Document Design logo

Document Design

Community
jamditis
document-design

Creates print-ready HTML that exports to PDF. Use to make a proposal, report, one-pager, newsletter, slides, or flyer.

Overview

Publisherjamditis
Repositoryclaude-skills-journalism
Skill namedocument-design
Stars
397
Forks
64
Bundled files
16
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.

  • 16 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by jamditis on GitHub. Read the source before you install it.

Installation

Install the Document Design 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/jamditis/claude-skills-journalism.git /tmp/claude-skills-journalism
mkdir -p .claude/skills
cp -r /tmp/claude-skills-journalism/pdf-playground/skills/document-design .claude/skills/document-design
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Document Design 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 Document Design 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 Document Design 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.

Document design

Create professional, print-ready HTML documents that export to PDF with customizable branding.

Brand configuration

Before creating documents, check for pdf-playground.local.md in the project root. If it is absent, check the legacy Claude Code path .claude/pdf-playground.local.md. If both exist, use only the project-root file. If neither exists, use sensible defaults or ask the user for their brand colors.

Reading brand config

Parse the selected config file's YAML frontmatter:

yaml
---
brand:
  name: "Organization Name"
  tagline: "Tagline"
  website: "https://example.com"
  email: "contact@example.com"

colors:
  primary: "#CA3553"
  secondary: "#000000"
  background: "#FFFFFF"
  text: "#2d2a28"
  muted: "#666666"

fonts:
  heading: "Playfair Display"
  body: "Source Sans 3"

style:
  headingCase: "sentence"
  useOxfordComma: true
---

Default brand values

If no config exists, use these defaults:

  • Primary color: #CA3553 (red)
  • Secondary color: #000000 (black)
  • Heading font: Playfair Display
  • Body font: Source Sans 3
  • Heading case: sentence case

Core principles

  1. Print-first design: All documents target 8.5" × 11" letter size with proper margins
  2. Brand compliance: Use colors and fonts from brand configuration
  3. Sentence case by default: Unless brand config specifies "title" case
  4. Clean exports: Documents must render correctly when printed to PDF

CSS variables

Generate CSS variables from brand config:

css
:root {
    --primary: [colors.primary];
    --secondary: [colors.secondary];
    --background: [colors.background];
    --text: [colors.text];
    --muted: [colors.muted];

    /* Derived colors */
    --primary-dark: [darken primary by 15%];
    --gray-100: #f5f4f2;
    --gray-200: #e8e6e3;
}

Print CSS fundamentals

Page setup

css
@page {
    size: 8.5in 11in;
    margin: 0;
}

@media print {
    body {
        -webkit-print-color-adjust: exact !important;
        print-color-adjust: exact !important;
    }
    .page {
        page-break-after: always;
        page-break-inside: avoid;
    }
}

Fixed page dimensions

css
.page {
    width: 8.5in;
    height: 11in;
    padding: 0.5in 0.75in;
    padding-bottom: 1in; /* Space for footer */
    position: relative;
    box-sizing: border-box;
    overflow: hidden;
}

Fixed footers

css
.page-footer {
    position: absolute;
    bottom: 0.4in;
    left: 0.75in;
    right: 0.75in;
    font-size: 9pt;
    border-top: 1px solid var(--gray-200);
    padding-top: 0.1in;
    background: var(--background);
}

Footer clearance (critical)

Content overlapping or touching the footer is a recurring issue.

Preferred layout, grid rows auto 1fr auto:

css
.page {
    display: grid;
    grid-template-rows: auto 1fr auto;
    overflow: hidden;
}

This makes the header and footer take their natural height, and the content fills the remaining space. No magic-number calc() needed, the footer clearance is structural.

