Document Authoring logo

Document Authoring

OrganizationPopular
leon-ai
document-authoring

Create, inspect and deliver charts, PDFs, Word documents and spreadsheets, and open animated browser presentations.

Overview

Publisherleon-ai
Repositoryleon
Skill namedocument-authoring
Stars
17.6K
Forks
1.5K
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 leon-ai on GitHub. Read the source before you install it.

Installation

Install the Document Authoring 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/leon-ai/leon/tree/develop/skills/agent/document-authoring
  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/leon-ai/leon.git /tmp/leon
mkdir -p .claude/skills
cp -r /tmp/leon/skills/agent/document-authoring .claude/skills/document-authoring
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Document Authoring 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 Authoring 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 Authoring 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 Authoring

  1. Establish the requested format, audience, content and acceptance criteria from the brief and supplied references. Reuse source material; for complex work, track criteria and verification evidence in plan details.
  2. Choose the creation tool based on the requested output:
    • Charts: use document.echarts.render with one named entry per requested chart and native ECharts JSON options. Ground the values in supplied/retrieved data, label units, and select only the requested image formats. Each chart becomes a separate SVG/PNG artifact. Use both formats when a vector document figure and raster preview are useful. Inspect a PNG preview and fix clipping or misleading axes before delivering it. Do not use image-generation models to invent or redraw quantitative charts.
    • Presentations: use document.slidev.create for an editable project, author slides.md and style.css with the file tool, and place selected chart/image assets in public/. Treat the scaffold as editable: owner choices for theme, layout, colors, typography, icons and animation override all defaults. Replace scaffold styles and components when needed; ensure additional themes have compatible installed dependencies. Use local Lucide icons and coherent cover/section/content layouts. Default to fully visible slides and a simple transition: fade between them. Animate mechanisms inside the slide automatically while it is active: moving evidence along a flow, state changes, process cycles or grounded chart evolution. Use CSS or v-motion with a static reduced-motion fallback. Avoid generic text/panel entrance and exit effects. Add click-triggered reveals (v-click or click motion variants) and elaborate slide transitions only when the owner explicitly requests them. Ground technical claims in retrieved context/source and label illustrative data. Batch independent grounding reads and author related files together. Use fenced code or HTML-escaped <pre v-pre><code> for literal examples; keep Vue markup balanced. Run inspect, then check; during repairs select affected options.slides. Targeted success has complete=false and cannot establish full-deck coverage. Run the default full check on the final source and require scope=full, complete=true and ok=true. Batch independent checks/previews and requested exports once source is stable; never edit files while those operations are reading them. Reuse current-run evidence and successful results while relevant source/assets are unchanged. Preview early/late motion frames and, only for requested staged reveals, initial/final click states; a passing check alone does not establish visual or animation quality. Finish with present to start/reuse a managed native Slidev server and open the deck in the host’s default browser. Return its audience and presenter links, Space/Right/Left navigation and f fullscreen control. Verify opening with the browser tool; if browserOpened=false, explain the reported issue and host-local URL scope. Use Satellite for device-side presentation when Leon runs remotely and ensure the project is on that device. Keep the session until the owner finishes, then stop its sessionId. Export web/PDF/PNG/PPTX downloads only when requested; opening a deck should not require extracting files or running commands. A web ZIP includes serve.mjs: extract and run node serve.mjs, then open its localhost URL; it can also be hosted as a static site. PDF/PNG and PowerPoint exports capture states rather than native browser motion. Normal PPTX contains slide images; editable PPTX may rasterize complex elements and needs fidelity review. Shared web decks omit notes by default; an optional source ZIP (includeSource=true) always contains them; omit that archive unless requested.
    • PDF: write a local .typ source with the file tool, then call document.typst.compile. Keep the source and selected assets together in a project directory. Use the smallest rootPath containing that project. Built-in/local assets require no generation-provider account or package download.
    • Editable Word: use document.document.create with format=docx. Typst does not export DOCX.
    • SVG/PNG: compile Typst with the requested format. Each selected page becomes an image artifact. For a standalone figure, set the page dimensions to fit the figure rather than exporting a full report page.
    • Plain text, CSV, Markdown and source files: use existing file writing.
    • Hosted generation or Office formats requiring a provider: inspect document.document.capabilities, then use generate with the configured defaults. Reserve generateWithModel for an explicitly owner-requested provider/model.

If hosted generation returns selection_required, ask the owner to select a provider or use local Typst/DOCX creation when it satisfies the request. Save a choice with configure only if asked to remember it.

  1. Use readable typography, consistent headings and generous spacing. Typst source supports tables, lists, equations, references and figures; use these instead of flattening everything into paragraphs. Generate chart assets with echarts.render or reuse supplied SVG/PNG assets. For PDFs, copy selected assets into the Typst project with the shell tool, embed them with image inside figure, and add a useful caption. For DOCX, pass each selected absolute artifact path in content.sections[].images with caption and altText; the writer preserves proportions and includes PNG fallbacks for SVG. Images follow the section's paragraphs, so use separate sections to position figures between text blocks. Keep chart values grounded in supplied or retrieved data. Use typst.listFonts before choosing multilingual fonts, and provide local fontPaths when needed. Inspect compiler diagnostics and fix unknown fonts or layout warnings; do not silently produce missing glyphs. Preview-package imports may download missing packages, so avoid them for offline work.
  2. Inspect final content against the sources and acceptance criteria. Render PDF pages with readPdf and compare layout with supplied references. For Word/Office files use an available renderer to inspect a PDF export; disclose when only structural/content checks were possible.
  3. Reconcile criteria with observed evidence and fix missing content or layout defects before delivery. Source or asset changes invalidate affected checks. A provider's success response alone is not a quality check; unresolved or unverified requirements remain incomplete.
  4. Generated files already have artifact references. For existing files use file_system.file.attach. Do not duplicate attachments, paste base64, or use server-local file markers as downloads.

Frequently asked questions

What does the Document Authoring AI skill do?

Create, inspect and deliver charts, PDFs, Word documents and spreadsheets, and open animated browser presentations.

Why use Document Authoring on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/leon-ai/leon/tree/develop/skills/agent/document-authoring. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Document Authoring?

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 Authoring?

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

Is the Document Authoring AI skill free?

Yes. It is published on GitHub by leon-ai 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 👇