Explains a concept from the wiki the way you would explain it to a twelve-year-old, then names where the explanation went thin.

MITAuto-check passedKnowledge Management

Install Feynman

skills CLI
$ npx skills add superhero-tech/super-brain --skill feynman -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install superhero-tech/super-brain feynman --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/superhero-tech/super-brain.git skills-src && mkdir -p .claude/skills && cp -r skills-src/7-Skills/feynman .claude/skills/feynman && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
feynman
GitHub stars
160
Token cost
~1.8k tokens
SKILL.md length
1,043 words
Files
1
Skills in repo
8
Repo updated
First seen
Licence
MIT

At a glance

Explains a concept from the wiki the way you would explain it to a twelve-year-old, then names where the explanation went thin.

  • Works in 7 steps: Pick the concept → Read it properly → Explain it to a twelve-year-old → …
  • The human wants to actually understand a page in 4-Knowledge/
  • SKILL.md covers How to invoke, How it works, Self-check and Hard constraints
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Feynman is an agent skill from superhero-tech/super-brain. Explains a concept from the wiki the way you would explain it to a twelve-year-old, then names where the explanation went thin. Use when the human wants to actually understand a page in 4-Knowledge/, is about to teach or present it, or asks what the vault is hand-waving about.

Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Knowledge Management. The repository describes itself as: Product Builder Second Brain - AI Product Heroes Edition 3. The licence is MIT.

When your agent uses it

  • The human wants to actually understand a page in 4-Knowledge/
  • Is about to teach
  • Asks what the vault is hand-waving about

Example prompts

  • “Use the feynman skill to explain a concept from the wiki the way you would explain it to a twelve-year-old, then names where the explanation went thin”
  • “/feynman”

Workflow steps

7 steps, taken from the step headings in SKILL.md.

  1. Pick the concept
  2. Read it properly
  3. Explain it to a twelve-year-old
  4. Name where it went thin
  5. Flip it
  6. Save the session
  7. Give them somewhere to go

What it can do on your machine

Read from SKILL.md and the folder at commit 0922a1a. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Feynman loads about 1.8k tokens when it runs. Until then it costs about 71 tokens; SKILL.md has 1,043 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~71
When it runs · the whole SKILL.md, loaded when a task matches
~1.8k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from superhero-tech/super-brain at commit 0922a1a, republished under its MIT licence (© superhero-tech). 1,043 words, ~1,799 tokens.

Download SKILL.mdSave it as .claude/skills/feynman/SKILL.md (or your agent's skills folder).
name
feynman
description
Explains a concept from the wiki the way you would explain it to a twelve-year-old, then names where the explanation went thin. Use when the human wants to actually understand a page in 4-Knowledge/, is about to teach or present it, or asks what the vault is hand-waving about.

Feynman

Take a concept out of 4-Knowledge/, explain it in words a child owns, and mark every place the explanation went thin. Those places are the gaps.

Teach in the language the human is using.

This skill reads the wiki and never edits it. It saves the session to 9-Outputs/ and logs it, so there is a record of what got studied - but it creates no wiki page, changes no existing page, and touches nothing in 5-Raw/. Learning is not ingesting.

How to invoke

  • "Explain X to me properly"
  • "Feynman me on [topic]"
  • "What am I fuzzy on?"
  • /feynman

How it works

1. Pick the concept

If the human named one, take it. Otherwise read 4-Knowledge/index.md and offer three candidates, each with a reason to pick it:

  • a page nobody has touched in months
  • a page marked status: draft - written by an AI, never checked by a human
  • a page with source_count: 1 - one source's opinion, sitting there looking like fact

Let them choose. They know which one they are bluffing about.

2. Read it properly

Read the page, the pages it links to, and where it gets thin, the original source in 5-Raw/. You cannot explain simply something you only half read - you will paraphrase instead, and paraphrasing is how the gap stays hidden.

3. Explain it to a twelve-year-old
  • No jargon. If the concept has a name, use the name once and then say what it means in words a child already owns.
  • Trading one term for another is cheating. "It is basically a heuristic" explains nothing to someone who does not know what a heuristic is.
  • One concrete example, early. Something with people and objects in it, not "imagine a system where".
  • Short sentences. A sentence that needs a comma to survive is usually two sentences.
  • Say why anyone should care before you say how it works.
  • Only what the page says. If the wiki explains a mechanism, explain it. If it does not, that is a gap, and it goes in step 4. Do not supply the missing reasoning yourself, not even flagged as a guess - a flagged guess gets quoted back six months later as if the wiki said it.

Link to the source after each block, not inside the sentences. One line under each chunk of explanation:

-> [[Page Name#Section Heading]]

Use the heading anchor, not the page on its own: a link to the top of a 260-line page is barely a link. The heading must match the page character for character or the anchor dies silently. Citations inside the sentences wreck plain language; a link underneath does not.

