feynman-learning
Skill1 starsChanged 4 months agoMITView on GitHub
Test and solidify understanding of new concepts using the Feynman Technique. Use when the user says "test me on [concept]", "Feynman [topic]", "I learned about [X]", or wants to practice explaining something they've learned. Creates a glossary of mastered concepts over time.
4 other projects use a version of this.
Adopted by
Most recently taken up by
- ZhouYinLong-lab/Dog-Skillstheir own version, first seen Nov 8, 2026
- JJjyJJ7F3/feynman-learningtheir own version, first seen Oct 20, 2026
- THU-MAIC/OpenMAICtheir own version, first seen Oct 8, 2026
- Xww-coder/feynman-learning-skilltheir own version, first seen Jun 26, 2026
Other versions4 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 4
- THU-MAIC/OpenMAIC★ 43ksame name
- Xww-coder/feynman-learning-skill★ 9same name
- ZhouYinLong-lab/Dog-Skills★ 7same name
- JJjyJJ7F3/feynman-learning★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository4 other files it gives its agents.
- exec-materials-reviewSkill
- fallacy-finderSkill
- goal-focused-folder-organizationSkill
- book-reviewSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 30
Ask the user to explain the concept as if teaching a curious 12-year-old.
- Distinctive: line 46
If the explanation needs work:
- Distinctive: line 48
Ask the user to try again
- Distinctive: line 79
Action: Ask what they want help with.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Feynman Learning
A structured workflow for deep learning through teaching.
Purpose
The Feynman Technique is based on Richard Feynman's insight: if you can't explain something simply, you don't understand it well enough.
- User selects a Concept to learn and triggers Feynman Learning
- User explains the Concept as if to a 12-year-old
- Claude reviews for simplicity and accuracy; User iterates
- Claude adds the refined explanation to a glossary Markdown file
When to Use
Trigger this skill when the user:
- Says "test me on [concept]" or "Feynman [topic]"
- Says "I learned about [X]" and wants to be tested
- Wants to practice explaining something they've learned
- Asks to add something to their learning glossary
Workflow
Step 1: Prompt for Explanation
Ask the user to explain the concept as if teaching a curious 12-year-old. Emphasize: no jargon, use analogies, keep it simple.
Step 2: Review Response
Evaluate the explanation on two dimensions:
Simplicity — Would a 12-year-old actually understand this?
- Flag jargon or unexplained technical terms
- Note missing analogies or examples
- Identify overly complex sentence structures
Accuracy — Is it technically correct?
- Identify factual errors or misconceptions
- Note oversimplifications that distort the truth
- Flag missing crucial details
Step 3: Iterate
If the explanation needs work:
- Provide specific, constructive feedback
- Ask the user to try again
- Repeat until both simplicity and accuracy pass
Step 4: Archive
Once the explanation is solid:
- Confirm mastery with the user
- Save the polished explanation to
/mnt/user-data/outputs/feynman-glossary.md - Format:
## [Concept Name]followed by the user's explanation and date
Examples
Correct Usage
User: "I learned about neural networks today — test me with Feynman" Claude: Prompts user to explain neural networks to a 12-year-old → Reviews → Iterates → Archives
User: "Feynman gradient descent" Claude: Prompts explanation → Reviews for simplicity/accuracy → Iterates → Archives
User: "Add my explanation of APIs to my glossary" Claude: Reviews existing explanation → Archives to glossary
Incorrect Usage
User: "What is the Feynman technique?" Action: Answer the question directly. Do not trigger the testing workflow.
User: "Explain neural networks to me" Action: Explain the concept. Do not trigger testing — the user wants to learn, not be tested.
User: "Help me study for my exam" Action: Ask what they want help with. Only trigger Feynman workflow if they want to test their understanding of specific concepts.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.