The Hannibal Barca
Framework
Audacity & Strategic Surprise
Hannibal Barca shaped outcomes at scale through decisions made under profound uncertainty. Hannibal Barca's leadership patterns, captured in this framework as mental models, decision heuristics, and the signature questions they would ask.
The audacity & strategic surprise framework distils Hannibal Barca'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 Hannibal Barca made when it mattered. Use it for decision-making, writing, strategy, or any situation where you want your AI to think with Hannibal Barca's distinctive patterns rather than a default model voice.
A glimpse of Hannibal Barca's thinking.
When facing overwhelming advantages held by opponents, victory comes through doing what they cannot imagine, not what they expect. The enemy's greatest strength becomes their greatest vulnerability when attacked from an impossible angle. Audacity succeeds where caution fails because it renders the opponent's preparations useless.
- 01
- 02
- 03
- 04
- 05
Five specific models, each named and explained with concrete examples, unlocked with purchase.
"What would my enemy consider impossible for me to attempt?"
4 more questions in Hannibal Barca'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 Hannibal Barca 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 Hannibal Barca'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 Hannibal Barca, 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
- →hannibal-barca.zip: a native Claude Skill. Upload to Settings → Skills in Claude, or unzip to
~/.claude/skills/ - →hannibal-barca-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 on terms that make retreat impossible.
A large, difficult client is the kind of account your competitors will not touch. That is exactly why it is valuable. If it were easy, a dozen larger firms would already be circling it. The difficulty is a moat: whatever you build to serve this client well becomes capability the comfortable players never develop, and the reference you earn carries weight that ten easy wins cannot.
But audacity is not recklessness. Hannibal crossed the Alps because he had counted every ration and scouted every pass, not because he felt brave. So the question is not whether the client is hard. It is whether you can survive the hardness long enough to profit from it. A client that can consume 60 percent of your capacity, or whose single late payment can strain your payroll, is a trap, not a campaign.
Here is the position: say yes, but fix the terrain before you march. Negotiate a paid discovery phase, milestone-based payments with money up front, and a written scope with a defined change process. Difficult clients become destructive mainly when scope is fuzzy and cash flows in arrears. Cap this account at roughly a third of your revenue, and assign your strongest person to it full time.
Your next move this week: send the client a proposal that makes the paid discovery phase a condition of engagement. Their reaction will tell you whether they are worth the climb.
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 Hannibal Barca. A mental-model toolkit, not a literal representation. Delivered as a .md file compatible with Claude, ChatGPT, Gemini, and any LLM.