Agent skill

PDF Gen Fallback

by HKUDS in HKUDS/OpenSpace

Reliable PDF generation using shell-based Python execution when sandbox fails

MITAuto-check passedDocuments & Office

Install PDF Gen Fallback

skills CLI
$ npx skills add HKUDS/OpenSpace --skill pdf-gen-fallback -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install HKUDS/OpenSpace pdf-gen-fallback --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/HKUDS/OpenSpace.git skills-src && mkdir -p .claude/skills && cp -r skills-src/benchmarks/gdpval/skills/pdf-gen-fallback .claude/skills/pdf-gen-fallback && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
pdf-gen-fallback
GitHub stars
7.8k
Token cost
~810 tokens
SKILL.md length
259 words
Files
2
Skills in repo
199
Repo updated
First seen
Licence
MIT

At a glance

Reliable PDF generation using shell-based Python execution when sandbox fails

  • Works in 5 steps: Check Library Availability → Attempt execute_code_sandbox First → Detect Opaque Errors → …
  • Tasks that involve PDF
  • SKILL.md covers When to Use, Step-by-Step Procedure, Complete Example Workflow and Error Handling Tips, plus 2 more sections
  • Calls python

What it does

PDF Gen Fallback is an agent skill from HKUDS/OpenSpace. Reliable PDF generation using shell-based Python execution when sandbox fails

Its SKILL.md is about 810 tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file.

It sits in Documents & Office, covering PDF. It works with Python and pypdf. The repository describes itself as: "OpenSpace: The Skill Management Layer for AI Agents" -- https://open-space.cloud/. The licence is MIT.

When your agent uses it

  • Tasks that involve PDF

Example prompts

  • “/pdf-gen-fallback”

Requirements

  • Python 3

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Check Library Availability
  2. Attempt execute_code_sandbox First
  3. Detect Opaque Errors
  4. Fall Back to run_shell
  5. Verify Output

What it can do on your machine

Read from SKILL.md and the folder at commit 3827781. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • python

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

PDF Gen Fallback loads about 810 tokens when it runs. Until then it costs about 24 tokens; SKILL.md has 259 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~24
When it runs · the whole SKILL.md, loaded when a task matches
~810

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from HKUDS/OpenSpace at commit 3827781, republished under its MIT licence (© HKUDS). 259 words, ~810 tokens.

Download SKILL.mdSave it as .claude/skills/pdf-gen-fallback/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
pdf-gen-fallback
description
Reliable PDF generation using shell-based Python execution when sandbox fails

PDF Generation Fallback

This skill provides a reliable workflow for generating PDFs and documents when execute_code_sandbox returns opaque errors. Use direct run_shell with python -c as a fallback, with library availability checks and explicit error handling.

When to Use

  • execute_code_sandbox fails with cryptic error messages during document/PDF generation
  • You need to generate PDFs, reports, or structured documents
  • Standard library execution is unreliable for document creation tasks

Step-by-Step Procedure

Step 1: Check Library Availability

Before attempting generation, verify that required libraries are installed:

bash
run_shell command="python -c \"import reportlab; print('reportlab available')\""
run_shell command="python -c \"import fpdf; print('fpdf available')\""
run_shell command="python -c \"import pypdf; print('pypdf available')\""
Step 2: Attempt execute_code_sandbox First

Try the sandbox approach initially (it's cleaner for iteration):

python
execute_code_sandbox code="""
from reportlab.lib.pagesizes import letter
from reportlab.pdfgen import canvas

c = canvas.Canvas("output.pdf", pagesize=letter)
c.drawString(100, 750, "Document Content")
c.save()
print("ARTIFACT_PATH:/path/to/output.pdf")
"""
Step 3: Detect Opaque Errors

Watch for these failure indicators:

  • Generic "execution failed" messages
  • Import errors that don't match library availability checks
  • Timeout errors during document rendering
  • Missing artifact paths in output
Step 4: Fall Back to run_shell

