Skip to content
Agent Orchestration
Skill

/eli5

Teach an unfamiliar topic from first principles with a picture-first HTML explanation, saved in Grain when connected. Use for "explain from scratch," "I'm lost," "what does this mean?", "explain in plain English," beginner questions about how something works, or /eli5; no

From plugin
pane
59739 skills4 agents

Claude Code

$ npx -y skills add greenfield-inc/Pane --skill eli5 --agent claude-code

SKILL.md

eli5.SKILL.md
name: eli5
description: Teach an unfamiliar topic from first principles with a picture-first HTML explanation, published to the workspace's document destination when one is named. Use for "explain from scratch," "I'm lost," "what does this mean?", "explain in plain English," beginner questions about how something works, or /eli5; no explicit skill invocation is needed. Skip simple factual lookups and respect text-only requests.
argument-hint: "<topic, question, or path to explain>"
allowed-tools: Read, Grep, Glob, Bash, Write

ELI5

Task: $ARGUMENTS

The reader is not five. The reader is sharp, busy, and new to exactly this. Respect both halves: no jargon they have not been given, and no padding they have to wade through. One page, one topic, picture first.

When to use it

  • Use ELI5 when the person needs the foundations of a topic, not just a visual alongside an answer. Preserve the three floors below.
  • For a companion to an existing discussion or review, use [explain-visually](../explain-visually/SKILL.md) without turning the task into a beginner lesson.
  • Read that skill's HTML, saving, and verification guidance for this page too. ELI5 owns the teaching structure and reply format; produce one artifact, not two.

Ground it

Before writing a word, find the truth of the topic in what is actually here. A topic inside this repo means reading the real code and tracing the real flow; a general topic means working from what you know and saying so. Collect the three to five facts the whole explanation hangs on. If the honest answer to "how does this work" is "it does not", the page says that; an explainer that flatters a broken thing teaches the wrong lesson.

The three floors

The page renders per the html-explainer skill (tokens, components, diagram rules, quality bar), structured as three floors the reader descends by choice:

1. **The picture.** Masthead, then the opening diagram, then at most a hundred words: the one metaphor or plain-language mechanism that makes the topic click. A reader who stops here leaves with the right intuition and no vocabulary. 2. **The mechanism.** How it actually works, still in plain words, with one or two more diagrams or panel pairs (before/after, request/ response, cause/effect). Each new term is introduced at the moment it pays for itself. A reader who stops here could explain it to someone else. 3. **The real names.** Inside `details` blocks: the proper terminology mapped to the plain words used above, the file:line anchors when the topic is code, the two or three things people commonly get wrong, and where to go deeper. A reader who opens these is ready for the real documentation.

Metaphors

One metaphor, carried all the way through, beats three abandoned ones. Pick it for mechanical honesty (the parts must correspond) rather than charm, and drop it the moment it would mislead; some topics are best explained literally, and a plain diagram of the actual parts is always an acceptable metaphor. For an abstract topic with no visual shape, diagram the relationship (what talks to what, what depends on what) rather than forcing an object.

Words

  • Floor 1 under a hundred words; the whole page under six hundred.

The budget counts every word the reader sees with `details` closed, captions, masthead, and SVG labels included; markup and style count nothing.

  • Short declarative sentences. No "simply", no "just", no "magic".
  • Numbers over adjectives: "answers in about 7 seconds" beats "fast".
  • Every sentence survives the question "does the reader need this to

understand the next one?"

Boundaries

  • Save the page in the existing task's folder at the document destination your workspace instructions name, following [explain-visually](../explain-visually/SKILL.md); pass the workspace ID and storage rule to any writer. Keep needed local files, respect audience/privacy limits, and without a destination save it in the work's page bundle (see [page](../page/SKILL.md)) and open it with `runpane panels open --file <path> --source agent --yes`. This overrides the renderer's local-only/no-publication defaults, not its visual standards.
  • Accuracy outranks simplicity: simplify by omission, never by

distortion, and name the biggest thing you left out in floor 3.

  • The page is the deliverable; the chat reply is one line saying where

it is and what it covers.

  • No em dashes.
Read more
@greenfield-inc
Ships withpane

pnpm dlx runpane@latest

59739 skills4 agents
Get the whole plugin

Stars on GitHub

Momentum

stars in total
597
Star history of greenfield-inc/Pane on GitHub, a chart by star-history.com

Other skills on pane.

babysit-pr

babysit-pr

Use after a pull request is open to watch its CI and review-bot comments until it is ready. Fixes real findings, replies with a…

@greenfield-inc@greenfield-incInstall Skill
brief

brief

Use when a problem, idea, or change of intent is worth capturing as a long-form page, or the person asks to write it up. Never…

@greenfield-inc@greenfield-incInstall Skill
bug-intake

bug-intake

Use when the person reports broken behaviour or starts a session to file a bug. Reproduces and reports. Never fixes.

@greenfield-inc@greenfield-incInstall Skill
codebase-design

codebase-design

Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening…

@greenfield-inc@greenfield-incInstall Skill
codebase-explorer

codebase-explorer

Explore the codebase to locate files, trace behavior, and document existing patterns with precise file references. Use when the…

@greenfield-inc@greenfield-incInstall Skill
cold-read

cold-read

Give a fresh agent something to walk through with zero context - a PR body, a landing page, a document, a process, instructions,…

@greenfield-inc@greenfield-incInstall Skill

More skills from other plugins.

1password

1password

Set up and use 1Password CLI for sign-in, desktop integration, and reading or injecting secrets.

clawdis11d393k
@steipete@steipeteInstall Skill
computer-use

computer-use

Drives the GUI of a visible local app window through `orca computer`: accessibility tree, clicks, typing, menus, dialogs, and…

orca11d111k
@stablyai@stablyaiInstall Skill
agentmail

agentmail

Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by…

paperclip10d109k
@paperclipai@paperclipaiInstall Skill
adr-create

adr-create

Create a new Architecture Decision Record with sequential numbering and AgentDB registration

@ruvnet@ruvnetInstall Skill

Questions about eli5.

Which coding agents can use eli5?
eli5 installs in Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode and Windsurf with the skills CLI, using each agent's flag shown on this page. Flowy's auto-invocation, which fires a skill when your prompt matches, runs in Claude Code only.