Required safeguards:

  1. Use grid-template-rows: auto 1fr auto on the page so content automatically gets the space between header and footer
  2. Set overflow: hidden on the content container to prevent text bleeding past its bounds
  3. Include padding-bottom: 0.3in (minimum) inside the content area as a buffer
  4. Never use hardcoded height: calc(...) with magic numbers for header/footer heights, they drift when padding or font sizes change
  5. After rendering, always screenshot and visually verify the bottom of the page before delivering
  6. If content overflows, reduce content, never shrink the footer gap. Tighten the header first if you need more room.

Typography patterns

Font loading

css
@import url('https://fonts.googleapis.com/css2?family=[heading-font]:wght@400;600;700&family=[body-font]:wght@400;500;600;700&display=swap');

body {
    font-family: '[body-font]', Arial, sans-serif;
    font-size: 11pt;
    line-height: 1.6;
    color: var(--text);
}

h1, h2, h3 {
    font-family: '[heading-font]', Georgia, serif;
    font-weight: 700;
}

Heading styles

css
.section-title {
    font-size: 26pt;
    color: var(--secondary);
    margin-bottom: 0.25in;
}

.section-title::after {
    content: '';
    display: block;
    width: 0.5in;
    height: 3px;
    background: var(--primary);
    margin-top: 0.12in;
}

Common components

Cover page header

html
<header class="cover-header">
    <div class="logo-bar">
        <div class="logo-primary">[brand.name]</div>
    </div>
    <div class="cover-title-block">
        <div class="cover-eyebrow">[Document type] • [Date]</div>
        <h1 class="cover-title">[Title in configured case]</h1>
    </div>
</header>

Budget table

css
.budget-table thead {
    background: var(--secondary);
    color: white;
}

.budget-table tbody tr:last-child {
    background: var(--primary);
    color: white;
    font-weight: 700;
}

Highlight box

css
.highlight-box {
    background: linear-gradient(135deg, var(--primary) 0%, var(--primary-dark) 100%);
    color: white;
    padding: 0.3in;
}

Document creation workflow

  1. Check for brand config at project-root pdf-playground.local.md, then the legacy .claude/pdf-playground.local.md fallback
  2. Locate this installed SKILL.md and resolve bundled resources from its directory. Do not assume a plugin-root environment variable is available.
  3. Load template from the skill-relative templates/ directory
  4. Apply brand settings to CSS variables and content
  5. Customize content based on user requirements
  6. Save HTML file in current working directory
  7. Offer preview with Playwright browser tools

PDF export instructions

  1. Open the HTML file in Chrome
  2. Press Ctrl+P (or Cmd+P on Mac)
  3. Set "Destination" to "Save as PDF"
  4. Set "Margins" to "None"
  5. Enable "Background graphics"
  6. Save the file

Additional resources

Templates

Pre-built templates in the installed skill's templates/ directory:

  • proposal-template.html
  • report-template.html
  • onepager-template.html
  • newsletter-template.html
  • slides-template.html
  • event-template.html

slides-template.html contains illustrative local photo and wordmark paths, not bundled image assets. Before delivering a deck based on it, replace every CSS url(...) and <img src> reference with an available asset. If the user has no suitable images, remove every unresolved reference, use the template's gradient or solid-color slide variants, and replace a missing wordmark image with text. Never deliver a deck with an unresolved local asset path.

Brand examples

Example brand configurations in the installed skill's brands/ directory:

  • default.yaml - Default brand settings
  • ccm.yaml - Center for Cooperative Media
  • example-newsroom.yaml - Sample newsroom config

Reference files

For detailed CSS patterns, use the installed skill's references/css-patterns.md.

Preview controls

Reusable preview assets are in the installed skill's controls/ directory. These files are resources for document generation; they do not turn the Claude-only preview command or plugin hook into Codex features.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Document Design AI skill do?

Creates print-ready HTML that exports to PDF. Use to make a proposal, report, one-pager, newsletter, slides, or flyer.

Why use Document Design on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/jamditis/claude-skills-journalism/tree/master/pdf-playground/skills/document-design. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Document Design?

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 Document Design?

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

Is the Document Design AI skill free?

Yes. It is published on GitHub by jamditis 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 👇