4. Name where it went thin

This is the part that matters. Go back over what you just said and find every place where you:

  • reached for a technical word because you could not find a plain one
  • wrote "essentially" or "basically" and then restated the jargon
  • described what something does without being able to say why it works
  • skipped a step because the wiki skips it too

Sort each one:

  • Gap in the wiki - the page is thin, hand-wavy, or asserts without explaining. Name what is missing and stop there. Answering it from your own knowledge turns a known hole into an invisible one.
  • Gap in the sources - the wiki faithfully reflects sources that never explained it either. Needs a new source, not a better page.
  • Gap in you - you read it and still cannot make it simple. Say that plainly. Fluent nonsense is worse than an admission.

Three or four gaps is a good haul. Zero means you did not look hard enough, and you should say what you would have to be wrong about for zero to be true.

Show full SKILL.md (426 more words)Show less
5. Flip it

Ask the human to explain one piece back in their own words, then ask one follow-up that goes a level deeper than their answer. Skip it only if they say so.

Explaining finds the gaps of whoever is doing the explaining. When you explain, it finds the wiki's gaps. When they explain, it finds theirs. The second one is what they came for, even if they did not ask for it. Whatever they say back goes into the record - that is the part worth rereading in six months.

6. Save the session

Write 9-Outputs/[YYYY-MM-DD]-feynman-[concept-slug].md:

markdown
---
concept: [Page Name]
date: [YYYY-MM-DD]
pages: [wiki pages read]
gaps: [how many]
---

# Feynman: [Concept]

## The explanation
[what you said, in the plain language you said it, each block followed by
its `-> [[Page#Heading]]` link]

## Where it went thin
**Wiki:** [gaps in the pages]
**Sources:** [gaps the sources never covered]
**Mine:** [what you could not make simple]

## What would close them
- [one line per gap, phrased as something they could do]

## What they said back
[their explanation from step 5, and where the follow-up landed. Skip the
section if step 5 did not run.]

## Where to go next
[the numbered moves from step 7]

Then append to 4-Knowledge/log.md:

## [YYYY-MM-DD] query | feynman: [Concept]
Pages read: Page A, Page B
Output: 9-Outputs/YYYY-MM-DD-feynman-slug.md
Gaps: x wiki, y sources, z mine

It is a query action because that is what it is: reading the wiki and producing something from it. The feynman: marker makes the study sessions easy to pick out later.

7. Give them somewhere to go

End every session with numbered next moves, so they can answer with a digit instead of composing a request. Three or four, drawn from what this session actually turned up - never a generic menu.

Pull from:

  • Dig into a gap - "go one level down on [gap 2]" when the gap is interesting rather than just missing
  • Go to the source - name the file in 5-Raw/ that would settle it, so they can read the original
  • Close it - offer to run ingest on a source they bring, or lint if the page looked structurally thin
  • Take it further - explain a page this one links to, or the same page for a different audience: a client, a room, a sceptic
  • Test the human - re-explain one part after they have answered step 5, harder

Fixing is a different job than studying. Offer, then wait to be asked.

Self-check

  • Could a twelve-year-old repeat the gist back?
  • Did the explanation stay out of the concept's own vocabulary?
  • Is there a concrete example with people or objects in it?
  • Are the gaps specific, rather than "this section could be clearer"?
  • Does every block carry a [[Page#Heading]] link, and does every heading exist on the page?
  • Is every sentence something the wiki says, rather than something you worked out?
  • Are the next moves numbered, and do they come from this session rather than a template?
  • Is the session in 9-Outputs/ and the entry in 4-Knowledge/log.md?

Hard constraints

  • No wiki page is created or edited. 4-Knowledge/log.md is the one file in that folder this skill appends to.
  • 5-Raw/ is read-only, as always. Reading a source to understand it is not ingesting it.
  • Filing a gap into the wiki is ingest or lint, and only when asked.

© superhero-tech, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in 7-Skills/feynman of superhero-tech/super-brain.

Open the folder on GitHubat commit 0922a1a

Compare with similar skills

Feynman next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Feynman compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Feynman this skillsuperhero-tech/super-brain160—~1.8kAutomated safety check: PassMIT
Baoyu URL To Markdownsdyckjq-lab/llm-wiki-skill2.5k3 repos~3.2kAutomated safety check: PassNone
Logseq Review Workflow Evallogseq/logseq45k—~1kAutomated safety check: PassAGPL-3.0
Obsidian CLIAtmosphere/atmosphere3.8k13 repos~795Automated safety check: PassApache-2.0
Esm Cjs Risk Scanlogseq/logseq45k—~3.3kAutomated safety check: PassAGPL-3.0
Capture Conversationoutline/outline41k—~474Automated safety check: PassCustom licence

Similar skills

  • Baoyu URL To Markdown

    sdyckjq-lab/llm-wiki-skill

    Fetch any URL and convert to markdown using Chrome CDP. An agent skill from sdyckjq-lab/llm-wiki-skill.

