The Loki
Framework
The Trickster's Lens & Productive Chaos
Loki represents one of the most distinctive thinking patterns in their field. Loki's approach, captured in this framework as mental models, decision heuristics, and the signature questions they would ask.
The the trickster's lens & productive chaos framework distils Loki'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 Loki made when it mattered. Use it for decision-making, writing, strategy, or any situation where you want your AI to think with Loki's distinctive patterns rather than a default model voice.
A glimpse of Loki's thinking.
Every system has a seam, a place where the official map and actual territory diverge, and that seam is where real leverage lives. Loki does not break rules carelessly. He studies them until he finds the one that, when pulled, unravels the whole garment on someone else's behalf. Chaos is not the goal. Chaos is the controlled solvent that dissolves the false structure so the true one becomes visible.
- 01
- 02
- 03
- 04
- 05
Five specific models, each named and explained with concrete examples, unlocked with purchase.
"Who wrote this rule, and are they still in the room?"
4 more questions in Loki'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 Loki 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 Loki'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 Loki, 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
- →loki.zip: a native Claude Skill. Upload to Settings → Skills in Claude, or unzip to
~/.claude/skills/ - →loki-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 on terms that make the difficulty visible. A large difficult client is rarely a revenue question. It is a question of who gets to set the rules once the contract is signed. Big clients win by making their demands feel like the cost of doing business, so you absorb scope creep, slow payment, and endless revisions as if they were laws of nature. They are not. They are habits the client has because nobody has priced them.
So before saying yes, run a Shapeshifter's Audit on the person you would actually report to. Their job is probably not to get the best outcome. It is to avoid blame inside their own company. That tells you what they will fight about (anything that looks like risk to them) and what they will let slide (price, if it comes wrapped in safety). Use that. Offer a structured engagement with a paid discovery phase, fixed change-order rates, and a clause making delays on their side billable. Present it as a risk-reduction package for them, not as protection for you.
If they accept, the difficulty becomes a managed cost, and the logo is worth having. If they balk at paying for their own friction, you have learned what the relationship would have been for a hundredth of the price.
Next move: this week, send a one-page proposal built around the paid discovery phase, and treat their reaction to it as the real interview.
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 Loki. A mental-model toolkit, not a literal representation. Delivered as a .md file compatible with Claude, ChatGPT, Gemini, and any LLM.