New: 97,000+ 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

Python Shell Fallback

by HKUDS in HKUDS/OpenSpace

Fallback to shell execution when sandbox fails for library-dependent Python code

MITAuto-check passed

Install Python Shell Fallback

skills CLI
$ npx skills add HKUDS/OpenSpace --skill python-shell-fallback -a claude-code

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

GitHub CLI
$ gh skill install HKUDS/OpenSpace python-shell-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/python-shell-fallback .claude/skills/python-shell-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
python-shell-fallback
GitHub stars
7.7k
Token cost
~745 tokens
SKILL.md length
261 words
Files
2
Skills in repo
199
Repo updated
First seen
Licence
MIT

At a glance

Fallback to shell execution when sandbox fails for library-dependent Python code

  • Works in 3 steps: Identify the Failure → Convert to Shell Execution → Execute via run_shell
  • SKILL.md covers When to Use This Pattern, How to Implement, Example: PDF Generation Fallback and Best Practices, plus 2 more sections
  • Calls python3 and pip3

What it does

Python Shell Fallback is an agent skill from HKUDS/OpenSpace. Fallback to shell execution when sandbox fails for library-dependent Python code

Its SKILL.md is about 750 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

  • “/python-shell-fallback”

Requirements

  • Python 3

Workflow steps

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

  1. Identify the Failure
  2. Convert to Shell Execution
  3. Execute via run_shell

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:

    • python3
    • pip3

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

  • Network

    No URLs in SKILL.md. Its commands use pip3, which can reach the network depending on how they are called.

    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

Python Shell Fallback loads about 745 tokens when it runs. Until then it costs about 26 tokens; SKILL.md has 261 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~26
When it runs · the whole SKILL.md, loaded when a task matches
~745

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). 261 words, ~745 tokens.

Download SKILL.mdSave it as .claude/skills/python-shell-fallback/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
python-shell-fallback
description
Fallback to shell execution when sandbox fails for library-dependent Python code

Python Shell Fallback

When execute_code_sandbox fails for Python code that depends on external libraries, use run_shell with a heredoc Python script as a reliable fallback. The shell environment typically has better access to installed packages and system configuration than the sandbox.

When to Use This Pattern

Apply this skill when:

  • execute_code_sandbox returns errors related to missing libraries (e.g., ModuleNotFoundError)
  • The code requires packages that may not be installed in the sandbox environment
  • You need PDF generation, data visualization, or other library-heavy operations
  • Previous sandbox execution attempts have failed with import errors

How to Implement

Step 1: Identify the Failure

Check if the sandbox error indicates a library/dependency issue:

  • ModuleNotFoundError: No module named 'xxx'
  • ImportError: cannot import name 'xxx'
  • Similar package-related errors
Step 2: Convert to Shell Execution

Rewrite the code execution using run_shell with a heredoc:

bash
python3 << 'EOF'
# Your Python code here
import library_name
# ... rest of code
EOF
Step 3: Execute via run_shell

Call run_shell with the heredoc Python script:

command: python3 << 'EOF'
import reportlab
from reportlab.lib.pagesizes import letter
from reportlab.pdfgen import canvas

# Your library-dependent code here
c = canvas.Canvas("output.pdf", pagesize=letter)
c.drawString(100, 750, "Hello World")
c.save()
EOF

Example: PDF Generation Fallback

Sandbox attempt (fails):

python
# execute_code_sandbox call fails with:
# ModuleNotFoundError: No module named 'reportlab'

Shell fallback (works):

bash
python3 << 'EOF'
from reportlab.lib.pagesizes import letter
from reportlab.pdfgen import canvas

c = canvas.Canvas("legal_memo.pdf", pagesize=letter)
c.setTitle("Legal Memorandum")
c.drawString(100, 750, "CONFIDENTIAL LEGAL MEMORANDUM")
c.save()
print("PDF created successfully")
EOF

Best Practices

  1. Use quoted heredoc (<< 'EOF') - Prevents variable expansion, keeping Python code intact
  2. Verify output - Check stdout/stderr from run_shell to confirm success
  3. Handle file paths - Ensure output files are written to accessible directories
  4. Test incrementally - For complex scripts, test in smaller chunks first
  5. Include error handling - Add try/except blocks to capture issues gracefully

Alternative: Inline Python Command

For simple one-liners or short scripts:

bash
python3 -c "import reportlab; print(reportlab.__version__)"

Troubleshooting

If shell execution also fails:

  • Check if Python3 is available: which python3
  • Verify package installation: pip3 list | grep package_name
  • Try python instead of python3 (some systems differ)
  • Consider installing the package: pip3 install package_name

© 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/python-shell-fallback of HKUDS/OpenSpace.

  • SKILL.md
  • .skill_id

Open the folder on GitHubat commit 3827781

Compare with similar skills

Python Shell 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.

Python Shell Fallback compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Python Shell Fallback this skillHKUDS/OpenSpace7.7k—~745Automated safety check: PassMIT
MCP Server Builderanthropics/skills180k62 repos~2.3kAutomated safety check: PassApache-2.0
PDF Processinganthropics/skills180k48 repos~2kAutomated safety check: PassProprietary
NotebookLM Research AssistantPleasePrompto/notebooklm-skill7.8k13 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 62 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 13 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.

    7.7k 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

    7.7k 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.

    7.7k 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.

    7.7k 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.

    7.7k 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

    7.7k GitHub stars~1.1k tokensUpdated 1 mo ago
    Auto-check passed

Works with

Questions about Python Shell Fallback

What does Python Shell Fallback do?

Fallback to shell execution when sandbox fails for library-dependent Python code. Python Shell Fallback is an agent skill from HKUDS/OpenSpace.

How do I install Python Shell Fallback in Claude Code?

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

How do I install Python Shell Fallback in Codex?

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

Can I use Python Shell 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 python-shell-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/python-shell-fallback, .gemini/skills/python-shell-fallback, .github/skills/python-shell-fallback and .opencode/skills/python-shell-fallback in your project.

What does Python Shell Fallback need to run?

Going by SKILL.md and its folder, Python Shell Fallback needs the command-line tools its instructions call (python3 and pip3). Our summary lists: Python 3.

Does Python Shell 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 Python Shell 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 Python Shell Fallback use?

Python Shell 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 Python Shell Fallback use?

About 745 tokens (SKILL.md is roughly 3k 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 Python Shell Fallback?

Skills that share tags, products or a category with Python Shell Fallback: 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 Python Shell Fallback?

HKUDS (a GitHub organization) maintains it in HKUDS/OpenSpace, which has 7,743 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.