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。

Chatgpt Search

技能 已验证 活跃

Search ChatGPT and extract the full response + hydration JSON that powers the UI. Attaches to a running Chrome instance (port 9222 by default), opens ChatGPT, submits a query, waits for the streamed response, and returns structured data: messages, product cards, hydration JSON, and API calls. Use when asked to "search chatgpt", "ask chatgpt", "chatgpt search", "get chatgpt response", or "scrape chatgpt".

目的

To automatically retrieve and structure the complete output from ChatGPT, including conversational messages and underlying UI data, for further analysis or use.

功能

  • Attaches to a running Chrome instance
  • Opens ChatGPT and submits queries
  • Extracts full response text and hydration JSON
  • Captures SSE streams and API calls
  • Returns structured data including messages and product cards

使用场景

  • Use when asked to search ChatGPT for specific information.
  • Use when needing to obtain the full structured response from a ChatGPT session.
  • Use when wanting to scrape ChatGPT for conversational data or UI elements.

非目标

  • Interacting with ChatGPT without a running Chrome instance.
  • Providing a chat interface; this skill extracts data from an existing session.

安装

npx skills add SeifBenayed/claude-code-sdk

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
100 /100
about 22 hours ago 分析

信任信号

最近提交about 1 month ago
GitHub 所有者 SeifBenayed (opens in new tab)
星标114
下载量 38 (opens in new tab)
许可证MIT
状态
查看源代码

类似扩展

Browser Extract

99

Extract structured data via stored browser-templates or one-shot DOM queries, with mandatory AIDefence PII + prompt-injection gates before content reaches the model

技能
ruvnet

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

AutoBrowse

100

Self-improving browser automation via the auto-research loop. Iteratively runs a browsing task, reads the trace, and improves the navigation skill (strategy.md) until it reliably passes. Supports parallel runs across multiple tasks using sub-agents. Use when you want to build or improve browser automation skills for specific website tasks.

技能
browserbase

Website Extraction Api

100

Extract typed JSON from public website pages using a schema.

技能
iterationlayer

Extract Supplier Catalog From Website

100

Extract SKUs, product names, unit prices, availability, and minimum order quantities from a supplier catalog page.

技能
iterationlayer

Extract Public Registry Page

100

Extract organization name, registration number, status, registration date, and officers from a public registry page.

技能
iterationlayer