CCM
/Skills
SkillsMCPMarketplacesDigestToolsAdvertise

This week in Claude

Every Monday: Claude Code, Agent SDK, MCP, and the Anthropic platform moves worth your time.

Skills by Category
Frontend DevelopmentBackend & APIsTesting & QASecurityDevOps & CI/CDGit & Pull RequestsDocumentationCode Review & QualityAI & Agent BuildingSkill Development
MCP Servers by Category
Sales & MarketingWeb & Browser AutomationDatabasesAI & LLM ToolsCloud & InfrastructureCommunication & MessagingDeveloper ToolsDesign & CreativeDocuments & KnowledgeSearch & Web Crawling
Marketplaces by Category
AI Agents & OrchestrationLLM IntegrationDevelopment ToolsFrontend & UIBackend & APIsDatabasesTesting & Code QualityDevOps & CloudSecurity & ComplianceGit & Version Control

Claude Code Marketplaces

Discover Claude Code plugins, extensions, and tools. Automatically updated directory of Anthropic Claude AI marketplaces with development tools, productivity plugins, and integrations.

Resources

  • Browse Skills
  • Browse MCP Servers
  • Browse Marketplaces
  • Skill index
  • MCP index
  • Marketplace index
  • Plugins Reference

Community

  • About
  • Tools
  • Feedback
  • Privacy Policy
  • Advertise

Built for the Claude Code community with Claude Code by mertbuilds.com

Independent project, not affiliated with Anthropic
neurofoo avatar

Feynman

neurofoo/agent-skills
328 installs106 stars
Summary

This walks you through the classic Feynman learning technique: explain a concept in plain language, spot where you're hand-waving or using jargon you can't define, research those gaps, then rewrite it better. It's structured as a four-step template with tables for tracking vague spots and undefined terms. Good for when you're learning something technical and want to actually understand it rather than just memorize definitions, or when you're preparing to teach and need to find the holes in your mental model. The "explain to a 12-year-old" bar forces you to confront what you don't really get yet, which is the whole point.

Install to Claude Code

npx -y skills add neurofoo/agent-skills --skill feynman --agent claude-code

Installs into .claude/skills of the current project.

CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
MCP-ready Email SendingMCP-ready Email Sending
MCP-ready Email Sending
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Capacitor - Shared memory for your team’s coding agents.
Capacitor - Shared memory for your team’s coding agents.
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
CodeScene MCP ServerCodeScene MCP Server
CodeScene MCP Server
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Give your AI the whole web as clean markdownGive your AI the whole web as clean markdown
Give your AI the whole web as clean markdown
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt - the only tool your agent needs
belt - the only tool your agent needs
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
inference shell
inference shell
create and run specialised agents in minutes
build now →
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
MCP-ready Email SendingMCP-ready Email Sending
MCP-ready Email Sending
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Capacitor - Shared memory for your team’s coding agents.
Capacitor - Shared memory for your team’s coding agents.
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
CodeScene MCP ServerCodeScene MCP Server
CodeScene MCP Server
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Give your AI the whole web as clean markdownGive your AI the whole web as clean markdown
Give your AI the whole web as clean markdown
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt - the only tool your agent needs
belt - the only tool your agent needs
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
inference shell
inference shell
create and run specialised agents in minutes
build now →
Files
SKILL.mdView on GitHub

Feynman 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

GapWhat I SaidWhat 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

TermCan 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

  1. [Core insight 1]
  2. [Core insight 2]
  3. [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

Featured
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
MCP-ready Email SendingMCP-ready Email Sending
MCP-ready Email Sending
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Capacitor - Shared memory for your team’s coding agents.
Capacitor - Shared memory for your team’s coding agents.
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
CodeScene MCP ServerCodeScene MCP Server
CodeScene MCP Server
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Give your AI the whole web as clean markdownGive your AI the whole web as clean markdown
Give your AI the whole web as clean markdown
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt - the only tool your agent needs
belt - the only tool your agent needs
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
inference shell
inference shell
create and run specialised agents in minutes
build now →
Categories
Testing & QAAI & Agent Building
First SeenJun 3, 2026
View on GitHub

More from neurofoo/agent-skills

All 2 skills →
  • Socratic299

Recommended

More Testing & QA →
pmprompt avatar
pmf-survey

pmprompt/claude-plugin-product-management

Use when asked to "PMF survey", "measure product-market fit", "40% rule", "Sean Ellis test", "Rahul Vohra method", or "how disappointed would you be". Helps quantify product-market fit and systematically improve it. The PMF Survey framework (created by Sean Ellis, popularized by Rahul Vohra at Superhuman) measures how disappointed users would be without your product and turns that data into a roadmap.
328
43
ahmedasmar avatar
ci-cd

ahmedasmar/devops-claude-skills

CI/CD pipeline design, optimization, DevSecOps security scanning, and troubleshooting. Use this skill whenever the user mentions CI/CD, GitHub Actions, GitLab CI, pipelines, workflows, builds, or DevSecOps. Triggers include creating new CI/CD workflows, debugging pipeline failures or flaky tests, implementing SAST/DAST/SCA security scanning, optimizing slow builds with caching or parallelization, setting up deployment workflows, securing pipelines with OIDC or secrets management, implementing matrix builds or test sharding, and troubleshooting Docker, permissions, or timeout issues.
327
196
kernel avatar
kernel-typescript-sdk

kernel/skills

Build Kernel browser automation in TypeScript with server-side Playwright or CDP, including profiles, proxies, and reliable session cleanup.
326
9
krutikjain avatar
android-di-hilt

krutikjain/android-agent-skills

Wire Android dependency injection with Hilt, scopes, testing overrides, and module ownership boundaries.
323
14
octagonai avatar
commodities-list

octagonai/skills

Retrieve the full catalog of tradable commodities across energy, metals, and agriculture using Octagon MCP. Use when researching commodity markets, identifying trading firms, understanding market participants, and analyzing commodity sector coverage.
323
129
pmprompt avatar
trustworthy-experiments

pmprompt/claude-plugin-product-management

Use when asked to "run an A/B test", "design an experiment", "check statistical significance", "trust our results", "avoid false positives", or "experiment guardrails". Helps design, run, and interpret controlled experiments correctly. Based on Ronny Kohavi's framework from "Trustworthy Online Controlled Experiments".
321
43