Pdf Engine Fallback logo

Pdf Engine Fallback

OrganizationPopular
HKUDS
pdf-engine-fallback

Retry PDF generation with alternative engines when pandoc fails

Overview

PublisherHKUDS
RepositoryOpenSpace
Skill namepdf-engine-fallback
Stars
7.8K
Forks
923
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 HKUDS on GitHub. Read the source before you install it.

Installation

Install the Pdf Engine Fallback 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/HKUDS/OpenSpace/tree/main/benchmarks/gdpval/skills/pdf-engine-fallback
  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/HKUDS/OpenSpace.git /tmp/OpenSpace
mkdir -p .claude/skills
cp -r /tmp/OpenSpace/benchmarks/gdpval/skills/pdf-engine-fallback .claude/skills/pdf-engine-fallback
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Pdf Engine Fallback 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 Pdf Engine Fallback 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 Pdf Engine Fallback 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.

PDF Engine Fallback

This skill provides a diagnostic-retry workflow for PDF generation when Pandoc's default PDF engine fails. It systematically checks available engines and retries with alternatives optimized for different content types (e.g., xelatex for Unicode).

When to Use

  • Pandoc PDF generation fails with errors
  • Document contains non-ASCII characters (Unicode, CJK, etc.)
  • Need robust PDF generation across different system configurations
  • Working in CI/CD or automated document pipelines

Steps

1. Attempt Initial PDF Generation

First, try generating with pandoc's default engine:

bash
pandoc input.md -o output.pdf

2. Diagnose on Failure

If the initial attempt fails, check which PDF engines are available:

bash
# Check for pdflatex
which pdflatex && echo "pdflatex: available" || echo "pdflatex: not found"

# Check for xelatex (better Unicode support)
which xelatex && echo "xelatex: available" || echo "xelatex: not found"

# Check for wkhtmltopdf (HTML-based rendering)
which wkhtmltopdf && echo "wkhtmltopdf: available" || echo "wkhtmltopdf: not found"

3. Retry with Alternative Engine

Based on available engines and document content, retry with an appropriate engine:

bash
# For documents with Unicode/special characters - prefer xelatex
pandoc input.md -o output.pdf --pdf-engine=xelatex

# Alternative: use pdflatex for simple Latin documents
pandoc input.md -o output.pdf --pdf-engine=pdflatex

# For HTML-heavy content or complex layouts
pandoc input.md -o output.pdf --pdf-engine=wkhtmltopdf

4. Handle Missing Engines

If no PDF engines are available, install one:

bash
# Ubuntu/Debian - install texlive with xelatex
sudo apt-get install texlive-xetex

# Or install minimal teTeX
sudo apt-get install texlive-latex-base texlive-latex-extra

# macOS with Homebrew
brew install basictex

Complete Fallback Script

bash
#!/bin/bash
# pdf-fallback.sh - Robust PDF generation with engine fallback

INPUT_FILE="${1:-input.md}"
OUTPUT_FILE="${2:-output.pdf}"

echo "Attempting PDF generation: $INPUT_FILE -> $OUTPUT_FILE"

# Try default engine first
if pandoc "$INPUT_FILE" -o "$OUTPUT_FILE" 2>/dev/null; then
    echo "SUCCESS: PDF generated with default engine"
    exit 0
fi

echo "Default engine failed. Checking available engines..."

# Check and try engines in priority order
if command -v xelatex &>/dev/null; then
    echo "Retrying with xelatex (Unicode support)..."
    if pandoc "$INPUT_FILE" -o "$OUTPUT_FILE" --pdf-engine=xelatex; then
        echo "SUCCESS: PDF generated with xelatex"
        exit 0
    fi
fi

if command -v pdflatex &>/dev/null; then
    echo "Retrying with pdflatex..."
    if pandoc "$INPUT_FILE" -o "$OUTPUT_FILE" --pdf-engine=pdflatex; then
        echo "SUCCESS: PDF generated with pdflatex"
        exit 0
    fi
fi

if command -v wkhtmltopdf &>/dev/null; then
    echo "Retrying with wkhtmltopdf..."
    if pandoc "$INPUT_FILE" -o "$OUTPUT_FILE" --pdf-engine=wkhtmltopdf; then
        echo "SUCCESS: PDF generated with wkhtmltopdf"
        exit 0
    fi
fi

echo "FAILURE: No available PDF engine succeeded"
echo "Install a PDF engine (texlive-xetex recommended) and retry"
exit 1

Usage

bash
# Make executable
chmod +x pdf-fallback.sh

# Run with defaults (input.md -> output.pdf)
./pdf-fallback.sh

# Run with custom files
./pdf-fallback.sh report.md report.pdf

Engine Selection Guide

EngineBest ForUnicodeSpeed
xelatexNon-Latin scripts, modern fontsExcellentModerate
pdflatexSimple Latin documentsLimitedFast
wkhtmltopdfHTML/CSS stylingGoodFast

Troubleshooting

  • Font errors: Install required fonts or use xelatex with system fonts
  • Package errors: Install missing LaTeX packages via tlmgr
  • Large documents: Try pdflatex for speed, xelatex for compatibility
  • Citation issues: Ensure pandoc-citeproc or citeproc is installed

Frequently asked questions

What does the Pdf Engine Fallback AI skill do?

Retry PDF generation with alternative engines when pandoc fails

Why use Pdf Engine Fallback on TypingMind?

Because you install it once and use it with any model. Pdf Engine Fallback 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 Pdf Engine Fallback in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/HKUDS/OpenSpace/tree/main/benchmarks/gdpval/skills/pdf-engine-fallback. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Pdf Engine Fallback?

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 Pdf Engine Fallback?

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

Is the Pdf Engine Fallback AI skill free?

Yes. It is published on GitHub by HKUDS 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 👇