Skip to content
cccskills
FreePublished on GitHub

safe-script-execution

Recover from repeated code execution tool failures by writing a script through the shell and running it with an absolute path. Check output files and investigate syntax, permissions, disk space, or execution errors when needed.

OriginalShow the original description

Fallback workflow for code execution when automated tools fail, using shell heredoc with verification

See how to install

Good for

  • Run scripts when automated execution tools keep failing
  • Save multiline scripts without shell variable expansion
  • Check generated files for size and type
  • Investigate script syntax and permission errors

Files included (2)

  • SKILL.md3.2 KB
  • .skill_id35 B

SKILL.md (original)

Review the instructions the agent will receive before you install.

Safe Script Execution Fallback

When to Use This Skill

Use this pattern when execute_code_sandbox or shell_agent repeatedly fails to produce expected outputs. This manual fallback provides explicit control over script creation and execution with built-in verification.

Step-by-Step Instructions

Step 1: Verify Working Directory

Before creating any scripts, confirm your current location and permissions:

pwd
ls -la

Document the absolute path. All subsequent file operations should use explicit paths from this point.

Step 2: Create Script via Heredoc

Use shell heredoc syntax to create scripts. This avoids issues with multi-line string escaping:

cat > /full/path/to/script.py << 'HEREDOC_END'
#!/usr/bin/env python3
# Your script content here
# Single quotes around delimiter prevent variable expansion
print("Hello from script")
HEREDOC_END

Key escaping rules:

  • Use single quotes around heredoc delimiter ('EOF') to prevent shell variable expansion
  • If script contains the delimiter string, choose a different unique delimiter
  • For bash scripts containing special characters, escape $, backticks, and !

Step 3: Make Executable and Run with Explicit Path

chmod +x /full/path/to/script.py
/full/path/to/script.py

Always use the full absolute path, never rely on . or relative paths.

Step 4: Verify Output

Confirm files were created and inspect their properties:

# Check file exists with size
ls -lh /full/path/to/output.file

# For PDFs, inspect metadata
pdfinfo /full/path/to/output.pdf 2>/dev/null || file /full/path/to/output.pdf

# For Word docs, check file type
file /full/path/to/output.docx

Step 5: Error Handling

If execution fails:

  1. Check script syntax: python3 -m py_compile /path/to/script.py
  2. Check permissions: ls -l /path/to/script.py
  3. Check available disk space: df -h .
  4. Review stderr output carefully

Example: PDF Generation Fallback

# Step 1: Verify directory
pwd
ls -la

# Step 2: Create Python script
cat > /workspace/generate_pdf.py << 'SCRIPT_END'
from reportlab.lib.pagesizes import letter
from reportlab.pdfgen import canvas

c = canvas.Canvas("/workspace/output.pdf", pagesize=letter)
c.drawString(100, 750, "Generated PDF")
c.save()
SCRIPT_END

# Step 3: Execute
chmod +x /workspace/generate_pdf.py
python3 /workspace/generate_pdf.py

# Step 4: Verify
ls -lh /workspace/output.pdf
pdfinfo /workspace/output.pdf 2>/dev/null || echo "PDF created, pdfinfo unavailable"

Anti-Patterns to Avoid

  • ❌ Don't use relative paths like ./script.py - always use absolute paths
  • ❌ Don't rely on unquoted heredoc delimiters if script contains variables
  • ❌ Don't skip verification steps - always confirm output exists and has expected size
  • ❌ Don't assume working directory - always pwd first

Troubleshooting Checklist

  • Working directory confirmed with pwd
  • Script file exists after heredoc creation (ls -l)
  • Script has execute permissions (chmod +x)
  • Output file exists with non-zero size (ls -lh)
  • File type verified (file command or type-specific inspection)

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