Explain logo

Explain

Organization
zenobi-us
explain

Research a subject and build a single-page Diátaxis explainer in minimalist HTML, when a user asks for a researched web explanation, resulting in a validated HTML page with sources

Overview

Publisherzenobi-us
Repositorydotfiles
Skill nameexplain
Stars
67
Forks
6
Bundled files
Instructions only
LicenseMIT
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 zenobi-us on GitHub. Read the source before you install it.

Installation

Install the Explain 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.
  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/zenobi-us/dotfiles.git /tmp/dotfiles
mkdir -p .claude/skills
cp -r /tmp/dotfiles/files/devtools/agent/bundles/agent-core/skills/explain .claude/skills/explain
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Explain 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 Explain 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 Explain 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.

Create a Single-Page Explainer

User Request

text
$ARGUMENTS

Goal

Research the request. Then build one HTML page that explains the subject.

Use the Diátaxis method. Keep each documentation type separate and clear.

The final result MUST be a web page, not a slide deck or presentation.

Required Skills

Load these skills before you start:

  • research
  • simple-english
  • poster
  • The best domain skills for the subject
  • A browser skill for final visual checks

1. Define the Subject

  1. Identify the subject, audience, and expected outcome.
  2. Read each supplied file or URL before you explain it.
  3. Trace related local code when the request concerns a codebase.
  4. Prefer primary sources, official documentation, specifications, and source code.
  5. If the request has no clear subject, ask one focused question and stop.

Use an existing output convention when one exists.

Otherwise, write the page to:

text
.tmp/explain/<subject-slug>/index.html

Store generated SVG files beside the HTML file in an files/assets/ directory.

2. Delegate Research

Use the subagent tool to start two or three independent researcher subagents.

Start all independent research tasks in parallel.

Give each subagent one focused question and a clear output contract.

Each subagent MUST:

  • Use the research skill.
  • Use relevant domain skills.
  • Prefer primary sources.
  • Cite exact URLs and local file paths.
  • Separate facts from interpretation.
  • Report contradictions and uncertain claims.
  • Return compact findings for synthesis.
  • Avoid editing the final HTML page.

Use these research lanes when they fit:

  1. Source model: Identify the main concepts, parts, and factual behavior.
  2. User model: Identify common tasks, examples, risks, and mistakes.
  3. Reference model: Collect exact commands, options, interfaces, limits, and terms.

Do not create extra research lanes without a clear need.

Read local source material while the subagents research independent questions.

After the subagents finish, compare their findings. Resolve conflicts before drafting.

3. Use the Diátaxis Method

Create these four sections on one page:

Tutorial

Give the reader one guided path to a small, successful result.

  • Teach through action.
  • State prerequisites.
  • Use tested steps.
  • Explain only what the reader needs for the next step.

How-to Guide

Show how to complete the most important real task.

  • Start with the reader's goal.
  • Put each condition before its instruction.
  • Use one instruction per step.
  • Include recovery steps for likely failures.

Reference

Give exact factual information for lookup.

  • Use tables, lists, signatures, commands, options, or state definitions.
  • Keep facts concise.
  • Do not add teaching narrative.
  • Cite the source for facts that can change.

Explanation

Explain why the subject works this way.

  • Describe the model, design choices, trade-offs, and limits.
  • Connect causes to effects.
  • Separate verified facts from interpretation.
  • Mark opinions with [bias: ...].

Do not mix the purpose of one section into another section.

4. Write in Simplified Technical English

Apply the simple-english skill to all page text.

  • Use active voice.
  • Use one term for one concept.
  • Use short, complete sentences.
  • Keep procedural sentences at 20 words or fewer.
  • Keep descriptive sentences at 25 words or fewer.
  • Put conditions before instructions.
  • Do not use contractions, filler, or decorative language.
  • Keep code, commands, paths, identifiers, and quoted errors unchanged.

5. Plan the Visuals

Use visuals only when they improve understanding.

Use the poster skill and poster_render to create at least one useful visual summary.

Render each poster visual as SVG. Use black, white, and neutral gray only.

Good poster visuals include:

  • A visual abstract
  • A comparison matrix
  • A sequence summary
  • A compact reference figure
  • A data chart when verified data exists

Create explanatory diagrams as minimalist grayscale SVG files or inline SVG elements.

All diagrams MUST:

  • Use black, white, and neutral gray only.
  • Use simple lines, boxes, arrows, and labels.
  • Include an accessible title and description.
  • Remain readable at mobile width.
  • Avoid gradients, color accents, textures, and decorative effects.

Do not use Mermaid. Do not use raster images for diagrams.

6. Build the HTML Page

Create one responsive index.html page.

Use Tailwind utility classes for the page style.

Use the Tailwind CDN when the output directory has no existing Tailwind build.

Use this visual direction:

  • Black text on a white background
  • White text on black emphasis blocks
  • Neutral gray borders and secondary text
  • Strong typography
  • Large margins and clear spacing
  • Thin rules instead of shadows
  • Square or slightly rounded corners
  • No gradients
  • No colored accents
  • No glass effects
  • No ornamental animation

The page MUST include:

  1. A concise title and summary.
  2. A compact navigation list for the four Diátaxis sections.
  3. The Tutorial section.
  4. The How-to Guide section.
  5. The Reference section.
  6. The Explanation section.
  7. The generated visual summary.
  8. Any necessary grayscale SVG diagrams.
  9. A source list with clickable citations.
  10. A short limitations section when evidence is incomplete.

Use semantic HTML landmarks and a logical heading order.

Add descriptive alt text to linked SVG files.

Add <title> and <desc> elements to inline SVG diagrams.

Make the page readable without JavaScript, except for the Tailwind CDN loader.

Do not add slide controls, carousels, hidden slides, or full-screen presentation behavior.

7. Validate the Result

Before completion:

  1. Open the page with the browser tool.
  2. Check the page at desktop and mobile widths.
  3. Check that all SVG files load.
  4. Check that no text or diagram overflows.
  5. Check that navigation links reach the correct sections.
  6. Check that citations open the correct sources.
  7. Check that the page remains usable without custom JavaScript.
  8. Check that all four Diátaxis sections have distinct purposes.
  9. Run the simple-english self-check on the final text.
  10. Remove unused assets and temporary files.

Fix errors before you report completion.

Completion Report

Report only:

  • The HTML file path.
  • The generated SVG file paths.
  • The main sources.
  • Any unresolved evidence limits.
  • Whether the page opened successfully in the browser.

Frequently asked questions

What does the Explain AI skill do?

Research a subject and build a single-page Diátaxis explainer in minimalist HTML, when a user asks for a researched web explanation, resulting in a validated HTML page with sources

Why use Explain on TypingMind?

Because you install it once and use it with any model. Explain 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 Explain in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/zenobi-us/dotfiles/tree/master/files/devtools/agent/bundles/agent-core/skills/explain. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Explain?

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 Explain?

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

Is the Explain AI skill free?

Yes. It is published on GitHub by zenobi-us under the MIT license. 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 👇