码力搭建 Skill
name: mali-builder
by chenjada45-maker · published 2026-03-22
$ claw add gh:chenjada45-maker/chenjada45-maker-mailprocess---
name: mali-builder
description: 自动调用码力搭建平台完成应用搭建。触发词:码力搭建、mali、低代码搭建、搭建应用、创建应用、管理系统、数据看板、表单系统。自动打开Chrome填充需求并点击发送。适合内部工具、数据展示、表单收集、快速原型开发。
---
# 码力搭建 Skill
功能说明
该 Skill 用于调用码力搭建平台(Mali App Builder),自动化完成以下操作:
1. 在用户的 Chrome 浏览器中打开码力搭建平台
2. 确保用户已登录
3. 将用户的搭建需求自动填入对话框
4. 触发搭建流程
触发条件
操作流程
步骤 1: 打开码力搭建平台
使用 AppleScript(macOS)或其他系统命令打开 Chrome 浏览器并导航到码力搭建平台:
# macOS 使用 AppleScript
osascript -e 'tell application "Google Chrome"
activate
open location "https://lowcode.baidu-int.com/ai-coding"
end tell'
# Linux 使用 xdg-open
xdg-open "https://lowcode.baidu-int.com/ai-coding"
# Windows 使用 start
start chrome "https://lowcode.baidu-int.com/ai-coding"步骤 2: 等待页面加载
等待 3-5 秒确保页面完全加载,并检查用户登录状态。
步骤 3: 注入需求并触发搭建
使用 Chrome DevTools Protocol 或 JavaScript 注入来填充搭建需求:
// 通过 Chrome DevTools Protocol 执行
// 1. 找到输入框并填入需求
const inputBox = document.querySelector('textarea[placeholder*="描述"], input[type="text"]');
if (inputBox) {
inputBox.value = "用户的搭建需求内容";
inputBox.dispatchEvent(new Event('input', { bubbles: true }));
}
// 2. 找到发送按钮并点击
const sendButton = document.querySelector('button[type="submit"], button.send-btn');
if (sendButton) {
sendButton.click();
}步骤 4: 确认执行状态
输出格式
执行完成后返回:
✅ 码力搭建已启动!
🌐 浏览器: Chrome
📍 平台地址: https://lowcode.baidu-int.com/ai-coding
📋 提交的需求:
{用户的原始需求}
⏳ 请在浏览器中查看搭建进度...错误处理
浏览器未安装
❌ 未找到 Chrome 浏览器
💡 建议: 请安装 Chrome 浏览器后重试登录状态异常
⚠️ 检测到未登录状态
💡 建议: 请先在浏览器中登录码力搭建平台
🔗 登录地址: https://lowcode.baidu-int.com/ai-coding页面加载失败
❌ 页面加载失败
💡 建议:
1. 检查网络连接
2. 确认是否在公司内网环境
3. 手动访问平台进行搭建技术实现
方案 A: AppleScript + Chrome (推荐 macOS)
tell application "Google Chrome"
activate
set myTab to make new tab at end of tabs of window 1
set URL of myTab to "https://lowcode.baidu-int.com/ai-coding"
delay 3
execute myTab javascript "
const input = document.querySelector('textarea, input[type=\"text\"]');
if (input) {
input.value = '用户需求内容';
input.dispatchEvent(new Event('input', {bubbles: true}));
const btn = document.querySelector('button[type=\"submit\"]');
if (btn) btn.click();
}
"
end tell方案 B: Python + Selenium (跨平台)
from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
import time
def launch_mali_builder(user_requirement):
driver = webdriver.Chrome()
driver.get('https://lowcode.baidu-int.com/ai-coding')
# 等待页面加载
time.sleep(3)
# 查找输入框
try:
input_box = WebDriverWait(driver, 10).until(
EC.presence_of_element_located((By.CSS_SELECTOR, "textarea, input[type='text']"))
)
input_box.send_keys(user_requirement)
# 查找发送按钮
send_btn = driver.find_element(By.CSS_SELECTOR, "button[type='submit']")
send_btn.click()
print("✅ 搭建需求已提交")
except Exception as e:
print(f"❌ 操作失败: {str(e)}")方案 C: 纯命令行 (最简单)
#!/bin/bash
# 简单地打开浏览器到指定页面
# 用户需要手动输入需求
MALI_URL="https://lowcode.baidu-int.com/ai-coding"
case "$(uname -s)" in
Darwin*)
open -a "Google Chrome" "$MALI_URL"
;;
Linux*)
xdg-open "$MALI_URL" || google-chrome "$MALI_URL"
;;
CYGWIN*|MINGW*|MSYS*)
start chrome "$MALI_URL"
;;
esac
echo "✅ 已在浏览器中打开码力搭建平台"
echo "📍 $MALI_URL"
echo ""
echo "📋 请手动输入以下需求:"
echo "$1"使用示例
示例 1: 简单应用搭建
用户: 帮我用码力搭建一个任务管理应用
助手: [执行 mali-builder skill]
✅ 码力搭建已启动!
📋 提交的需求: 任务管理应用示例 2: 复杂需求搭建
用户: 使用码力搭建创建一个包含用户登录、数据看板、报表导出的管理系统
助手: [执行 mali-builder skill]
✅ 码力搭建已启动!
📋 提交的需求: 包含用户登录、数据看板、报表导出的管理系统注意事项
1. **网络要求**: 需要在公司内网或 VPN 环境下使用
2. **浏览器要求**: 推荐使用 Chrome 浏览器(最新版本)
3. **登录状态**: 首次使用需要手动登录一次
4. **权限要求**: 需要系统允许脚本控制浏览器的权限
5. **自动化限制**: 部分页面可能有反自动化机制,需要用户手动确认
兼容性
| 操作系统 | Chrome | Safari | Firefox | Edge |
|---------|--------|--------|---------|------|
| macOS | ✅ | ✅ | ⚠️ | ❌ |
| Linux | ✅ | ❌ | ⚠️ | ❌ |
| Windows | ✅ | ❌ | ⚠️ | ✅ |
✅ 完全支持 ⚠️ 部分支持 ❌ 不支持
More tools from the same signal band
Order food/drinks (点餐) on an Android device paired as an OpenClaw node. Uses in-app menu and cart; add goods, view cart, submit order (demo, no real payment).
Sign plugins, rotate agent credentials without losing identity, and publicly attest to plugin behavior with verifiable claims and authenticated transfers.
The philosophical layer for AI agents. Maps behavior to Spinoza's 48 affects, calculates persistence scores, and generates geometric self-reports. Give your...