Skip to content

evanshlee/feynman-skill

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

1 Commit
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

feynman-skill

An AI agent skill that makes you learn concepts the hard way: by explaining them out loud and getting your gaps exposed.

/feynman JWT signatures → the AI plays a strict critic, points out ONE gap in your explanation per turn, and loops until you actually understand it (or you tap out).

No summaries. No hand-holding. The AI never gives you the answer — you have to produce it yourself. That's the whole point.

What is this?

An implementation of the Feynman Technique as an interactive agent skill. Named after physicist Richard Feynman's learning method: if you can't explain something simply, you don't understand it.

The skill acts as the missing piece most learners lack — a critic who stress-tests your explanation and refuses to let you get away with fluent-sounding BS.

Why?

Self-study suffers from two well-documented illusions:

  • Fluency illusion: re-reading or re-explaining feels like learning, but the explanation gets smoother without getting deeper.
  • Illusion of Explanatory Depth (IOED): people believe they can explain mechanisms they actually can't.

Feynman Technique alone doesn't fix these — you still grade your own homework. This skill adds the missing critic.

Quick Start

1. Install

Pick your platform:

Full installation guide: INSTALL.md.

2. Run

/feynman [concept you want to master]

Example:

/feynman TCP three-way handshake

The AI will:

  1. Ask you to explain it in your own words
  2. Quote you, point out ONE gap, ask a probing question
  3. Repeat until 4 of 5 mastery criteria are met (or you say "done")
  4. Save a session log you can revisit or resume

3. Example session

User: /feynman DNS

AI: 🎓 Feynman session started: DNS
    Rules: explain simply, I point out ONE gap per turn, say "done" to wrap up.
    Go ahead.

User: DNS is like a phone book. You type a domain and it gives you an IP.

AI: ✅ The phone-book analogy captures the indexing idea.

    🔍 [mechanism-blackbox] spot:
    > "gives you an IP"

    Who does the lookup, and where? A phone book has a shelf.

    💬 When you visit a brand-new site, who does your computer ask first?

User: My computer asks my router, I think?

AI: ✅ You're tracing a path, which is the right instinct.

    🔍 [mechanism-blackbox] spot:
    > "my router, I think"

    The router forwards it somewhere. The hedging suggests this is the black box.

    💬 What does the router do with that query?

[... continues until mastery ...]

Features

  • 🎯 7-category gap taxonomy with priority ordering
  • 🔁 Multi-turn loop — one gap at a time, strict
  • 🏁 4-of-5 mastery detection — knows when to stop
  • 📁 Session logs — markdown files you can resume, revisit, or share
  • 🌐 Language mirroring — AI replies in whatever language you explain in
  • 🌍 i18n support — English + Korean shipped, more via community
  • 🔌 5+ agent platforms supported

Gap Categories (quick reference)

Code Category What it catches
[factual-error] Wrong claim "HTTP is always encrypted"
[jargon-dodge] Term defined by itself "Recursion is when a function recurses"
[causal-gap] No "why" Describing what without motivation
[mechanism-blackbox] Magic steps "it just works"
[boundary-blur] No differentiation Can't tell X from Y
[broken-analogy] Metaphor breaks Analogy fails under stress
[edge-case-blind] Happy path only No handling of weird inputs

Full details: docs/gap-taxonomy.md.

Mastery Criteria (4 of 5 required)

  1. Term Independence — defines core term without using itself
  2. Causal Chain — can explain why it exists
  3. Mechanism Transparency — step-by-step, no black boxes
  4. Boundary Differentiation — distinguishes from adjacent concepts
  5. Stress-Test Pass — handles at least one edge case

Full criteria: docs/mastery-criteria.md.

Examples

See examples/ for full session transcripts:

Internationalization

The skill ships with language tone guides:

Want to add your language? See i18n/README.md and use the TEMPLATE.md.

Design Philosophy

Read docs/design-rationale.md for the research grounding (retrieval practice, desirable difficulty, IOED, metacognition) and why specific design decisions were made.

Contributing

PRs welcome. See CONTRIBUTING.md — especially for new language translations and domain-specific example sessions.

License

MIT. See LICENSE.

Credits

Inspired by Richard Feynman's learning approach, popularized by Scott Young and the Farnam Street blog. Cognitive science grounding: Chi (self-explanation), Dunning-Kruger, Rozenblit & Keil (IOED), Sweller (cognitive load), Roediger & Karpicke (retrieval practice).

About

An AI agent skill that teaches concepts through the Feynman Technique: you explain, AI finds gaps, loop to mastery.

Topics

Resources

License

Contributing

Stars

Watchers

Forks

Packages

 
 
 

Contributors