f2CBVx

t.ly/s0R4x t.ly/gDGm6 ppt.cc/fwlgFx ppt.cc/fVjECx ppt.cc/fEnHsx ppt.cc/fRZTnx ppt.cc/fSZ3cx ppt.cc/fLOuCx ppt.cc/fE9Nux ppt.cc/fL5Kyx ppt.cc/f71Yqx tecmint.com linuxcool.com linux.die.net linux.it.net.cn ostechnix.com unix.com ubuntugeek.com runoob.com man.linuxde.net ppt.cc/fwpCex ppt.cc/fxcLIx ppt.cc/foX6Ux linuxprobe.com linuxtechi.com howtoforge.com linuxstory.org systutorials.com ghacks.net linuxopsys.com ppt.cc/ffAGfx ppt.cc/fJbezx ppt.cc/fNIQDx ppt.cc/fCSllx ppt.cc/fybDVx ppt.cc/fIMQxx

Showing posts with label ai. Show all posts

Thursday, 8 October 2026

Codex CLI 的交互式启动器cx

为 Codex CLI 提供更顺手的交互式启动器

一条命令启动，动态补全参数，减少重复输入

简介 • 安装 • 使用 • 开发

简介

cx 是一个轻量级命令行启动器，用来简化 Codex CLI 的启动流程。

功能特性

交互式菜单启动 Codex
已传入的参数自动跳过，不重复询问
支持 reasoning / yolo / model 动态补全
支持在交互菜单中回退上一步
检测到 fzf 时默认启用增强交互
支持 macOS / Linux
支持 bash / zsh

安装

环境要求

已安装 codex
bash 可用
fzf 可选，安装后会自动启用增强交互

快速安装

curl -fsSL https://raw.githubusercontent.com/Shadowzzh/cx/main/scripts/install.sh | bash

手动安装

git clone https://github.com/Shadowzzh/cx.git
cd cx
bash scripts/install.sh

卸载

curl -fsSL https://raw.githubusercontent.com/Shadowzzh/cx/main/scripts/uninstall.sh | bash

bash scripts/uninstall.sh

使用

基础示例

cx
cx yolo
cx gpt-5.5
cx xhigh
cx gpt-5.4
cx yolo xhigh
cx yolo xhigh gpt-5.4
cx no-yolo high

规则说明

传了什么参数，就跳过对应菜单
缺什么参数，就只补什么菜单
三个维度都齐了，就直接启动

菜单回退

从第二个交互步骤开始，可输入 b 或 back 返回上一步
fzf 菜单支持 ctrl-b 返回上一步
同时提供显式菜单项 返回上一步
仅能回退当前这次交互里实际出现过的步骤

默认值

reasoning: medium
yolo: yes
model: gpt-5.4

支持的思考等级

low
medium
high
xhigh

支持的 model

gpt-5.4
gpt-5.5
gpt-5.3-codex
gpt-5.2-codex
gpt-5.1-codex-max
gpt-5.2
gpt-5.1-codex-mini

开发

项目结构

├── bin/
│   └── cx
├── scripts/
│   ├── install.sh
│   └── uninstall.sh
├── tests/
│   └── cx_smoke_test.sh
├── docs/
│   ├── demo.gif
│   └── logo.svg
└── .github/
    └── workflows/
        └── smoke.yml

本地检查

bash -n bin/cx
bash -n scripts/install.sh
bash -n scripts/uninstall.sh
bash tests/cx_smoke_test.sh

设计原则

核心逻辑保持单文件，方便安装和维护
安装脚本只做最小配置，不隐式修改太多用户环境
交互保持轻量，fzf 作为可选增强，未安装时，回退 shell的原生能力

from  https://github.com/Shadowzzh/cx

AI Website Cloner

A reusable template for reverse-engineering any website into a clean, modern Next.js codebase using AI coding agents.

Recommended: Claude Code with Opus 4.6 for best results — but works with a variety of AI coding agents.

Point it at a URL, run /clone-website, and your AI agent will inspect the site, extract design tokens and assets, write component specs, and dispatch parallel builders to reconstruct every section.

Demo

Click the image above to watch the full demo on YouTube.

Quick Start

Clone this repository

git clone https://github.com/JCodesMore/ai-website-cloner-template.git my-clone
cd my-clone

Install dependencies
```
npm install
```
Start your AI agent — Claude Code recommended:
```
claude --chrome
```

Run the skill:

/clone-website <target-url1> [<target-url2> ...]

Customize (optional) — after the base clone is built, modify as needed

Using a different agent? Open AGENTS.md for project instructions — most agents pick it up automatically.

