Back to Details

x-ai-digest

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese
<!-- i18n-examples:start -->
<!-- i18n-examples:start -->

调用 / Invoke / 呼び出し

Invoke

中文

Chinese (Translated)

  • "用 x-ai-digest 抓取今天的 AI 热点"
  • "用 x-ai-digest 生成昨天的 X 平台 AI 简报"
  • "x-ai-digest 帮我看看前天 X 上有什么 AI 相关动态"
  • "用 x-ai-digest 整理最近的 AI 推文并给出回复建议"
  • "Use x-ai-digest to scrape today's AI hot topics from X"
  • "Use x-ai-digest to generate yesterday's X platform AI digest"
  • "Use x-ai-digest to check AI-related updates on X from the day before yesterday"
  • "Use x-ai-digest to organize recent AI tweets and provide reply suggestions"

English

English

  • "Use x-ai-digest to scrape today's AI hot topics from X"
  • "Use x-ai-digest to summarize AI posts from yesterday in English"
  • "Generate an X platform AI digest for 2026-01-20 using x-ai-digest"
  • "Use x-ai-digest to compile recent AI tweets with reply suggestions"
  • "Use x-ai-digest to scrape today's AI hot topics from X"
  • "Use x-ai-digest to summarize AI posts from yesterday in English"
  • "Generate an X platform AI digest for 2026-01-20 using x-ai-digest"
  • "Use x-ai-digest to compile recent AI tweets with reply suggestions"

日本語

Japanese (Translated)

  • "x-ai-digest で今日のAI関連投稿を日本語で要約して"
  • "x-ai-digest で昨日のXプラットフォームのAI動向を取得して"
  • "x-ai-digest を使って最近のAI関連ツイートをまとめて"
  • "x-ai-digest で一昨日のAI投稿を収集して返信提案を作成して"
<!-- i18n-examples:end -->
  • "Use x-ai-digest to summarize today's AI-related posts in Japanese"
  • "Use x-ai-digest to obtain yesterday's AI trends on X platform"
  • "Use x-ai-digest to organize recent AI-related tweets"
  • "Use x-ai-digest to collect AI posts from the day before yesterday and create reply suggestions"
<!-- i18n-examples:end -->

目标

Objectives

从 X 平台主页的「为你推荐」栏目抓取指定日期的 AI 相关信息，生成结构化的每日简报：
  • 交付物：1 份 Markdown 简报 + 1 份 JSON 原始数据 + 1 张公众号分享图片
  • 每条帖子：时间、作者、内容、原文链接
  • 简报内容：热点话题汇总、产品发布、精选帖子、回复建议
  • 分享图片：卡片式设计，包含今日热点摘要，适合公众号/朋友圈分享
  • 默认输出：中文（英文/日文内容需翻译）
Scrape AI-related information for a specified date from the "For You" section of the X platform homepage, and generate a structured daily digest:
  • Deliverables: 1 Markdown digest + 1 JSON raw data file + 1 WeChat official account share image
  • Each post includes: Time, Author, Content, Original link
  • Digest content: Hot topic summary, product releases, selected posts, reply suggestions
  • Share image: Card-style design with today's hot topic summary, suitable for sharing on WeChat official accounts/Moments
  • Default output: Chinese (English/Japanese content needs to be translated)

前置条件

Prerequisites

  1. dev-browser skill 已安装并运行
    • 需要使用浏览器扩展模式连接到已登录 X 的浏览器
    • 启动命令：
      cd skills/dev-browser && npm run start-extension
  2. X 账号已登录
    • 用户需要在 Chrome 浏览器中登录 X 账号
    • 确保能访问「为你推荐」栏目
  1. dev-browser skill is installed and running
    • Need to use browser extension mode to connect to a browser logged into X
    • Startup command: 
      cd skills/dev-browser && npm run start-extension
  2. X account is logged in
    • Users need to log into their X account in Chrome browser
    • Ensure access to the "For You" section

输入（先问清）

Input (Confirm First)

参数说明默认值
日期抓取哪天的数据今天 (YYYY-MM-DD)
数量范围目标帖子数量50-100 条
输出目录简报保存位置当前工作目录
是否生成回复是否为精选帖子生成回复建议是
ParameterDescriptionDefault Value
DateWhich day's data to scrapeToday (YYYY-MM-DD)
Quantity RangeTarget number of posts50-100 posts
Output DirectorySave location for the digestCurrent working directory
Generate RepliesWhether to generate reply suggestions for selected postsYes

流程

Workflow

第一步：连接浏览器并访问 X 主页

Step 1: Connect to Browser and Access X Homepage

javascript
// 使用 dev-browser 连接已登录的浏览器
const client = await connect();
const page = await client.page("x-home", { viewport: { width: 1920, height: 1080 } });

// 访问 X 主页
await page.goto("https://x.com/home");
await waitForPageLoad(page);

// 切换到「为你推荐」标签
await page.click('text=为你推荐');
await page.waitForTimeout(3000);
javascript
// Connect to logged-in browser using dev-browser
const client = await connect();
const page = await client.page("x-home", { viewport: { width: 1920, height: 1080 } });

// Access X homepage
await page.goto("https://x.com/home");
await waitForPageLoad(page);

// Switch to "For You" tab
await page.click('text=For You');
await page.waitForTimeout(3000);

