Feynman Thinking
Explains a software architecture, algorithm, or control flow in plain language, using a mental model (inputs, transformation, outputs), a text or ASCII flow diagram, and Socratic questions that expose hidden assumptions, then flags needless abstraction. Use when the user asks to explain something simply, "Feynman style", to build a mental model of a system, to explain an architecture to a junior developer, or to challenge a design for over-engineering. Do not use for mechanical edits (renames, typo fixes, formatting, format conversions), boilerplate config, or when the user asks for code only
Install
/plugin marketplace add frankxai/claude-skills-libraryThe repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.
npx skills add frankxai/claude-skills-library --skill feynman-thinkinggit clone --depth 1 https://github.com/frankxai/claude-skills-library.git /tmp/claude-skills-library
mkdir -p ~/.claude/skills
cp -r /tmp/claude-skills-library/packs/skills-with-evals/skills/feynman-thinking ~/.claude/skills/feynman-thinkingPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Feynman Thinking Explain a system so a junior developer could rebuild it from the explanation, then strip out what does not need to exist. This applies to the request that triggered the skill, not to every later task in the session. ## Response template Answer in this order and use these headings: 1. **Problem**: one or two plain sentences. What goes in, what must come out, and what breaks without it. 2. **Mental model**: name the exact inputs (payload, file, request), each transformation step, and the output state. One concrete analogy at most. 3. **Flow**: a text diagram for anything with two or more steps, files, or state changes: ```text Client request ──> Auth middleware (verify JWT, attach user_id) ──> Suggestion engine (embed, vector query) ──> Top-K items ``` 4. **Simplest solution**: the least code that solves the stated problem. Name any layer, flag, or interface that exists only for future extension, and say what deleting it would break. 5. **Questions**: two to four Socratic questions from the table below, aimed at assumptions the user has not stated. When the user supplied code, quote the specific function or line each point refers to. ## Socratic questions | Probe | Question template | |---|---| | Hidden assumption | "What are we assuming about the shape of this data that might not hold?" | | Scope | "If we deleted this helper, what would break? Can it be inlined?" |
Details
- Skill name
feynman-thinking- Repository
- frankxai/claude-skills-library
- Path
packs/skills-with-evals/skills/feynman-thinking/SKILL.md- License
- MIT
- Repo updated
- 18 November 2026
FAQ
What does the Feynman Thinking skill do?
Explains a software architecture, algorithm, or control flow in plain language, using a mental model (inputs, transformation, outputs), a text or ASCII flow diagram, and Socratic questions that expose hidden assumptions, then flags needless abstraction. Use when the user asks to explain something simply, "Feynman style", to build a mental model of a system, to explain an architecture to a junior developer, or to challenge a design for over-engineering. Do not use for mechanical edits (renames, typo fixes, formatting, format conversions), boilerplate config, or when the user asks for code only
How do I install the Feynman Thinking skill?
Claude Code plugin: /plugin marketplace add frankxai/claude-skills-library. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Feynman Thinking popular?
It lives in frankxai/claude-skills-library, which has 48 GitHub stars and 6 forks.
Related skills
Acos Meta
48frankxai/claude-skills-library
ACOS self-description and configuration skill. Documents how ACOS works, how to extend it, how to add new skills/commands/agents, and how to debug the hook system. Use when building new ACOS capabilities, understanding the system architecture, or onboarding to ACOS for the first time.
Acos Visual Gen
48frankxai/claude-skills-library
Generate research-grounded visuals using the InfoGenius pipeline. Use when creating infographics, diagrams, educational visuals, or any image that benefits from factual accuracy. Supports 8 visual styles (3D, technical, minimalist, photorealistic, futuristic, vintage, cartoon, standard) and 4 audience levels.
Agent Harness Construction
48frankxai/claude-skills-library
Shape an agent's tools, observations, and recovery without adding a second coordinator. Use when defining a tool, a skill, a hook, or a worktree lane.
Hyperframes CLI
48frankxai/claude-skills-library
HyperFrames CLI dev loop — `npx hyperframes` for scaffolding (init), validation (lint, inspect), preview, render, and environment troubleshooting (doctor, browser, info, upgrade). Use when running any of these commands or troubleshooting the HyperFrames build/render environment. For asset preprocessing commands (`tts`, `transcribe`, `remove-background`), invoke the `hyperframes-media` skill instead.
Doubt Driven Development
48frankxai/claude-skills-library
Cross-examine a non-trivial decision with a fresh, adversarial reviewer before it stands, ideally a different model family. Use before committing branching logic, a boundary change, a safety or idempotence claim, an irreversible step (deploy, migration, merge, public claim), or any confident statement that is cheaper to disprove now than to debug later.
Metrics Framework
430xranx/agentbrief
When the user needs to define KPIs, set up a metrics framework, choose what to measure, or says 'what should we track,' 'define our metrics,' 'KPIs,' 'north star metric,' 'how do we measure success,' 'OKRs,' 'dashboard metrics,' or is starting a new product/feature and needs to decide what data matters.
Browse the most popular Claude skills, all software development skills, or write your own with the skills generator.