New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Sandbox Fallback Execution 5eda7b

by HKUDS in HKUDS/OpenSpace

Fallback pattern for executing Python code when sandbox execution fails by writing scripts to disk and running via shell

MITAuto-check passed

Install Sandbox Fallback Execution 5eda7b

skills CLI
$ npx skills add HKUDS/OpenSpace --skill sandbox-fallback-execution-5eda7b -a claude-code

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

GitHub CLI
$ gh skill install HKUDS/OpenSpace sandbox-fallback-execution-5eda7b --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/sandbox-fallback-execution-5eda7b .claude/skills/sandbox-fallback-execution-5eda7b && 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
sandbox-fallback-execution-5eda7b
GitHub stars
7.8k
Token cost
~939 tokens
SKILL.md length
272 words
Files
2
Skills in repo
199
Repo updated
First seen
Licence
MIT

At a glance

Fallback pattern for executing Python code when sandbox execution fails by writing scripts to disk and running via shell

  • Works in 5 steps: Attempt Sandbox Execution First → Detect Failure and Switch to Fallback → Example Implementation → …
  • SKILL.md covers Overview, When to Use, Step-by-Step Instructions and Best Practices, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Sandbox Fallback Execution 5eda7b is an agent skill from HKUDS/OpenSpace. Fallback pattern for executing Python code when sandbox execution fails by writing scripts to disk and running via shell

Its SKILL.md is about 940 tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file.

It works with Python. The repository describes itself as: "OpenSpace: The Skill Management Layer for AI Agents" -- https://open-space.cloud/. The licence is MIT.

Example prompts

  • “/sandbox-fallback-execution-5eda7b”

Requirements

  • Python 3

Workflow steps

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

  1. Attempt Sandbox Execution First
  2. Detect Failure and Switch to Fallback
  3. Example Implementation
  4. Handle Dependencies
  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

    No scripts in the folder and no shell commands in SKILL.md (its code samples are 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

Sandbox Fallback Execution 5eda7b loads about 939 tokens when it runs. Until then it costs about 39 tokens; SKILL.md has 272 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~39
When it runs · the whole SKILL.md, loaded when a task matches
~939

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). 272 words, ~939 tokens.

Download SKILL.mdSave it as .claude/skills/sandbox-fallback-execution-5eda7b/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
sandbox-fallback-execution-5eda7b
description
Fallback pattern for executing Python code when sandbox execution fails by writing scripts to disk and running via shell

Sandbox Fallback Execution

Overview

When execute_code_sandbox fails due to e2b initialization errors or sandbox unavailability, use this fallback pattern to execute Python code by writing it to disk and running it via run_shell. This approach is particularly useful for PDF generation, data processing, and other Python-intensive tasks.

When to Use

Use this skill when you encounter errors like:

  • e2b initialization error
  • sandbox not available
  • execute_code_sandbox timeout or connection failures
  • Any sandbox execution that consistently fails

Step-by-Step Instructions

Step 1: Attempt Sandbox Execution First

Always try execute_code_sandbox first, as it provides isolation and artifact handling:

python
execute_code_sandbox(code="your_python_code_here")
Step 2: Detect Failure and Switch to Fallback

When sandbox execution fails with initialization errors, switch to the fallback pattern:

  1. Write the Python script to disk using write_file:

    • Choose a descriptive filename (e.g., generate_pdf.py, process_data.py)
    • Include the complete Python code with all necessary imports

  2. Execute via shell using run_shell:

    • Run the script with python or python3
    • Capture stdout/stderr for verification
Step 3: Example Implementation
python
# Write the script to disk
write_file(
    path="generate_pdf.py",
    content="""
from reportlab.lib.pagesizes import letter
from reportlab.pdfgen import canvas

def create_pdf(filename, content):
    c = canvas.Canvas(filename, pagesize=letter)
    c.drawString(100, 750, content)
    c.save()

create_pdf('output.pdf', 'Hello World')
"""
)

# Execute the script via shell
run_shell(command="python generate_pdf.py")
Step 4: Handle Dependencies

If the script requires external packages:

python
# Install dependencies first
run_shell(command="pip install reportlab pillow")

# Then execute the script
run_shell(command="python generate_pdf.py")
Step 5: Verify Output

After execution, verify the output was created:

python
# Check if file was created
run_shell(command="ls -la output.pdf")

# Optionally read the file to confirm
read_file(file_path="output.pdf", filetype="pdf")

Best Practices

  1. Keep scripts self-contained: Include all imports and logic in the written file
  2. Use descriptive filenames: Make it clear what each script does
  3. Clean up when done: Remove temporary scripts if not needed for debugging
  4. Capture errors: Always check stdout/stderr from run_shell for debugging
  5. Handle paths carefully: Use relative paths or absolute paths consistently

Complete Example Pattern

python
# Primary: Try sandbox execution
try:
    result = execute_code_sandbox(code=python_code)
except Exception as e:
    if "e2b" in str(e).lower() or "sandbox" in str(e).lower():
        # Fallback: Write to disk and execute via shell
        script_path = "task_script.py"
        
        write_file(
            path=script_path,
            content=python_code
        )
        
        # Install any required dependencies
        run_shell(command="pip install -q reportlab")
        
        # Execute the script
        result = run_shell(command=f"python {script_path}")
        
        # Verify output
        run_shell(command="ls -la")

Applicable Use Cases

  • PDF generation (reportlab, fpdf, etc.)
  • Image processing (PIL, OpenCV)
  • Data analysis (pandas, numpy)
  • File manipulation tasks
  • Any Python script that doesn't require special sandbox features

© 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/sandbox-fallback-execution-5eda7b of HKUDS/OpenSpace.

