The Harriet Tubman
Framework
Underground Networks & Liberation
Harriet Tubman shaped outcomes at scale through decisions made under profound uncertainty. Harriet Tubman's leadership patterns, captured in this framework as mental models, decision heuristics, and the signature questions they would ask.
The underground networks & liberation framework distils Harriet Tubman'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 Harriet Tubman made when it mattered. Use it for decision-making, writing, strategy, or any situation where you want your AI to think with Harriet Tubman's distinctive patterns rather than a default model voice.
A glimpse of Harriet Tubman's thinking.
Authority comes from proving yourself in the field, not from titles or recognition. Real leadership means you go first into danger and never lose a person under your care. The network is everything—without trusted allies positioned at critical points, individual courage means nothing.
- 01
- 02
- 03
- 04
- 05
Five specific models, each named and explained with concrete examples, unlocked with purchase.
"Who in your network has actually proven themselves when the stakes were life and death?"
4 more questions in Harriet Tubman'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 Harriet Tubman 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 Harriet Tubman'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 Harriet Tubman, 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
- →harriet-tubman.zip: a native Claude Skill. Upload to Settings → Skills in Claude, or unzip to
~/.claude/skills/ - →harriet-tubman-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 it, but only as a tested crossing, not a leap. A large, difficult client is the kind of load that kills a young company quietly: not on day one, but in month four, when one invoice runs late, one key person burns out, and everything else you promised other customers starts slipping. The question is not whether the client is worth having. It is whether your company has already proven it can carry weight like this without losing anyone along the way.
Think about the Moses Route: never stake the whole journey on a single path. If this client would exceed a third of your revenue, or if losing them would mean missing payroll, then you have one route and no alternative, and a hostile client will find that out fast. Difficult people sense dependency and use it.
So here is my judgment: negotiate a bounded first engagement. Ninety days, a defined scope, payment terms that keep your cash safe (deposit up front, short invoice cycles), and an explicit exit clause for both sides. Put your own most capable person on it, and be on the first calls yourself. Do not send your team into territory you have not walked.
Next move this week: ask the client for a paid pilot with those terms. How they respond to a reasonable structure will tell you more than any reference call. If they refuse all guardrails, you have your answer, and it was cheap to learn.
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 Harriet Tubman. A mental-model toolkit, not a literal representation. Delivered as a .md file compatible with Claude, ChatGPT, Gemini, and any LLM.