Supported Platforms

Agent	Status
Claude Code	Recommended — Opus 4.6
Codex CLI	Supported
OpenCode	Supported
GitHub Copilot	Supported
Cursor	Supported
Windsurf	Supported
Gemini CLI	Supported
Cline	Supported
Roo Code	Supported
Continue	Supported
Amazon Q	Supported
Augment Code	Supported
Aider	Supported

Prerequisites

Node.js 24+
An AI coding agent (see Supported Platforms)

Tech Stack

Next.js 16 — App Router, React 19, TypeScript strict
shadcn/ui — Radix primitives + Tailwind CSS v4
Tailwind CSS v4 — oklch design tokens
Lucide React — default icons (replaced by extracted SVGs during cloning)

How It Works

The /clone-website skill runs a multi-phase pipeline:

Reconnaissance — screenshots, design token extraction, interaction sweep (scroll, click, hover, responsive)
Foundation — updates fonts, colors, globals, downloads all assets
Component Specs — writes detailed spec files (docs/research/components/) with exact computed CSS values, states, behaviors, and content
Parallel Build — dispatches builder agents in git worktrees, one per section/component
Assembly & QA — merges worktrees, wires up the page, runs visual diff against the original

Each builder agent receives the full component specification inline — exact getComputedStyle() values, interaction models, multi-state content, responsive breakpoints, and asset paths. No guessing.

Use Cases

Platform migration — rebuild a site you own from WordPress/Webflow/Squarespace into a modern Next.js codebase
Lost source code — your site is live but the repo is gone, the developer left, or the stack is legacy. Get the code back in a modern format
Learning — deconstruct how production sites achieve specific layouts, animations, and responsive behavior by working with real code

Not Intended For

Phishing or impersonation — this project must not be used for deceptive purposes, impersonation, or any activity that breaks the law.
Passing off someone's design as your own — logos, brand assets, and original copy belong to their owners.
Violating terms of service — some sites explicitly prohibit scraping or reproduction. Check first.

Project Structure

src/
  app/              # Next.js routes
  components/       # React components
    ui/             # shadcn/ui primitives
    icons.tsx       # Extracted SVG icons
  lib/utils.ts      # cn() utility
  types/            # TypeScript interfaces
  hooks/            # Custom React hooks
public/
  images/           # Downloaded images from target
  videos/           # Downloaded videos from target
  seo/              # Favicons, OG images
docs/
  research/         # Extraction output & component specs
  design-references/ # Screenshots
scripts/
  sync-agent-rules.sh  # Regenerate agent instruction files
  sync-skills.mjs      # Regenerate /clone-website for all platforms
AGENTS.md           # Agent instructions (single source of truth)
CLAUDE.md           # Claude Code config (imports AGENTS.md)
GEMINI.md           # Gemini CLI config (imports AGENTS.md)

Commands

npm run dev    # Start dev server
npm run build  # Production build
npm run lint   # ESLint check
npm run typecheck # TypeScript check
npm run check  # Run lint + typecheck + build

If using docker

docker compose up app --build # build and run the app
docker compose up dev --build # run the app in dev mode on port 3001

Updating for Other Platforms

Two source-of-truth files power all platform support. Edit the source, then run the sync script:

What	Source of truth	Sync command
Project instructions	`AGENTS.md`	`bash scripts/sync-agent-rules.sh`
`/clone-website` skill	`.claude/skills/clone-website/SKILL.md`	`node scripts/sync-skills.mjs`

Each script regenerates the platform-specific copies automatically. Agents that read the source files natively need no regeneration.

from https://github.com/Shadowzzh/lisu-website

用muse的web版帮我在cloudflare.com平台上构建基于deno的静态博客程序pagic

我用email id: luckypoem@gmail.com登录cloudflare.com后，导入仓库https://github.com/brightmann/pg

下面的插图就是我跟它的对话过程.共9张截图。

我得到的博客网址是：

https://pg.luckypoem.workers.dev/

https://pg.luckypoem.workers.dev/blog/ 支持分页

项目地址：

https://github.com/xcatliu/pagic

https://github.com/brightmann/pg

在这里 https://github.com/brightmann/pg/tree/master/pagic.org/blog ，新建源帖fh.md ,内容为：

---
date: 2026-10-08T01:34
---

# 战马

此处写正文或html codes.

（详见https://github.com/brightmann/pg/blob/master/pagic.org/blog/fh.md?plain=1）

---------------------

要不是muse,我是无法搞定静态博客程序pagic的安装的。本博客里写的用muse帮我搭建的静态博客程序都是我无法安装成功的。如果我能安装成功，就不用通过muse了。

Wednesday, 7 October 2026

用muse的web版帮我在cloudflare.com平台上构建基于nextjs的静态博客程序nart

我用email id: luckypoem@gmail.com登录cloudflare.com后，导入仓库https://github.com/brightmann/nart, 原仓库https://github.com/mickasmt/next-auth-roles-template 带有用户认证板块，还涉及到数据库，muse把用户认证板块和数据库都剥离了，只构建静态博客程序那部分。

下面的插图就是我跟它的对话过程.共6张截图。