  • SKILL.md
  • .skill_id

Open the folder on GitHubat commit 3827781

Compare with similar skills

Sandbox Fallback Execution 5eda7b 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.

Sandbox Fallback Execution 5eda7b compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Sandbox Fallback Execution 5eda7b this skillHKUDS/OpenSpace7.8k—~939Automated safety check: PassMIT
MCP Server Builderanthropics/skills180k63 repos~2.3kAutomated safety check: PassApache-2.0
PDF Processinganthropics/skills180k48 repos~2kAutomated safety check: PassProprietary
NotebookLM Research AssistantPleasePrompto/notebooklm-skill7.8k14 repos~2.4kAutomated safety check: NotesMIT
Manim Video Productionbrowser-use/video-use28k6 repos~3kAutomated safety check: PassMIT
Code Review ChecklistshareAI-lab/learn-claude-code78k5 repos~1.1kAutomated safety check: PassMIT

Similar skills

  • MCP Server Builder

    anthropics/skills

    Official

    Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.

    180k GitHub starsUsed in 63 repos~2.3k tokens
    Agent WorkflowsAuto-check passed

  • PDF Processing

    anthropics/skills

    Official

    Handles everyday PDF jobs in Python and on the command line: extract text and tables, merge, split, rotate, watermark, fill forms, encrypt and OCR.

    180k GitHub starsUsed in 48 repos~2k tokens
    Documents & OfficeAuto-check passed

  • NotebookLM Research Assistant

    PleasePrompto/notebooklm-skill

    Lets Claude Code ask questions of your Google NotebookLM notebooks through browser automation and return answers grounded in your uploaded sources.

    7.8k GitHub starsUsed in 14 repos~2.4k tokens
    Knowledge ManagementAuto-check: notes

  • Manim Video Production

    browser-use/video-use

    Produces math and technical explainer videos with Manim Community Edition: concept animations, equation derivations, algorithm walkthroughs and data stories.

    28k GitHub starsUsed in 6 repos~3k tokens
    Media & CreativeAuto-check passed

  • Code Review Checklist

    shareAI-lab/learn-claude-code

    Reviews code against a five-part checklist covering security, correctness, performance, maintainability and testing, and reports findings in a fixed format.

    78k GitHub starsUsed in 5 repos~1.1k tokens
    DevelopmentAuto-check passed

  • PPT Master

    hugohe3/ppt-master

    Generates editable PowerPoint decks, rebuilds slides from images, fills .pptx templates and polishes existing presentations through routed workflows.

    58k GitHub starsUsed in 1 repo~2.5k tokens
    Documents & OfficeAuto-check passed

More from HKUDS/OpenSpace

All 199 skills in this repo

  • Audio Track Production Workflow

    HKUDS/OpenSpace

    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

  • Cascade Failure Recovery

    HKUDS/OpenSpace

    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

  • Sandbox Code Execution Fallback

    HKUDS/OpenSpace

    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

  • Code Execution Fallback

    HKUDS/OpenSpace

    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

  • Code Execution Fallback and Path Anchoring

    HKUDS/OpenSpace

    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

  • Code Execution Fallback E81068

    HKUDS/OpenSpace

    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 Sandbox Fallback Execution 5eda7b

What does Sandbox Fallback Execution 5eda7b do?

Fallback pattern for executing Python code when sandbox execution fails by writing scripts to disk and running via shell. Sandbox Fallback Execution 5eda7b is an agent skill from HKUDS/OpenSpace.

How do I install Sandbox Fallback Execution 5eda7b in Claude Code?

Run `npx skills add HKUDS/OpenSpace --skill sandbox-fallback-execution-5eda7b -a claude-code`. Or copy the skill folder (benchmarks/gdpval/skills/sandbox-fallback-execution-5eda7b in HKUDS/OpenSpace) into .claude/skills/sandbox-fallback-execution-5eda7b in your project. Claude Code loads it when a task matches its description.

How do I install Sandbox Fallback Execution 5eda7b in Codex?

Run `npx skills add HKUDS/OpenSpace --skill sandbox-fallback-execution-5eda7b -a codex`. Or copy the skill folder (benchmarks/gdpval/skills/sandbox-fallback-execution-5eda7b in HKUDS/OpenSpace) into .agents/skills/sandbox-fallback-execution-5eda7b in your project. Codex loads it when a task matches its description.

Can I use Sandbox Fallback Execution 5eda7b 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 sandbox-fallback-execution-5eda7b -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/sandbox-fallback-execution-5eda7b, .gemini/skills/sandbox-fallback-execution-5eda7b, .github/skills/sandbox-fallback-execution-5eda7b and .opencode/skills/sandbox-fallback-execution-5eda7b in your project.

What does Sandbox Fallback Execution 5eda7b need to run?

SKILL.md names no scripts, command-line tools or credentials: Sandbox Fallback Execution 5eda7b is instructions for the agent only. Our summary lists: Python 3.

Does Sandbox Fallback Execution 5eda7b 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 Sandbox Fallback Execution 5eda7b 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 Sandbox Fallback Execution 5eda7b use?

Sandbox Fallback Execution 5eda7b 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 Sandbox Fallback Execution 5eda7b use?

About 939 tokens (SKILL.md is roughly 3.8k 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 Sandbox Fallback Execution 5eda7b?

Skills that share tags, products or a category with Sandbox Fallback Execution 5eda7b: MCP Server Builder (anthropics/skills, 180k stars), PDF Processing (anthropics/skills, 180k stars), NotebookLM Research Assistant (PleasePrompto/notebooklm-skill, 7.8k stars) and Manim Video Production (browser-use/video-use, 28k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Sandbox Fallback Execution 5eda7b?

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.