The Kathryn Bigelow
Framework
Tension Craft & Procedural Realism
Kathryn Bigelow produced work that defined or redefined their medium through sustained attention to craft. Kathryn Bigelow's creative approach, captured in this framework as mental models, decision heuristics, and the signature questions they would ask.
The tension craft & procedural realism framework distils Kathryn Bigelow'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 Kathryn Bigelow made when it mattered. Use it for decision-making, writing, strategy, or any situation where you want your AI to think with Kathryn Bigelow's distinctive patterns rather than a default model voice.
A glimpse of Kathryn Bigelow's thinking.
Real danger creates real stakes—audiences smell manufactured peril from miles away. The camera becomes a participant, not an observer, placing viewers inside the pressure cooker rather than watching from safety. Procedural accuracy isn't research theater; it's the foundation that makes impossible situations feel inevitable.
- 01
- 02
- 03
- 04
- 05
Five specific models, each named and explained with concrete examples, unlocked with purchase.
"How do we put the camera where no camera should be?"
4 more questions in Kathryn Bigelow'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 Kathryn Bigelow 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 Kathryn Bigelow'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 Kathryn Bigelow, 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
- →kathryn-bigelow.zip: a native Claude Skill. Upload to Settings → Skills in Claude, or unzip to
~/.claude/skills/ - →kathryn-bigelow-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, but only after you see the hard part up close. Right now you're deciding from a satellite view: the contract value, the logo, the revenue line. Everything that will actually decide whether this works sits at ground level, in the details nobody puts in a proposal. Who at the client approves invoices, and how long do they really take? How many people can redirect your team, and do they agree with each other? What happens on the third revision request at 6 p.m. on a Friday?
"Difficult" is doing too much work in your description. Difficult because the work is technically demanding, or difficult because the people are? The first kind builds a company: you get paid to develop expertise competitors can't copy. The second kind quietly consumes your best people while the revenue number looks great. Founders get into trouble when they accept a large client without knowing which one they signed.
Here is the part that matters most: a large client concentrates your risk. If they'd represent more than a third of revenue, a bad quarter on their side becomes a survival question on yours.
Next move: before you answer, spend one working session with the people who will do the work, ideally on a paid pilot or scoped first phase. Watch how the client behaves when something goes wrong. If the pilot can't be arranged, treat that refusal as your answer.
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 Kathryn Bigelow. A mental-model toolkit, not a literal representation. Delivered as a .md file compatible with Claude, ChatGPT, Gemini, and any LLM.