Eli5 logo

Eli5

Organization
greenfield-inc
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 explicit skill invocation is needed. Skip simple factual lookups and respect text-only requests.

Overview

Publishergreenfield-inc
RepositoryPane
Skill nameeli5
Stars
529
Forks
227
Bundled files
Instructions only
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by greenfield-inc on GitHub. Read the source before you install it.

Installation

Install the Eli5 AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/greenfield-inc/Pane/tree/main/main/src/services/paneChatBundle/skills/eli5
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/greenfield-inc/Pane.git /tmp/Pane
mkdir -p .claude/skills
cp -r /tmp/Pane/main/src/services/paneChatBundle/skills/eli5 .claude/skills/eli5
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Eli5 in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Eli5 on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Eli5 is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

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 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 Grain workspace when connected, following explain-visually; pass the workspace ID and storage rule to any writer. Keep needed local files, respect audience/privacy limits, and fall back locally when disconnected. 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.

Frequently asked questions

What does the Eli5 AI skill do?

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 explicit skill invocation is needed. Skip simple factual lookups and respect text-only requests.

Why use Eli5 on TypingMind?

Because you install it once and use it with any model. Eli5 is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Eli5 in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/greenfield-inc/Pane/tree/main/main/src/services/paneChatBundle/skills/eli5. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Eli5?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Eli5?

As many as you like. As long as a model supports skills, you can use Eli5 with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Eli5 AI skill free?

It is published on GitHub by greenfield-inc. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