name: "使用 gpt-engineer 从自然语言规范生成并在本地代码库上迭代开发" slug: "generate-and-iterate-on-a-local-codebase-from-a-natural-language-spec-with-gpt-engineer" version: "1.0.0" displayName: "使用 gpt-engineer 从自然语言规范生成并在本地代码库上迭代开发" summary: "当代理/操作员需要将提示文件转换为本地项目脚手架、检查生成的代码并在采用结果之前运行监督改进循环时，请使用 gpt-engineer。" license: "MIT" description: "当代理/操作员需要将提示文件转换为本地项目脚手架、检查生成的代码并在采用结果之前运行监督改进循环时，请使用 gpt-engineer。" github_stars: 55220 verification: "security_reviewed" source: "https://github.com/1991513ccie-png/skills" author: "1991513ccie-png" publisher_type: "individual" category: "Developer Tools" framework: "Multi-Framework" tool_ecosystem: github_repo: "1991513ccie-png/skills" github_stars: 55220

使用 gpt-engineer 从自然语言规范生成并在本地代码库上迭代开发

Use gpt-engineer when an agent/operator needs to turn a prompt file into a local project scaffold, inspect the generated code, and run a supervised improvement loop before adopting the result.

Prerequisites

Python, pip, OpenAI-compatible or supported model API key, gpte CLI

Installation

Use the upstream install or setup path that matches your environment: - Use Docker (instructions)

Requirements and caveats from upstream: - python -m pip install gpt-engineer - We actively support Python 3.10 - 3.12. The last version to support Python 3.8 - 3.9 was 0.2.6.

Basic usage or getting-started notes: - For stable release: - For development: - git clone https://github.com/1991513ccie-png/skills

• Source: https://github.com/1991513ccie-png/skills
• Extracted from upstream docs: https://raw.githubusercontent.com/AntonOsika/gpt-engineer/HEAD/README.md

Documentation

• https://gpt-engineer.readthedocs.io/en/latest/

这个 Skill 质量中等偏下。元数据比较完整，但实际内容单薄，安装说明不完整，关键步骤还留有空白。缺少使用示例和具体指引，对新手不够友好。推荐有经验的开发者使用，新手可能需要额外查阅官方文档才能上手。