Fallback File Creation logo

Fallback File Creation

OrganizationPopular
HKUDS
fallback-file-creation

Fallback pattern for reliable file creation when code execution tools fail

Overview

PublisherHKUDS
RepositoryOpenSpace
Skill namefallback-file-creation
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 Fallback File Creation 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/fallback-file-creation .claude/skills/fallback-file-creation
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Fallback File Creation 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 Fallback File Creation 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 Fallback File Creation 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.

Fallback File Creation Workflow

Use this skill when execute_code_sandbox or shell_agent fails repeatedly for file creation tasks. This pattern provides a manual but reliable approach to create and verify files.

When to Use

  • Code execution tools fail after multiple retries
  • You need to create specific file formats (PDF, DOCX, etc.)
  • Direct shell commands are more reliable than generated scripts
  • You need explicit verification of file outputs

Step-by-Step Instructions

Step 1: Verify Working Directory

Before any file operations, confirm your current location:

bash
pwd
ls -la

This ensures you're creating files in the correct workspace directory.

Step 2: Create Scripts via Heredoc

Use shell heredocs to create scripts with properly escaped syntax:

bash
cat > /path/to/script.sh << 'EOF'
#!/bin/bash
# Your script content here
# Variables are NOT expanded inside 'EOF' (quoted)
echo "Creating file..."
# Commands to generate output
EOF

Key escaping rules:

  • Use 'EOF' (quoted) to prevent variable expansion inside the heredoc
  • Use EOF (unquoted) if you want shell variables to expand
  • Escape any $, backticks, or special characters if using unquoted EOF

Step 3: Execute with Explicit Path

Always run scripts with their full or explicit relative path:

bash
chmod +x /path/to/script.sh
/path/to/script.sh
# or
bash /path/to/script.sh

Avoid relying on . or implicit paths.

Step 4: Verify Output

After execution, verify files were created correctly:

bash
# Check file exists and size
ls -lh /path/to/output.file

# For PDFs: inspect metadata
pdfinfo /path/to/output.pdf

# For DOCX: check structure
unzip -l /path/to/output.docx | head -20

# For any file: check content preview
file /path/to/output.file
head -c 500 /path/to/output.file

Step 5: Iterative Debugging

If verification fails:

  1. Check error messages from script execution
  2. Verify all dependencies are available (which command)
  3. Test individual commands from the script manually
  4. Re-run with verbose output (bash -x script.sh)

Example: Creating a PDF Document

bash
# Step 1: Verify directory
pwd
ls -la

# Step 2: Create conversion script
cat > /workspace/create_pdf.sh << 'EOF'
#!/bin/bash
cd /workspace
libreoffice --headless --convert-to pdf checklist.odt --outdir .
EOF

# Step 3: Execute
chmod +x /workspace/create_pdf.sh
/workspace/create_pdf.sh

# Step 4: Verify
ls -lh /workspace/checklist.pdf
pdfinfo /workspace/checklist.pdf

Example: Creating a DOCX Document

bash
# Step 1: Verify directory
pwd
ls -la

# Step 2: Create document script
cat > /workspace/create_docx.sh << 'EOF'
#!/bin/bash
cd /workspace
pandoc -f markdown -t docx action_tracker.md -o action_tracker.docx
EOF

# Step 3: Execute
chmod +x /workspace/create_docx.sh
/workspace/create_docx.sh

# Step 4: Verify
ls -lh /workspace/action_tracker.docx
unzip -l /workspace/action_tracker.docx | head -20

Best Practices

  1. Always verify before and after - Check directory state before starting and after completion
  2. Use absolute or explicit paths - Avoid ambiguity in file locations
  3. Quote heredoc delimiters - Use 'EOF' to prevent unwanted variable expansion
  4. Make scripts executable - Always chmod +x before running
  5. Inspect file metadata - Use format-specific tools (pdfinfo, unzip -l, file) to verify content
  6. Keep scripts simple - Each script should do one thing well
  7. Clean up temporary files - Remove intermediate files after successful completion

Troubleshooting

IssueSolution
Script not foundUse full path: /workspace/script.sh
Permission deniedRun chmod +x script.sh
File not createdCheck script output, verify working directory in script
Wrong file formatVerify conversion tool supports target format
Corrupted outputRe-run with verbose mode, check intermediate files

Frequently asked questions

What does the Fallback File Creation AI skill do?

Fallback pattern for reliable file creation when code execution tools fail

Why use Fallback File Creation on TypingMind?

Because you install it once and use it with any model. Fallback File Creation 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 Fallback File Creation in TypingMind?

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

Which AI models can use Fallback File Creation?

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 Fallback File Creation?

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

Is the Fallback File Creation 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 👇