If sandbox fails, use direct shell execution:

bash
run_shell command="python -c \"
from reportlab.lib.pagesizes import letter
from reportlab.pdfgen import canvas
c = canvas.Canvas('output.pdf', pagesize=letter)
c.drawString(100, 750, 'Document Content')
c.save()
print('PDF created successfully')
\""
Step 5: Verify Output

After generation, confirm the file exists:

bash
run_shell command="ls -la output.pdf && file output.pdf"

Complete Example Workflow

1. Check libraries: run_shell "python -c \"import reportlab\""
2. Try sandbox: execute_code_sandbox with PDF generation code
3. If error detected: Fall back to run_shell with python -c
4. Verify: run_shell "ls -la *.pdf"
5. Read result: read_file filetype="pdf" file_path="output.pdf"

Error Handling Tips

  • Capture stderr from run_shell to diagnose issues
  • Use absolute paths when possible to avoid working directory issues
  • For complex documents, write the Python script to a file first, then execute
  • Consider installing missing libraries: run_shell command="pip install reportlab"

Library Alternatives

If reportlab is unavailable, try:

  • fpdf - Simpler API, good for basic PDFs
  • weasyprint - HTML/CSS to PDF conversion
  • pypdf - PDF manipulation and merging

Common Pitfalls

  • Don't assume sandbox errors mean the approach is wrong—often it's环境 issues
  • Always verify the PDF was created before proceeding
  • Handle encoding issues explicitly (use utf-8)
  • For images in PDFs, ensure image files are accessible to the execution context

© HKUDS, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in benchmarks/gdpval/skills/pdf-gen-fallback of HKUDS/OpenSpace.

  • SKILL.md
  • .skill_id

Open the folder on GitHubat commit 3827781

Compare with similar skills

PDF Gen Fallback next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

PDF Gen Fallback compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
PDF Gen Fallback this skillHKUDS/OpenSpace7.8k—~810Automated safety check: PassMIT
PDF ToolkitXiaomiMiMo/MiMo-Code14k—~1.7kAutomated safety check: PassApache-2.0
PDF Generation, Forms and Extractionpipeshub-ai/pipeshub-ai3.8k—~2.9kAutomated safety check: PassApache-2.0
PDFNousResearch/hermes-agent252k—~3.1kAutomated safety check: PassMIT
PDF ExploreHughYau/AcademicForge2.6k—~3.1kAutomated safety check: PassApache-2.0
PDF Readerespennilsen/pi122—~1.6kAutomated safety check: PassMIT

Similar skills

  • PDF Toolkit

    XiaomiMiMo/MiMo-Code

    Reads, transforms, composes and fills PDFs with Python scripts for extraction, merging, watermarking, encryption, OCR and form filling.

    14k GitHub stars~1.7k tokensUpdated today
    Documents & OfficeAuto-check passed
  • Picks the right library for generating a new PDF, filling an existing PDF form, or extracting text and tables, defaulting to Node where possible.

    3.8k GitHub stars~2.9k tokensUpdated today
    Documents & OfficeAuto-check passed
  • PDF

    NousResearch/hermes-agent

    PDF files: create, read, merge, fill, OCR, edit text. An agent skill from NousResearch/hermes-agent.

    252k GitHub stars~3.1k tokensUpdated today
    Documents & OfficeAuto-check passed
  • PDF Explore

    HughYau/AcademicForge

    A skill your agent uses when the user has attached a PDF, paper, report, or other document and the answer needs content from more than one place in it: summarize the methods or any other section…

    2.6k GitHub stars~3.1k tokensUpdated 1 mo ago
    Documents & OfficeAuto-check passed
  • PDF Reader

    espennilsen/pi

    Read and extract content from PDF files — text, tables, metadata, and images.

