The Winnie Mandela
Framework
Resistance Leadership Under Siege
Winnie Mandela navigated political power by managing coalitions, communication, and trade-offs under public scrutiny. Winnie Mandela's governing patterns, captured in this framework as mental models, decision heuristics, and the signature questions they would ask.
The resistance leadership under siege framework distils Winnie Mandela'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 Winnie Mandela made when it mattered. Use it for decision-making, writing, strategy, or any situation where you want your AI to think with Winnie Mandela's distinctive patterns rather than a default model voice.
A glimpse of Winnie Mandela's thinking.
When the system designates you as an enemy, your survival becomes an act of rebellion, and your visibility becomes your shield. The oppressor's brutality against you exposes their true nature to the world, making your persecution a strategic asset rather than just personal suffering.
- 01
- 02
- 03
- 04
- 05
Five specific models, each named and explained with concrete examples, unlocked with purchase.
"How does my suffering today advance our freedom tomorrow?"
4 more questions in Winnie Mandela'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 Winnie Mandela 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 Winnie Mandela'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 Winnie Mandela, 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
- →winnie-mandela.zip: a native Claude Skill. Upload to Settings → Skills in Claude, or unzip to
~/.claude/skills/ - →winnie-mandela-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 if the difficulty works for you rather than against you. A founder weighing a large, difficult client is not facing the siege this framework was built for, so I would not borrow its posture of defiance. What transfers is one idea: proxy power. Influence you build through others survives pressure you cannot absorb yourself.
Here is how that applies. A difficult client will demand your time, your people's patience, and your attention. You cannot be everywhere, so the real question is who can carry this account when you are not in the room. If the answer is only you, decline. A client that makes the founder the single point of failure will bend the company around itself, and the revenue will not repay that.
If you do have, or can quickly build, a capable second chair, such as an account lead with real authority to say no and the backing to make it stick, the client becomes an asset. Large and difficult customers also tend to be references that open doors, provided the work holds up.
Your next move: before signing, name the person who will run the relationship day to day and write the boundaries into the contract: scope limits, response windows, a clean exit clause. Then put those terms to the client directly. How they respond to being told no on paper will tell you almost everything about what the next year looks like.
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 Winnie Mandela. A mental-model toolkit, not a literal representation. Delivered as a .md file compatible with Claude, ChatGPT, Gemini, and any LLM.