, the revenue will fix the cash problem. That is an extraordinary claim, and the evidence offered so far is mostly the size of the contract and the founder's hope. Size is not proof of anything except exposure.
So take the baloney-detection approach and ask what could falsify the story. If the client is difficult in the ways you can already see, such as slow payment, shifting scope, or a history of burning vendors, then past behavior is the best data you have, and it is not encouraging. Ask the client for three former vendors to call. A client who refuses is answering the question for you.
My position: do not sign the deal as offered, but do not walk away yet either. The upside here is real, and dismissing it on instinct would be its own kind of lazy thinking. Instead, convert the opportunity into an experiment. Propose a paid pilot of four to six weeks, with defined deliverables, payment up front, and a written exit clause. Then watch what happens. Do they honor the boundaries? Do they pay on time?
Concrete next move this week: write down the three conditions under which you would say no, and share them with the client before negotiating anything else. Their reaction is your first real data point.
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 Carl Sagan. A mental-model toolkit, not a literal representation. Delivered as a .md file compatible with Claude, ChatGPT, Gemini, and any LLM.