    122 GitHub stars~1.6k tokensUpdated 17 days ago
    Documents & OfficeAuto-check passed
  • PDF Explore

    JimLiu/science-skills

    A skill your agent uses when the user has attached a PDF, paper, report, or other document and the answer needs content from more than one place in it: summarize the methods or any other section…

    227 GitHub starsUsed in 2 repos~3.6k tokens
    Documents & OfficeAuto-check passed

More from HKUDS/OpenSpace

All 199 skills in this repo
  • Walks through producing a master audio track plus stems in Python, from checking a reference file and timing sections by BPM to effects, a zip archive and final verification.

    7.8k GitHub stars~2.9k tokensUpdated 1 mo ago
    Auto-check passed
  • Handle cascading data retrieval tool failures by falling back to embedded knowledge generation

    7.8k GitHub stars~765 tokensUpdated 1 mo ago
    Auto-check passed
  • Gives an agent a workaround when its code-execution sandbox keeps failing: save the Python script to a file and run it through the shell instead.

    7.8k GitHub stars~588 tokensUpdated 1 mo ago
    Auto-check passed
  • A recovery routine for agents whose sandboxed code runner keeps failing: save the Python script to disk, then run it through the shell and read the output.

    7.8k GitHub stars~652 tokensUpdated 1 mo ago
    Auto-check passed
  • Fallback ladder for failed sandboxed code runs, plus the habit of fixing the working directory first so generated files land in the right place.

    7.8k GitHub stars~1.1k tokensUpdated 1 mo ago
    Auto-check passed
  • Fallback workflow for executing Python code when executecodesandbox fails repeatedly

    7.8k GitHub stars~1.1k tokensUpdated 1 mo ago
    Auto-check passed

Works with

Questions about PDF Gen Fallback

What does PDF Gen Fallback do?

Reliable PDF generation using shell-based Python execution when sandbox fails. PDF Gen Fallback is an agent skill from HKUDS/OpenSpace.

When should I use PDF Gen Fallback?

PDF Gen Fallback fits situations like: tasks that involve PDF.

How do I install PDF Gen Fallback in Claude Code?

Run `npx skills add HKUDS/OpenSpace --skill pdf-gen-fallback -a claude-code`. Or copy the skill folder (benchmarks/gdpval/skills/pdf-gen-fallback in HKUDS/OpenSpace) into .claude/skills/pdf-gen-fallback in your project. Claude Code loads it when a task matches its description.

How do I install PDF Gen Fallback in Codex?

Run `npx skills add HKUDS/OpenSpace --skill pdf-gen-fallback -a codex`. Or copy the skill folder (benchmarks/gdpval/skills/pdf-gen-fallback in HKUDS/OpenSpace) into .agents/skills/pdf-gen-fallback in your project. Codex loads it when a task matches its description.

Can I use PDF Gen Fallback in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add HKUDS/OpenSpace --skill pdf-gen-fallback -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/pdf-gen-fallback, .gemini/skills/pdf-gen-fallback, .github/skills/pdf-gen-fallback and .opencode/skills/pdf-gen-fallback in your project.

What does PDF Gen Fallback need to run?

Going by SKILL.md and its folder, PDF Gen Fallback needs the command-line tools its instructions call (python). Our summary lists: Python 3.

Does PDF Gen Fallback access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is PDF Gen Fallback safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does PDF Gen Fallback use?

PDF Gen Fallback is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does PDF Gen Fallback use?

About 810 tokens (SKILL.md is roughly 3.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to PDF Gen Fallback?

Skills that share tags, products or a category with PDF Gen Fallback: PDF Toolkit (XiaomiMiMo/MiMo-Code, 14k stars), PDF Generation, Forms and Extraction (pipeshub-ai/pipeshub-ai, 3.8k stars), PDF (NousResearch/hermes-agent, 252k stars) and PDF Explore (HughYau/AcademicForge, 2.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains PDF Gen Fallback?

HKUDS (a GitHub organization) maintains it in HKUDS/OpenSpace, which has 7,750 GitHub stars. The repository holds 199 skills in this directory. The repository was last updated on August 12, 2026.

Source: HKUDS/OpenSpace on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.