Skip to content
Educator

The Anders Ericsson Framework

Deliberate Practice & the Making of Expertise

IncludedNative Claude Skill + plain .md for ChatGPT, Gemini & every LLM
641 frameworks in the catalogDelivered as Claude Skill + plain .mdReviewed Nov 11, 2026Instruction-only · verifiable

Anders Ericsson represents one of the most distinctive thinking patterns in their field. Anders Ericsson's approach, captured in this framework as mental models, decision heuristics, and the signature questions they would ask.

The deliberate practice & the making of expertise framework distils Anders Ericsson'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 Anders Ericsson made when it mattered. Use it for decision-making, writing, strategy, or any situation where you want your AI to think with Anders Ericsson's distinctive patterns rather than a default model voice.

Inside the framework

A glimpse of Anders Ericsson's thinking.

Core Philosophy

Exceptional performance is the product of accumulated, well-structured adaptations in the brain and body, driven by practice that targets specific weaknesses just beyond current ability. The number of hours spent in an activity is almost irrelevant. What matters is whether each hour forces the nervous system to encode a more refined mental representation of the skill. The goal of any training intervention is to build richer, more accurate internal models that allow the performer to detect, diagnose, and self-correct errors in real time.

Five Mental Models
  1. 01
  2. 02
  3. 03
  4. 04
  5. 05

Five specific models, each named and explained with concrete examples, unlocked with purchase.

A Signature Question · sample

What is the specific sub-skill this learner cannot yet execute, and what does that tell us about the gap in her current mental representation?

4 more questions in Anders Ericsson's voice are unlocked with purchase.

What Anders Ericsson Would NOT Do · sample
✗**Accept hours logged as a proxy for development.** Ericsson spent much of his career correcting the misreading of his own "10,000 hours" finding. He would not evaluate a training program by its duration. He would evaluate it by the ratio of deliberate to naive practice within those hours, and by whether each session produced measurable movement in a specific representational gap.

Full list of anti-patterns unlocked with purchase.

Continue reading

The full framework adds: detailed explanations of all five mental models with real-world examples, the decision heuristics Anders Ericsson 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.

What's inside
  • ✦Core philosophy: 2–3 sentences grounded in Anders Ericsson'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 Anders Ericsson, 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
Delivered in two formats
  • →anders-ericsson.zip: a native Claude Skill. Upload to Settings → Skills in Claude, or unzip to ~/.claude/skills/
  • →anders-ericsson-framework.md: plain markdown. Works in ChatGPT Custom GPTs, Gemini, Claude Projects, agent system prompts, anywhere
Sample output

What it does with a real question.

The brief

A founder is deciding whether to take a large but difficult client.

Take the client, but only if you can name the skill it will force you to build. A large, difficult account is useful to a founder in exactly one way: it can push your team to the edge of what it currently does well. Most growth is not that. Most of it is repeating familiar work at larger volume, which feels like progress and teaches almost nothing. So the question is not "can we survive this client?" but "what will this client make us learn that we cannot learn any other way?"

Be specific. Maybe it is running delivery across three stakeholders who disagree, or scoping work when requirements shift weekly, or holding margin under pressure. If you can't say which, the difficulty is just cost, and you should decline or price it as pure cost.

Second, check the feedback loop. Hard clients teach when you learn quickly where you failed. If the first signal arrives in a quarterly review, you will absorb the pain without the lesson. You need short cycles: weekly check-ins, explicit criteria for what good looks like, and someone senior who has run an account like this and can tell you what you are missing.

Next move: before signing, write one page naming the capability gap this client exposes, who on your team will own closing it, and the weekly signal that tells you it is closing. If you can't fill the page, negotiate scope down or pass.

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.

Download this framework
$4.99
4 for $14.99 · 10 for $29.99
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 Anders Ericsson. A mental-model toolkit, not a literal representation. Delivered as a .md file compatible with Claude, ChatGPT, Gemini, and any LLM.

Featured in

Anders Ericsson in the guides

Related frameworks

Other educators