跳转到主要内容
此内容尚未提供您的语言版本,正在以英文显示。

Python Executor

技能 已验证 活跃

Execute 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

目的

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.

功能

  • 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

使用场景

  • 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

非目标

  • Running GPU-intensive ML models (explicitly CPU-only)
  • Interactive debugging or live code execution
  • Modifying the sandboxed environment beyond code execution

安装

npx skills add inferen-sh/skills

通过 npx 运行 Vercel skills CLI(skills.sh)— 需要本地安装 Node.js,以及至少一个兼容 skills 的智能体(Claude Code、Cursor、Codex 等)。前提是仓库遵循 agentskills.io 格式。

质量评分

已验证
99 /100
1 day ago 分析

信任信号

最近提交1 day ago
星标433
状态
查看源代码

类似扩展

Agent Browser

100

AI 代理的浏览器自动化 CLI。当用户需要与网站交互时使用,包括浏览页面、填写表单、点击按钮、截屏、提取数据、测试 Web 应用或自动化任何浏览器任务。触发条件包括请求“打开网站”、“填表”、“点击按钮”、“截屏”、“抓取页面数据”、“测试此 Web 应用”、“登录网站”、“自动化浏览器操作”或任何需要以编程方式进行 Web 交互的任务。

技能
shanraisshan

Wasm Agent

99

Create and manage sandboxed WASM agents for isolated code execution

技能
ruvnet

Cloudflare Sandbox SDK

99

构建用于安全代码执行的沙盒应用程序。在构建 AI 代码执行、代码解释器、CI/CD 系统、交互式开发环境或执行不受信任的代码时加载。涵盖 Sandbox SDK 生命周期、命令、文件、代码解释器和预览 URL。倾向于从 Cloudflare 文档中检索信息,而不是依赖预训练知识。

技能
cloudflare

Agent Sandbox

95

Agent skill for sandbox - invoke with $agent-sandbox

技能
ruvnet

AgentBay AIO 技能

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。

技能
agentbay-ai

Project Session Manager

100

Worktree-first dev environment manager for issues, PRs, and features with optional tmux sessions

技能
Yeachan-Heo