Export

Community

NatsuFox

export

Export knowledge base content to PDF, Markdown, or HTML files saved under _data/exports/. Use when a user wants to save or share KB content as downloadable files. Supports exporting a single document file, a single feed entry, a single note, or the entire knowledge base.

Overview

Publisher	NatsuFox
Repository	`Tapestry`
Skill name	`export`
Stars	64
Forks	5
Bundled files	1
License	MIT
Links	Skill source Repository Homepage

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.
1 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by NatsuFox on GitHub. Read the source before you install it.

Installation

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

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.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
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.

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/NatsuFox/Tapestry.git /tmp/Tapestry
mkdir -p .claude/skills
cp -r /tmp/Tapestry/skills/tapestry/export .claude/skills/export

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Export 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 Export 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 Export 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.

Tapestry Export

Export knowledge base content to portable file formats: $ARGUMENTS

When to use this skill

Use this skill when:

A user wants to export, save, download, or share knowledge base content
The user asks for a PDF, Markdown, or HTML version of a document or the whole KB
The user wants offline-readable files from the knowledge base
The user wants to share a chapter or article outside the viewer

Arguments

The argument string may contain any combination of:

format: pdf, markdown, html, or all (default: all)
scope: file, note, feed, or kb (default: kb)
target: a path or partial path to the target artifact (required for file, note, feed scopes)

Examples:

"pdf kb" — export the entire knowledge base as PDF
"html file _data/books/ai/chapter.md" — export one document as HTML
"all note _data/notes/2025/03/my-note.md" — export one note in all three formats
"markdown feed _data/feeds/2025/03/abc123.json" — export one feed entry as Markdown

Scope Resolution

Scope	Source files	Notes
`file`	Single `.md` file under `_data/books/`	Path provided by user
`note`	Single `.md` file under `_data/notes/`	Path provided by user
`feed`	Single `.json` file under `_data/feeds/`	Exports the `body` field as Markdown
`kb`	All `.md` files under `_data/books/` recursively	Entire knowledge base

Workflow

Parse the argument to determine format, scope, and target.
Change to the project root directory.
Run the export script:

bash
# Export entire KB as PDF
python export/_scripts/export.py --format pdf --scope kb

# Export entire KB in all formats
python export/_scripts/export.py --format all --scope kb

# Export a single document as HTML
python export/_scripts/export.py --format html --scope file --target _data/books/topic/chapter/doc.md

# Export a single note as Markdown
python export/_scripts/export.py --format markdown --scope note --target _data/notes/2025/03/note.md

# Export a single feed entry in all formats
python export/_scripts/export.py --format all --scope feed --target _data/feeds/2025/03/abc123.json

The script prints a JSON summary of all exported file paths to stdout.
Report the output paths back to the user.

Output Location

All exported files are saved under _data/exports/:


_data/exports/
  markdown/   ← .md files
  html/       ← standalone .html files (self-contained, with embedded images)
  pdf/        ← .pdf files (requires playwright)

File names mirror the source path structure. For example: _data/books/ai/chapter/doc.md → _data/exports/html/ai/chapter/doc.html

PDF Export Notes

PDF export uses Playwright (headless Chromium) to render the HTML to PDF. If Playwright is not installed, the script falls back to saving a self-printing HTML file (with window.onload = window.print()) and will notify the user to open it in a browser and use Print → Save as PDF.

To install Playwright:

bash
pip install playwright && playwright install chromium

Rich Text Handling

Math (KaTeX): All exported HTML files include KaTeX CDN scripts for math rendering.
Images: Images are base64-encoded and embedded inline in HTML/PDF exports for full portability.
Code blocks: Syntax-highlighted HTML is preserved from the knowledge base renderer.
Tables: Standard HTML tables are preserved.

Resources

export/_scripts/export.py: Main export script.
display/_scripts/publish_viewer.py: Provides render_markdown_document() used for HTML rendering.
_src/config.py: TapestryConfig for resolving project and data paths.

Bundled files

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

_scripts/export.py13 KB

Frequently asked questions

What does the Export AI skill do?

Why use Export on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/NatsuFox/Tapestry/tree/main/skills/tapestry/export. 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 Export?

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 Export?

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

Is the Export AI skill free?

Yes. It is published on GitHub by NatsuFox 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

Cli Anything Qgis

HKUDS

OrganizationPopular

Stateful QGIS CLI for projects, writable layers, features, layouts, exports, and qgis_process operations using the real QGIS runtime.

Cli Anything Audacity

HKUDS

OrganizationPopular

Command-line interface for Audacity - A stateful command-line interface for audio editing, following the same patterns as the GIMP and Ble...

Subagent Driven Development

obra

CommunityPopular

Use when executing implementation plans with independent tasks in the current session

Docx

Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files) or Word templates (.dotx files). Triggers include: any mention of 'Word doc', 'word document',…

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Tapestry Export

When to use this skill

Arguments

Scope Resolution

Workflow

Output Location

PDF Export Notes

Rich Text Handling

Resources

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now