#ChatGPT# 这几天用 Cursor ，我发现Gemini 2.5 Pro 是要比Claude 3.7 o3 强的。

#稍后阅读# Interactive User Feedback MCP,本 MCP 工具 interactive_feedback ，把多轮对话在一次请求内完成，最大化利用 25 次子调用额度，实现把 Cursor 500次请求变2500次。https://github.com/kele527/interactive-feedback-mcp

用cursor做的UI/UX设计：https://d.cellmean.com/html/movie-app/

只用了claude sonnet 3.5，因为3.7这几天一直处理繁忙状态基本不可用。
步骤是先用chat生成提示词，这里的要点是让它生成一步步，或者说按部分生成提示词，以防止token过于庞大 cursor 返回出错。

#Cursor# cursor 的change log页面：
https://changelog.cursor.sh/

最近在迁移服务器，有一段时间没用cursor了，不能落伍，最新版本推出了agent。

#Cursor# next.js的 cursor rule
https://cursor.directory/nextjs-react-typescript-cursor-rules

#ChatGPT# #Cursor#

https://reweb.so
可视化修改v0导出的代码

https://v0.dev/explore
更多用户生成的v0界面，可参考

#Cursor# I want to create a chrome extension that uses open ai api to summarize youtube video transcripts. I need you to generate me a folder for the chrome extension and a python file for my extemal api server. the chrome extension will make API calls to the flask server that I will host locally. the python file should use YouTubeTranscriptApi for the transcript and then use openai for summary. There should be a button inside the youtube window that says summarize as well as one within the actual chrom extension, when they are clicked they should send the api request to the flask server to get the trascript. the Chrome extension should have a nice modem Ul that is dark mode with white text, it should have one tab that shows the transcript and one tab that shows the summary returned from the APl, at the top of the chrome extension it should say Stride Tube in gold letters. The user should be able to input their openai api key that will be sent to the flask server for the Open Al api ca