Document Gen Fallback logo

Document Gen Fallback

OrganizationPopular
HKUDS
document-gen-fallback

Fallback workflow for multi-format document generation when shell_agent encounters errors

Overview

PublisherHKUDS
RepositoryOpenSpace
Skill namedocument-gen-fallback
Stars
7.7K
Forks
918
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 Document Gen 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.
  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/document-gen-fallback .claude/skills/document-gen-fallback
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Document Gen 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 Document Gen 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 Document Gen 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.

Document Generation Fallback Workflow

When to Use

Use this skill when shell_agent returns unknown or unclear errors on complex document generation tasks, especially when:

  • Generating documents in multiple formats (e.g., .docx, .pdf, .html)
  • The error message doesn't provide clear debugging information
  • You need better visibility into each step of the generation process

Core Technique

Instead of delegating the entire document generation to shell_agent, manually split the workflow into discrete, observable steps:

  1. Content creation → Use write_file to create source document (Markdown)
  2. Format conversion → Use run_shell with pandoc for each target format
  3. Verification → Check output files exist and are valid

Step-by-Step Workflow

Step 1: Create Source Content with write_file

Write your document content as Markdown to a temporary source file. This gives you full visibility into the content being generated.

write_file
path: /tmp/document_source.md
content: |
  # Document Title
  
  ## Section 1
  Content here...
  
  ## Section 2
  More content...

Step 2: Convert to Target Formats with run_shell

Use run_shell with explicit pandoc commands for each format. This isolates conversion errors.

run_shell
command: pandoc /tmp/document_source.md -o output.docx
run_shell
command: pandoc /tmp/document_source.md -o output.pdf

Step 3: Verify Outputs

Check that files were created successfully:

run_shell
command: ls -lh output.docx output.pdf

Complete Example

markdown
# Generate Negotiation Strategy Document

## Step 1: Write Markdown source
write_file
path: /tmp/negotiation_strategy.md
content: |
  # Negotiation Strategy
  
  ## Executive Summary
  [Content...]
  
  ## Resolution Path
  [Content...]
  
  ## BATNA Analysis
  [Content...]

## Step 2: Convert to DOCX
run_shell
command: pandoc /tmp/negotiation_strategy.md -o negotiation_strategy.docx

## Step 3: Convert to PDF
run_shell
command: pandoc /tmp/negotiation_strategy.md -o negotiation_strategy.pdf

## Step 4: Verify
run_shell
command: ls -lh negotiation_strategy.*

Advantages Over shell_agent

Aspectshell_agentManual Workflow
Error visibilityOpaque, may retry silentlyEach step shows explicit output
RecoveryAutomatic but may loopManual intervention at specific step
DebuggingHard to isolate failure pointClear which step failed
ControlAgent decides approachYou control each conversion

Common pandoc Commands

bash
# Markdown to Word
pandoc input.md -o output.docx

# Markdown to PDF (requires LaTeX or wkhtmltopdf)
pandoc input.md -o output.pdf

# Markdown to HTML
pandoc input.md -o output.html

# With custom template
pandoc input.md --template=template.html -o output.html

# With metadata
pandoc input.md -o output.pdf --metadata title="Document Title"

Troubleshooting

  • PDF generation fails: Ensure LaTeX is installed (texlive package) or use --pdf-engine=wkhtmltopdf
  • DOCX formatting issues: Add --reference-doc=template.docx for custom styles
  • Unicode/encoding errors: Add -f markdown+utf8 to pandoc command
  • Missing pandoc: Install via apt-get install pandoc or brew install pandoc

When to Return to shell_agent

After successfully completing the manual workflow once, you can attempt shell_agent again for similar tasks, now with a known-working fallback if errors recur.

Frequently asked questions

What does the Document Gen Fallback AI skill do?

Fallback workflow for multi-format document generation when shell_agent encounters errors

Why use Document Gen Fallback on TypingMind?

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

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

Which AI models can use Document Gen 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 Document Gen Fallback?

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

Is the Document Gen 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 👇