The Sherlock Holmes
Framework
Deduction & the Attention to What Is Absent
Sherlock Holmes represents one of the most distinctive thinking patterns in their field. Sherlock Holmes's approach, captured in this framework as mental models, decision heuristics, and the signature questions they would ask.
The deduction & the attention to what is absent framework distils Sherlock Holmes'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 Sherlock Holmes made when it mattered. Use it for decision-making, writing, strategy, or any situation where you want your AI to think with Sherlock Holmes's distinctive patterns rather than a default model voice.
A glimpse of Sherlock Holmes's thinking.
Most reasoning fails not because people process the wrong evidence but because they never notice the evidence that failed to appear. Holmes operated on the principle that a world in which a certain event occurred leaves a specific residue, and a world in which it did not leaves a different one. When those residues do not match the story being told, the story is wrong. Certainty is not the goal. The elimination of every impossible explanation until only one remains, however improbable it seems at the outset, is the goal.
- 01
- 02
- 03
- 04
- 05
Five specific models, each named and explained with concrete examples, unlocked with purchase.
"What would we expect to find here if the stated account were true, and which of those things is not present?"
4 more questions in Sherlock Holmes'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 Sherlock Holmes 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 Sherlock Holmes'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 Sherlock Holmes, 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
- →sherlock-holmes.zip: a native Claude Skill. Upload to Settings → Skills in Claude, or unzip to
~/.claude/skills/ - →sherlock-holmes-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.
Start with what is missing. A large, difficult client arrives with a story: big revenue, tough personality, worth the pain if you can stomach it. That story is vivid, which is exactly why I distrust it. The founder has told me what the client offers and what the client costs. Nobody has mentioned why this client is available. A company that size, with that much need, has presumably burned through other vendors, and the departed vendors are the quietest witnesses in the room.
So my position: do not decide on the strength of the pitch. Decide on the residue the client has left behind. How long did the previous provider last? Did the client pay late, scope-creep, or churn through account managers? Difficulty rarely announces itself in the first meeting, but it leaves marks in the client's history: a thinning roster of vendors, a procurement process that suspiciously requires heavy discounts, a contract that front-loads the client's rights.
Two ordinary explanations fit the evidence. Either this client is hard but fair, and the founder's team can grow into it, or it is a pattern of extraction that will consume the team's best hours. One observation separates them.
The next move: ask for two references from former vendors, not current ones, and ask the founder's own team how many of their weekly hours the client would claim. If the client refuses the first request, you have your answer. If the second number exceeds a third of capacity, walk away.
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 Sherlock Holmes. A mental-model toolkit, not a literal representation. Delivered as a .md file compatible with Claude, ChatGPT, Gemini, and any LLM.