The James Baldwin
Framework
Moral Witness & American Truth-Telling
James Baldwin shaped how their era thought about itself through distinctive voice and observational rigour. James Baldwin's intellectual method, captured in this framework as mental models, decision heuristics, and the signature questions they would ask.
The moral witness & american truth-telling framework distils James Baldwin'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 James Baldwin made when it mattered. Use it for decision-making, writing, strategy, or any situation where you want your AI to think with James Baldwin's distinctive patterns rather than a default model voice.
A glimpse of James Baldwin's thinking.
Real love requires the courage to see people and systems as they actually are, not as we wish them to be. The most dangerous lies are the ones we tell ourselves about our own goodness. Truth-telling is an act of liberation for both the witness and the witnessed.
- 01
- 02
- 03
- 04
- 05
Five specific models, each named and explained with concrete examples, unlocked with purchase.
What is this person/system afraid I will see?
4 more questions in James Baldwin'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 James Baldwin 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 James Baldwin'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 James Baldwin, 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
- →james-baldwin.zip: a native Claude Skill. Upload to Settings → Skills in Claude, or unzip to
~/.claude/skills/ - →james-baldwin-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.
Look at what "difficult" is doing in that sentence. Founders use the word as a fog. Difficult how? A client who pays late, scopes badly and shouts on calls is difficult in a way you can price. A client who needs your people to be smaller than they are, to flatter, to look away, is difficult in a way that costs you something no invoice recovers. You have to say which one this is before you do anything else.
Here is my position: take the client only if you can name the price of the ticket in plain words, to your team, before you sign. Every large contract has a hidden cost, and it gets paid by someone. Usually it is the people closest to the work, quietly, in exhaustion and in the small compromises they stop mentioning. If you cannot say out loud who will pay and what they will pay, you are not weighing a risk, you are avoiding a fact.
The size of the check is the loudest thing in the room, and that is exactly why I distrust it. Money this big makes a founder generous with his own self-image. Be honest about whether you want this client or want to be the kind of company that survives without needing them.
Next move: before the contract is signed, write one page listing what this client will demand, who on your team absorbs each demand, and what you will refuse. Then show that page to those people. If you flinch at showing it, you have 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 James Baldwin. A mental-model toolkit, not a literal representation. Delivered as a .md file compatible with Claude, ChatGPT, Gemini, and any LLM.