Skip to content
cccskills
FreePublished on GitHub

python-heredoc-fallback

Run Python through the shell when a code sandbox fails to start or connect. Uses a heredoc, a way to pass multiline code, with examples for generating charts, Word documents, and processed JSON files.

OriginalShow the original description

Use shell Python heredoc as fallback when code sandbox fails

Works withWord
See how to install

Good for

  • Continue Python work when the code sandbox is unavailable
  • Create a graph image from Excel data
  • Generate a Word document with headings and a table
  • Read, process, and save JSON data

Files included (2)

  • SKILL.md3.4 KB
  • .skill_id37 B

SKILL.md (original)

Review the instructions the agent will receive before you install.

Python Heredoc Fallback for Code Execution

When to Use

Use this pattern when execute_code_sandbox fails with e2b initialization errors, sandbox connection issues, or other execution environment problems. This is especially reliable for file generation tasks.

Core Pattern

Instead of execute_code_sandbox, run Python code directly in the shell using a heredoc:

python3 << 'EOF'
# Your Python code here
import sys
print("Python code executing in shell")
EOF

Key Syntax Rules

  1. Use single-quoted EOF (<< 'EOF') to prevent shell variable expansion within the Python code
  2. No indentation before EOF - the closing delimiter must be at the start of the line
  3. Install packages first if needed, before the Python heredoc block

Common Use Cases

1. Matplotlib Graph Generation

python3 << 'EOF'
import matplotlib.pyplot as plt
import pandas as pd

# Load data
data = pd.read_excel('input.xlsx')

# Create visualization
plt.figure(figsize=(10, 6))
plt.plot(data['x'], data['y'])
plt.xlabel('X Label')
plt.ylabel('Y Label')
plt.title('Graph Title')
plt.savefig('output_graph.png', dpi=300, bbox_inches='tight')
plt.close()

print("Graph saved successfully")
EOF

2. Python-docx Document Creation

pip install python-docx -q

python3 << 'EOF'
from docx import Document
from docx.shared import Inches, Pt
from docx.enum.text import WD_ALIGN_PARAGRAPH

doc = Document()

# Add title
title = doc.add_heading('Document Title', 0)
title.alignment = WD_ALIGN_PARAGRAPH.CENTER

# Add sections
doc.add_heading('Section 1', level=1)
doc.add_paragraph('Content for section 1.')

# Add table
table = doc.add_table(rows=3, cols=3)
table.style = 'Table Grid'

# Save document
doc.save('output.docx')
print("Document created successfully")
EOF

3. General File Operations

python3 << 'EOF'
import json
import os

# Read input file
with open('input.json', 'r') as f:
    data = json.load(f)

# Process data
result = {'processed': True, 'items': len(data)}

# Write output
with open('output.json', 'w') as f:
    json.dump(result, f, indent=2)

print(f"Processed {result['items']} items")
EOF

Best Practices

  1. Install dependencies first: Run pip install package-name -q before the Python block if packages aren't guaranteed to be available
  2. Verify file paths: Files are read from and written to the current working directory
  3. Add print statements: Include progress/output messages to verify execution succeeded
  4. Close resources: Explicitly close matplotlib figures and file handles
  5. Handle errors gracefully: Add try/except blocks for production code

Troubleshooting

IssueSolution
Module not foundAdd pip install <module> -q before Python block
File not foundVerify file exists in current directory with ls
Permission deniedCheck file permissions and directory write access
Syntax errorsEnsure proper Python indentation within heredoc

Advantages Over execute_code_sandbox

  • No initialization overhead - runs immediately in existing shell
  • Persistent environment - maintains state across multiple commands
  • Direct file system access - no sandbox isolation issues
  • Full system Python - access to all installed packages
  • Reliable for large files - no sandbox size restrictions

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

Prepare audio stems, the separate parts of a track, for mixing by matching their durations with silence, loops, or crossfades. Verify each generated and processed file before moving to the next production step.

  • Match audio parts with different durations
  • Extend drums and melodic parts using suitable methods
  • Check audio specifications before mixing
HKUDS/OpenSpace7.8KUpdated Aug 13, 2026

Produce audio in separate stems, meaning individual instrument tracks, and verify each output as you go. Align track lengths with silence, loops, or crossfades, then apply effects, mix a master, and package the files.

  • Align instrument tracks to a reference audio file
  • Choose how to extend tracks that are too short
  • Verify audio properties after generation and effects
HKUDS/OpenSpace7.8KUpdated Aug 13, 2026

Build serverless endpoints that relay external API requests for a dashboard while keeping API keys on the server. Includes Vercel examples for input checks, caching, cross-origin access, and consistent JSON responses.

  • Connect a dashboard to external APIs without exposing API keys
  • Create endpoints for stock quotes and news
  • Standardize API responses and error handling
HKUDS/OpenSpace7.8KUpdated Aug 13, 2026

Produce a master track and separate audio parts through a structured Python workflow. Apply filters and reverb, export WAV files with consistent settings, package them in a ZIP archive, and check that the deliverables meet the requested specifications.

  • Export a master track with separate audio parts
  • Apply filters and reverb to audio
  • Check duration and format across deliverables
HKUDS/OpenSpace7.8KUpdated Aug 13, 2026

Keep document creation moving when web searches and page retrieval repeatedly fail. The skill preserves the original task, uses the model’s existing knowledge, and clearly identifies information that could not be checked against external sources.

  • Continue drafting after repeated web retrieval failures
  • Preserve task requirements during network errors
  • Mark information that could not be externally verified
HKUDS/OpenSpace7.8KUpdated Aug 13, 2026

When Python execution repeatedly fails in execute_code_sandbox, use a file-based alternative: save the script, run it through the shell, and capture results or errors. The guidance covers paths, imports, timeouts, structured output, and optional cleanup.

  • Retry Python work through the shell after repeated sandbox failures
  • Run longer tasks with an adjusted timeout
  • Execute Python work that needs multiple files or system utilities
HKUDS/OpenSpace7.8KUpdated Aug 13, 2026

See all skills by HKUDS

Report a problem with this skill