Feynman Agent Skill
Feynman Technique for deep learning—explain a concept simply, identify gaps, fill them, then refine. Use when learning something new, testing understanding, or preparing to teach.
Install
one command, takes just this skill from the repositorynpx skills add https://github.com/neurofoo/agent-skills --skill feynmanWhat comes with it
13 559 bytes besides the instructionThe instruction itself
16 sections, as written by the authorFeynman Technique
Apply the full Feynman learning technique to deeply understand a concept.
Instructions
Work through all four steps of the Feynman technique. Be honest about gaps—they're the point.
Output Format
Concept: [What are we trying to understand?]
Step 1: Explain It Simply
*Explain as if teaching someone with no background in this field*
Simple Explanation
[Write a plain-language explanation. Use everyday words. Avoid jargon. Aim for a bright 12-year-old to understand.]
Analogy
[Create an analogy using something familiar to illustrate the concept]
Step 2: Identify Gaps
*Where did the explanation get fuzzy, hand-wavy, or require jargon?*
Gaps Found
| Gap | What I Said | What I'm Not Sure About |
|-----|-------------|------------------------|
| 1 | [vague part] | [the underlying question] |
| 2 | [vague part] | [the underlying question] |
| 3 | [vague part] | [the underlying question] |
Jargon Used
| Term | Can I Explain It Simply? |
|------|-------------------------|
| [term] | Yes / No / Partially |
Step 3: Fill the Gaps
*Research or think through each gap*
Gap 1: [Topic]
- The question: [What wasn't clear?]
- The answer: [What I learned]
- Now I can explain it as: [Simple version]
Step 4: Refined Explanation
*Rewrite the complete explanation with gaps filled and simpler language*
Final Simple Explanation
[The improved, complete explanation in plain language]
Improved Analogy
[A refined or new analogy that better captures the concept]
Key Takeaways
- [Core insight 1]
- [Core insight 2]
- [Core insight 3]
Test Question
If someone asked me to explain this in 30 seconds, I'd say:
> [Elevator pitch version]
Guidelines
- Don't pretend to understand—gaps are valuable
- Use analogies from everyday life
- If you need jargon, define it simply
- Shorter is usually better
- The "explain to a child" bar is high—take it seriously
$ARGUMENTS
Other skills for the same job
different authors, same section of the catalogue
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup
Use when implementing any feature or bugfix, before writing implementation code
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always
Expert guidance for systematic backtesting of trading strategies. Use when developing, testing, stress-testing, or validating quantitative trading strategies. Covers "beating ideas to death" methodology, parameter robustness testing, slippage modeling, bias prevention, and interpreting backtest results. Applicable when user asks about backtesting, strategy validation, robustness testing, avoiding overfitting, or systematic trading development.
Cloud laboratory platform for automated protein testing and validation. Use when designing proteins and needing experimental validation including binding assays, expression testing, thermostability measurements, enzyme activity assays, or protein sequence optimization. Also use for submitting experiments via API, tracking experiment status, downloading results, optimizing protein sequences for better expression using computational tools (NetSolP, SoluProt, SolubleMPNN, ESM), or managing protein design workflows with wet-lab validation.
This skill should be used for time series machine learning tasks including classification, regression, clustering, forecasting, anomaly detection, segmentation, and similarity search. Use when working with temporal data, sequential patterns, or time-indexed observations requiring specialized algorithms beyond standard ML approaches. Particularly suited for univariate and multivariate time series analysis with scikit-learn compatible APIs.
How to use it
Take neurofoo/feynman from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.