python-executor

Execute Python code in a sandboxed environment with 100+ pre-installed libraries.

Updated Jul 28, 2026
One-click install
npx skills add https://github.com/Aadi-110i/PEP-PROJECT --skill python-executor-aadi-110i
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: python-executor
Source: https://github.com/Aadi-110i/PEP-PROJECT/tree/main/skills/python-executor
Command: npx skills add https://github.com/Aadi-110i/PEP-PROJECT --skill python-executor-aadi-110i

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Running Python code for data processing, web scraping, or media manipulation normally requires local environment setup, dependency management, and security concerns. This Skill executes Python code in a safe, sandboxed cloud environment with over 100 pre-installed libraries, eliminating setup friction. ## Core Features & Use Cases - Sandboxed Code Execution: Run arbitrary Python 3.10 code in an isolated subprocess with configurable timeout (1-300 seconds) and memory (8GB or 16GB). - Rich Library Ecosystem: Pre-installed packages include pandas, NumPy, Matplotlib, Selenium, Playwright, MoviePy, Pillow, OpenCV, trimesh, and ReportLab. - Automatic File Output: Files saved to the outputs/ directory (charts, CSVs, videos, 3D models, PDFs) are automatically detected and returned. - Use Case: Scrape a website with BeautifulSoup, analyze the data with pandas, generate a Matplotlib chart, and receive the PNG file back—all in one request. ## Quick Start Run my Python script that fetches data from an API and saves a pandas DataFrame as a CSV file using the python-executor skill.

Frequently Asked Questions about python-executor

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I run Python code in a sandboxed environment?

Use the belt CLI with the command `belt app run infsh/python-executor` and pass your code as JSON input. The code runs in an isolated Python 3.10 subprocess, and any files saved to the outputs directory are returned automatically.

What Python libraries are pre-installed for web scraping and data analysis?

The environment includes requests, httpx, BeautifulSoup, Selenium, Playwright, and Scrapy for scraping, plus pandas, NumPy, SciPy, Matplotlib, Seaborn, and Plotly for data processing and visualization.

Can I use Selenium or Playwright for browser automation in this environment?

Yes, both Selenium and Playwright are pre-installed for browser automation. The environment is CPU-only and non-interactive, so scripts must run headlessly without display output.

Does the Python executor support GPU or machine learning libraries?

No, the environment is CPU-only and does not include GPU or ML libraries. For AI-based image, video, or text generation, use the dedicated inference.sh AI apps instead.

Why is my Matplotlib chart not showing when I run code?

The environment is non-interactive, so plt.show() does nothing. Use plt.savefig('outputs/chart.png') instead—files saved to the outputs directory are automatically detected and returned.

What are the timeout and memory limits for code execution?

Timeouts range from 1 to 300 seconds with a 30-second default. Memory is 8GB by default, with a high_memory variant offering 16GB for large datasets.