    2.5k GitHub starsUsed in 3 repos~3.2k tokens
    Knowledge ManagementAuto-check passed
  • Compare two revisions of the Logseq logseq-review-workflow skill by running the same review prompt against isolated before and after skill snapshots, collecting both outputs, and producing a…

    45k GitHub stars~1k tokensUpdated today
    Knowledge ManagementAuto-check passed
  • Obsidian CLI

    Atmosphere/atmosphere

    Interact with Obsidian vaults using the Obsidian CLI to read, create, search, and manage notes, tasks, properties, and more.

    3.8k GitHub starsUsed in 13 repos~795 tokens
    Knowledge ManagementAuto-check passed
  • Esm Cjs Risk Scan

    logseq/logseq

    Scan Logseq ClojureScript Node/Electron targets for npm module loading risks, especially ESM-only packages that may fail when loaded through js/require or shadow-cljs require-based shims.

    45k GitHub stars~3.3k tokensUpdated today
    Knowledge ManagementAuto-check passed
  • Capture Conversation

    outline/outline

    Save the current conversation, a decision, or a set of notes as a document in an Outline collection; use when the user wants to keep what was discussed in their knowledge base.

    41k GitHub stars~474 tokensUpdated today
    Knowledge ManagementAuto-check passed
  • Karpathy LLM Wiki

    Astro-Han/karpathy-llm-wiki

    A skill your agent uses when building or maintaining a personal LLM-powered knowledge base.

    2.4k GitHub stars~3.6k tokensUpdated 2 mo ago
    Knowledge ManagementAuto-check passed

More from superhero-tech/super-brain

All 8 skills in this repo
  • Ingest

    superhero-tech/super-brain

    Compiles a source from 2-Inbox/ into the wiki, across every page it touches, then archives it.

    160 GitHub stars~1.3k tokensUpdated 1 mo ago
    Auto-check passed
  • Second Brain Setup

    superhero-tech/super-brain

    A skill your agent uses when creating or refreshing a product builder's personal profile in 8-System/about.md - supports both assessment-based (Gallup, DISC, MBTI) and interview-based onboarding

    160 GitHub stars~1k tokensUpdated 1 mo ago
    Auto-check passed
  • Lint

    superhero-tech/super-brain

    Health check over the compiled wiki in 4-Knowledge/, written up as a ranked report.

    160 GitHub stars~1.2k tokensUpdated 1 mo ago
    Auto-check passed
  • Query

    superhero-tech/super-brain

    Answers from the compiled wiki in 4-Knowledge/, with citations and a saved output file.

    160 GitHub stars~909 tokensUpdated 1 mo ago
    Auto-check passed
  • Youtube

    superhero-tech/super-brain

    Captures a YouTube video as a source note and a wiki page. An agent skill from superhero-tech/super-brain.

    160 GitHub stars~985 tokensUpdated 1 mo ago
    Auto-check passed
  • Project Start

    superhero-tech/super-brain

    Sets up a new project folder and runs the interview that fills its brief.

    160 GitHub stars~1.1k tokensUpdated 1 mo ago
    Auto-check passed

Questions about Feynman

What does Feynman do?

Explains a concept from the wiki the way you would explain it to a twelve-year-old, then names where the explanation went thin. Feynman is an agent skill from superhero-tech/super-brain. Explains a concept from the wiki the way you would explain it to a twelve-year-old, then names where the explanation went thin.

When should I use Feynman?

Feynman fits situations like: the human wants to actually understand a page in 4-Knowledge/; is about to teach; asks what the vault is hand-waving about.

How do I install Feynman in Claude Code?

Run `npx skills add superhero-tech/super-brain --skill feynman -a claude-code`. Or copy the skill folder (7-Skills/feynman in superhero-tech/super-brain) into .claude/skills/feynman in your project. Claude Code loads it when a task matches its description.

How do I install Feynman in Codex?

Run `npx skills add superhero-tech/super-brain --skill feynman -a codex`. Or copy the skill folder (7-Skills/feynman in superhero-tech/super-brain) into .agents/skills/feynman in your project. Codex loads it when a task matches its description.

Can I use Feynman in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add superhero-tech/super-brain --skill feynman -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/feynman, .gemini/skills/feynman, .github/skills/feynman and .opencode/skills/feynman in your project.

What does Feynman need to run?

SKILL.md names no scripts, command-line tools or credentials: Feynman is instructions for the agent only.

Does Feynman access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Feynman safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Feynman use?

Feynman is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Feynman use?

About 1.8k tokens (SKILL.md is roughly 7.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Feynman?

Skills that share tags, products or a category with Feynman: Baoyu URL To Markdown (sdyckjq-lab/llm-wiki-skill, 2.5k stars), Logseq Review Workflow Eval (logseq/logseq, 45k stars), Obsidian CLI (Atmosphere/atmosphere, 3.8k stars) and Esm Cjs Risk Scan (logseq/logseq, 45k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Feynman?

superhero-tech (a GitHub organization) maintains it in superhero-tech/super-brain, which has 160 GitHub stars. The repository holds 8 skills in this directory. The repository was last updated on August 25, 2026.

Source: superhero-tech/super-brain on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.