Python Executor
Skill Verified ActiveExecute Python code in a safe sandboxed environment via [inference.sh](https://inference.sh). Pre-installed: NumPy, Pandas, Matplotlib, requests, BeautifulSoup, Selenium, Playwright, MoviePy, Pillow, OpenCV, trimesh, and 100+ more libraries. Use for: data processing, web scraping, image manipulation, video creation, 3D model processing, PDF generation, API calls, automation scripts. Triggers: python, execute code, run script, web scraping, data analysis, image processing, video editing, 3D models, automation, pandas, matplotlib
Execute arbitrary Python code securely and efficiently in a pre-configured environment with a rich set of libraries, enabling complex data processing, web scraping, and automation tasks without local setup.
Features
- Execute Python 3.10 code in a safe sandbox
- Over 100 pre-installed libraries (NumPy, Pandas, requests, etc.)
- Supports web scraping, data analysis, image/video processing
- Configurable timeout and memory variants
- Automatic return of captured output and files
Use Cases
- Process and analyze datasets using Pandas and Matplotlib
- Scrape data from websites using requests and BeautifulSoup
- Manipulate images with Pillow and OpenCV
- Automate tasks with custom Python scripts
- Interact with APIs using requests or httpx
Non-Goals
- Running GPU-intensive ML models (explicitly CPU-only)
- Interactive debugging or live code execution
- Modifying the sandboxed environment beyond code execution
Installation
npx skills add inferen-sh/skillsRuns the Vercel skills CLI (skills.sh) via npx — needs Node.js locally and at least one installed skills-compatible agent (Claude Code, Cursor, Codex, …). Assumes the repo follows the agentskills.io format.
Quality Score
VerifiedSimilar Extensions
Agent Browser
100Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.
Wasm Agent
99Create and manage sandboxed WASM agents for isolated code execution
Cloudflare Sandbox SDK
99Build sandboxed applications for secure code execution. Load when building AI code execution, code interpreters, CI/CD systems, interactive dev environments, or executing untrusted code. Covers Sandbox SDK lifecycle, commands, files, code interpreter, and preview URLs. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.
Agent Sandbox
95Agent skill for sandbox - invoke with $agent-sandbox
AgentBay AIO Skills
95用于任何「运行/执行/评估代码」的请求（如 run this code、execute script、用 Python 画图、跑代码/画图/执行脚本）。通过 AgentBay SDK 创建 code_latest 沙箱，调用 run_code 执行并返回结果。支持 Python、JavaScript、R、Java。
Project Session Manager
100Worktree-first dev environment manager for issues, PRs, and features with optional tmux sessions