Html Explainer logo

Html Explainer

Organization
greenfield-inc
html-explainer

The house standard for any skill that renders an HTML page for a person to read, covering design tokens, typography, components, diagrams, and quality gates so every generated page shares one calm, graphic-first look. Use when a skill's instructions say to render its output per the html-explainer standards, or when the user asks for an HTML explainer of anything and no more specific skill applies.

Overview

Publishergreenfield-inc
RepositoryPane
Skill namehtml-explainer
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 Html Explainer 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/html-explainer
  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/html-explainer .claude/skills/html-explainer
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Html Explainer 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 Html Explainer 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 Html Explainer 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.

HTML Explainer

Task: $ARGUMENTS

A page for a person is pictures interrupted by words. The diagram carries the argument and the prose annotates it, the way a whiteboard sketch carries a design review; a section that has no visual either earns its place in prose or belongs folded into depth. Without one standard, every generated page invents its own fonts, colors, and structure, and the reader pays for the drift. This skill is where the look and the bar live. eli5 renders with it (other pages follow page); invoked directly, it renders a one-off explainer of whatever the argument names.

The file

One self-contained .html file, tuned entirely for reading: there is no hosting, no publish step, no capability layer to design for. Inline CSS in a single <style> block, inline SVG for every drawing, no external requests of any kind: no CDN, no web fonts, no remote images, no scripts unless the page genuinely needs interaction, and then only vanilla inline JS. System font stacks only. Target well under 200KB. Write it to ./tmp/ (or the caller's stated destination), then open it unless the caller says not to. Inside Pane (PANE_SESSION_ID is set), run runpane panels open --file <path> --source agent --yes --json; it opens a browser tab in split view beside the conversation. Elsewhere use the system browser (open on macOS, xdg-open on Linux).

Tokens

Copy this block verbatim as the start of the style sheet. Extend it only by adding tokens, never by restyling these.

css
:root {
  --paper: #FAF8F5; --ink: #1F2328; --ink-soft: #5A5F66;
  --line: #E4DFD7; --panel: #FFFFFF;
  --accent: #0E7569; --accent-soft: #E3F0EE;
  --warn: #B45309; --warn-soft: #F7EBDD;
  --bad: #9F3A38; --bad-soft: #F6E8E7;
  --mono: ui-monospace, "SF Mono", SFMono-Regular, Menlo, Consolas, monospace;
  --serif: Georgia, "Iowan Old Style", "Times New Roman", serif;
  --sans: -apple-system, BlinkMacSystemFont, "Segoe UI", Roboto, sans-serif;
}
@media (prefers-color-scheme: dark) {
  :root {
    --paper: #15191D; --ink: #E8E6E1; --ink-soft: #9BA1A8;
    --line: #2C3237; --panel: #1C2126;
    --accent: #2FA79A; --accent-soft: #16302D;
    --warn: #D98E3D; --warn-soft: #32271A;
    --bad: #CF6F6C; --bad-soft: #33211F;
  }
}

Drawings

Every page opens with one drawing directly after the masthead: the whiteboard sketch the rest of the page elaborates. More follow wherever a relationship, a flow, or a comparison is the point; drawing first and writing around the drawing is the intended order of work.

  • Inline SVG on the tokens: --panel fills, --line strokes, --accent for the path that matters, --warn and --bad where verdicts are part of the picture, --sans labels at 12 to 14px.
  • Sketch energy over precision: slightly rounded corners, imperfect widths, dashed strokes for the tentative and solid for the certain, arrows with real heads. Boxes and arrows over art; three boxes and an arrow beats a mural.
  • Warmth comes from the drawing, never from decoration: no gradients, no shadows, no icon fonts, no clip art.
  • Legible at page width, viewBox set, no fixed pixel widths. A simple subject gets a simple drawing, never a skipped one.
  • When the user wants a diagram they can edit themselves, that is the excalidraw-pr-diagrams skill's job, not an inline SVG.

Type and layout

  • Body: --sans, 16px, line-height 1.6, --ink on --paper, one centered column, max-width: 72ch, generous vertical rhythm.
  • h1: --serif, weight 500, ~2.1rem, text-wrap: balance. One per page. Directly under it, a one-sentence standfirst in --ink-soft.
  • Section headers: a mono uppercase eyebrow (.72rem, letter-spacing .1em, --accent) above an h2 (~1.25rem). Sections are numbered when order matters and unnumbered when it does not.
  • Code: --mono on --panel with a --line border. Prose lines stay under 90 characters; nothing scrolls horizontally except inside a pre with its own overflow.

Components

The whole vocabulary. A page uses what it needs and invents nothing:

  • .badge: mono, uppercase, .72rem, soft background. Accent for identity and success, warn for caution, bad for failure. Badges carry verdicts; prose carries reasons.
  • .panel: --panel background, --line border, 6px radius, padded. The unit of grouped content; grids of panels for comparisons (before/after, expected/actual).
  • .callout: a panel with a 3px left border in accent, warn, or bad. One-paragraph emphasis, used sparingly.
  • .card: a panel with a mono eyebrow title, for repeating items (a lesson, a promise, a dependency).
  • details > summary: for depth the reader opts into. The page must read complete with every details closed.

The bar

Before opening the page, verify all of these; fix rather than ship:

  1. The drawings could carry the page alone: a reader who skims only them and the headers leaves oriented.
  2. Renders complete with JavaScript disabled and every details closed.
  3. Nothing is fetched: no src, href, or url() that loads an external resource (stylesheet, script, font, image). URLs quoted as text or code content are fine; a page about an endpoint must be able to print it.
  4. Both color schemes hold: readable in light and dark.
  5. Every fact on the page came from the caller's material; the page adds structure and pictures, never claims.
  6. One h1, sections in reading order, nothing beyond the component vocabulary above.

Boundaries

  • This skill owns form. The invoking skill owns content, truth, where the file lives, and what the chat reply says; its reply and open-in-browser rules override the defaults here.
  • When a caller's needs exceed the vocabulary, extend the vocabulary here in a PR, do not fork the style inline.
  • No em dashes, on the page and in this file.

Frequently asked questions

What does the Html Explainer AI skill do?

The house standard for any skill that renders an HTML page for a person to read, covering design tokens, typography, components, diagrams, and quality gates so every generated page shares one calm, graphic-first look. Use when a skill's instructions say to render its output per the html-explainer standards, or when the user asks for an HTML explainer of anything and no more specific skill applies.

Why use Html Explainer on TypingMind?

Because you install it once and use it with any model. Html Explainer 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 Html Explainer 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/html-explainer. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Html Explainer?

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 Html Explainer?

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

Is the Html Explainer 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 👇