技能 python-executor
📦

python-executor

低风险 ⚙️ 外部命令🌐 网络访问

Execute Python code in a sandboxed cloud environment

也可从以下获取: qu-skills,skillssh,inference-sh-skills,inferen-sh,infsh-skills,inference-skills,inference-sh

Run Python scripts without local setup or dependency management. Access 100+ pre-installed libraries for data analysis, web scraping, image processing, and automation through a simple API call.

支持: Claude Codex Code(CC)
⚠️ 65
1

下载技能 ZIP

2

在 Claude 中上传

前往 设置 → 功能 → 技能 → 上传技能

3

开启并开始使用

测试它

正在使用“python-executor”。 Execute Python code to create a gradient image

预期结果:

  • Code executed successfully in 2.3 seconds
  • Output files: outputs/gradient.png (256x256 grayscale image)
  • Memory used: 45 MB

正在使用“python-executor”。 Scrape weather data from a weather API and display current temperature

预期结果:

  • Code executed successfully in 1.8 seconds
  • API Response: Temperature is 72°F, Conditions: Partly Cloudy
  • Location: San Francisco, CA

安全审计

低风险
v1 • 2/27/2026

Static analysis flagged 72 patterns but most are false positives. The 'external_commands' detections are bash code examples in markdown documentation, not actual shell execution. Network URLs point to the legitimate inference.sh service. The skill executes code on a remote sandboxed service, not locally. Low risk assigned due to third-party service dependency and ability to run arbitrary user code remotely.

1
已扫描文件
184
分析行数
5
发现项
1
审计总数
中风险问题 (1)
Pipe to Shell Installation Pattern
The install command uses curl piped to sh (curl | sh) which can be risky if the server is compromised. This is a common pattern for CLI tools but users should be aware of the trust model.
低风险问题 (2)
Third-Party Code Execution Service
The skill relies on inference.sh remote service for code execution. Users must trust the service provider with their code and any data processed.
Network Access for Web Scraping
The skill supports web scraping and API calls using requests library. This is intended functionality but could be used to access external services.
审计者: claude

质量评分

38
架构
100
可维护性
87
内容
21
社区
81
安全
83
规范符合性

你能构建什么

Data Analysis and Visualization

Process CSV or Excel files with Pandas, create charts with Matplotlib, and generate reports without installing any libraries locally.

Automated Web Scraping

Extract data from websites using BeautifulSoup for static pages or Selenium for JavaScript-rendered content, then export to structured formats.

Media Processing Pipeline

Create video content with MoviePy, manipulate images with Pillow and OpenCV, or process 3D models with trimesh in automated workflows.

试试这些提示

Basic Python Execution
Run this Python code and show me the output: print('Hello World')
Data Analysis Task
Create a Pandas DataFrame with sample sales data, calculate summary statistics, and generate a bar chart saved as outputs/sales.png
Web Scraping Request
Scrape the article titles from https://example.com/news and return them as a JSON list. Use BeautifulSoup for parsing.
Complex Media Pipeline
Create a 10-second video with a blue background, add animated text that fades in, include a background music track, and export as outputs/promo.mp4 with 120 second timeout

最佳实践

  • Always save output files to the outputs/ directory to ensure they are returned in the response
  • Set appropriate timeout values for long-running tasks like video processing or large data operations
  • Use plt.savefig() instead of plt.show() for matplotlib visualizations since the environment is non-interactive

避免

  • Do not attempt to install additional packages at runtime - use only the pre-installed libraries
  • Avoid infinite loops or excessively long computations that will hit the timeout limit
  • Do not use interactive input functions like input() or plt.show() that require user interaction

常见问题

How do I install additional Python libraries not in the pre-installed list?
You cannot install additional packages at runtime. The environment comes with 100+ pre-installed libraries. Check the documentation for the full list or request new libraries to be added to the base image.
Where are my output files stored and how do I access them?
Save files to the outputs/ directory in your code. The system automatically detects and returns all files in this directory as part of the response. Files persist only for the duration of the execution.
Can I run machine learning models with this skill?
No, this is a CPU-only environment without GPU support. For ML workloads, use dedicated AI skills like ai-image-generation or llm-models that are optimized for those tasks.
What is the maximum execution time for my code?
The default timeout is 30 seconds. You can set timeout up to 300 seconds (5 minutes) by including the timeout parameter in your request. Use the high_memory variant for memory-intensive tasks.
Is my code and data secure when using this skill?
Code executes in an isolated sandbox on inference.sh servers. Each execution is independent. However, do not send sensitive credentials or personal data as the code runs on third-party infrastructure.
How do I handle errors in my Python code?
Errors are returned in the response with full tracebacks. Use try-except blocks in your code for graceful error handling. The capture_output option (enabled by default) includes stdout and stderr in the response.

开发者详情

文件结构

📄 SKILL.md