The Katherine Johnson
Framework
Mathematical Precision & Quiet Authority
Katherine Johnson advanced human understanding by treating curiosity as a daily discipline. Katherine Johnson's method of inquiry, captured in this framework as mental models, decision heuristics, and the signature questions they would ask.
The mathematical precision & quiet authority framework distils Katherine Johnson'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 Katherine Johnson made when it mattered. Use it for decision-making, writing, strategy, or any situation where you want your AI to think with Katherine Johnson's distinctive patterns rather than a default model voice.
A glimpse of Katherine Johnson's thinking.
Mathematics doesn't lie, and neither should you. When human lives or critical outcomes depend on your calculations, personal comfort becomes irrelevant. Authority isn't claimed through titles or volume—it's earned through consistent precision and the quiet confidence that comes from knowing your numbers are right.
- 01
- 02
- 03
- 04
- 05
Five specific models, each named and explained with concrete examples, unlocked with purchase.
"What happens if this calculation is wrong?"
4 more questions in Katherine Johnson'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 Katherine Johnson 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 Katherine Johnson'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 Katherine Johnson, 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
- →katherine-johnson.zip: a native Claude Skill. Upload to Settings → Skills in Claude, or unzip to
~/.claude/skills/ - →katherine-johnson-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.
Don't decide on the revenue; decide on the arithmetic. A large, difficult client feels like one question, but it's really a set of numbers you can compute before you sign anything. Most founders skip that step because the contract value is loud and the costs are quiet.
Start by pricing the difficulty. Estimate the hours this client will actually consume once you count revisions, escalation calls, scope creep, and the senior attention that gets pulled away from everyone else. Then put a dollar figure on the work you will turn down or do worse because of it. Subtract both from the headline number. Many difficult clients look attractive at the top line and turn marginal, or negative, at the bottom.
Next, ask what failure costs. If this client is more than a quarter of your revenue, losing them or fighting with them puts payroll at risk, and that margin of error is far too thin for a company your size. If you can absorb the loss, the downside is bounded and the case improves considerably.
My position: take them only if the adjusted margin still clears your normal threshold and the contract limits the damage, meaning a defined scope, a paid change-order process, and a short exit clause.
Your next move is concrete. This week, build a one-page model with three scenarios, best, expected, and worst, and have someone you trust check the assumptions independently before you answer the client.
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 Katherine Johnson. A mental-model toolkit, not a literal representation. Delivered as a .md file compatible with Claude, ChatGPT, Gemini, and any LLM.