第二步：滚动抓取帖子

Step 2: Scroll and Scrape Posts

循环滚动页面，提取每条帖子的：
  • tweetId
    - 帖子唯一 ID
  • tweetUrl
    - 原文链接 (
    https://x.com/{username}/status/{tweet_id}
    )
  • datetime
    - ISO 8601 格式的发布时间
  • username
    - 用户名
  • displayName
    - 显示名称
  • content
    - 帖子内容
详细实现见 
references/scraping-guide.md
Loop to scroll the page and extract the following information for each post:
  • tweetId
    - Unique post ID
  • tweetUrl
    - Original link (
    https://x.com/{username}/status/{tweet_id}
    )
  • datetime
    - Publication time in ISO 8601 format
  • username
    - Username
  • displayName
    - Display name
  • content
    - Post content
Detailed implementation can be found in 
references/scraping-guide.md

第三步：时间筛选

Step 3: Time Filtering

将 UTC 时间转换为北京时间 (UTC+8) 进行筛选：
javascript
// 北京时间 YYYY-MM-DD 对应的 UTC 时间范围
// 北京时间 00:00:00 = UTC 前一天 16:00:00
// 北京时间 23:59:59 = UTC 当天 15:59:59
const startUTC = new Date(`${date.slice(0, 4)}-${date.slice(5, 7)}-${parseInt(date.slice(8, 10)) - 1}T16:00:00.000Z`);
const endUTC = new Date(`${date}T15:59:59.999Z`);
Convert UTC time to Beijing Time (UTC+8) for filtering:
javascript
// UTC time range corresponding to Beijing Time YYYY-MM-DD
// Beijing Time 00:00:00 = UTC 16:00:00 of the previous day
// Beijing Time 23:59:59 = UTC 15:59:59 of the same day
const startUTC = new Date(`${date.slice(0, 4)}-${date.slice(5, 7)}-${parseInt(date.slice(8, 10)) - 1}T16:00:00.000Z`);
const endUTC = new Date(`${date}T15:59:59.999Z`);

第四步：去重与数量控制

Step 4: Deduplication and Quantity Control

  • 使用 
    tweetId
    去重
  • 累计到 50 条时可以停止，最多抓取 100 条
  • 如果滚动多次仍未达到 50 条，则以实际数量为准
  • 连续 10 次滚动无新数据时停止
  • Use 
    tweetId
    for deduplication
  • Stop when 50 posts are accumulated, maximum 100 posts
  • If 50 posts are not reached after multiple scrolls, use the actual number
  • Stop when no new data is found after 10 consecutive scrolls

第五步：筛选 AI 相关内容

Step 5: Filter AI-Related Content

使用关键词匹配筛选 AI 相关帖子，关键词列表见 
references/ai-keywords.md
Filter AI-related posts using keyword matching, see 
references/ai-keywords.md
for the keyword list

第六步：生成简报

Step 6: Generate Digest

使用模板 
assets/digest-template.md
生成简报，包含：
  1. 今日热点话题
  2. 重要产品/功能发布
  3. 行业观察
  4. 精选帖子及回复建议
  5. 值得关注的账号
回复建议规则：
  • 使用帖子原文语言生成回复
  • 非中文帖子需附中文说明
  • 回复内容要有价值，避免空洞夸赞
Generate the digest using the template 
assets/digest-template.md
, including:
  1. Today's hot topics
  2. Important product/function releases
  3. Industry observations
  4. Selected posts and reply suggestions
  5. Accounts worth following
Reply suggestion rules:
  • Generate replies in the original language of the post
  • Attach Chinese explanations for non-Chinese posts
  • Reply content should be valuable, avoid empty compliments

第七步：生成公众号分享图片

Step 7: Generate WeChat Official Account Share Image

基于 
assets/share-card-template.html
生成分享卡片：
  1. 生成 HTML 文件：根据今日热点填充模板
  2. 截图生成 PNG：使用 playwright 截取 
    .card
    元素
javascript
import { chromium } from "playwright";

const browser = await chromium.launch({ headless: true });
const page = await browser.newPage({ viewport: { width: 900, height: 1800 } });

await page.goto(`file://${htmlPath}`);
await page.waitForTimeout(2000);

// 只截取 .card 元素，不要背景
const card = await page.$('.card');
await card.screenshot({
  path: `${outputDir}/ai-digest-${date}.png`,
  type: "png"
});

await browser.close();
卡片内容包含：
  • 标题和日期
  • 今日 3-4 个热点话题摘要
  • 统计数据（帖子数、话题数、产品发布数）
  • 数据来源标注
Generate a share card based on 
assets/share-card-template.html
:
  1. Generate HTML file: Fill the template with today's hot topics
  2. Screenshot to generate PNG: Use playwright to capture the 
    .card
    element
javascript
import { chromium } from "playwright";

const browser = await chromium.launch({ headless: true });
const page = await browser.newPage({ viewport: { width: 900, height: 1800 } });

await page.goto(`file://${htmlPath}`);
await page.waitForTimeout(2000);

// Capture only the .card element, exclude background
const card = await page.$('.card');
await card.screenshot({
  path: `${outputDir}/ai-digest-${date}.png`,
  type: "png"
});

await browser.close();
Card content includes:
  • Title and date
  • Summaries of 3-4 hot topics today
  • Statistical data (number of posts, topics, product releases)
  • Data source annotation

护栏

Guardrails

  • 只抓取公开可见的帖子，不尝试绑定登录或绕过限制
  • 滚动间隔 >= 1 秒，避免触发反爬机制
  • 如遇网络错误或页面异常，降级输出已抓取的数据
  • 输出文件前确认路径，避免覆盖已有文件
  • 翻译时保留原文链接，确保可追溯
  • Only scrape publicly visible posts, do not attempt to bind login or bypass restrictions
  • Scroll interval >= 1 second to avoid triggering anti-crawling mechanisms
  • In case of network errors or page exceptions, downgrade to output the already scraped data
  • Confirm the path before outputting files to avoid overwriting existing files
  • Keep original links during translation to ensure traceability

输出示例

Output Examples

文件结构

File Structure

{output_dir}/
├── x-posts-{date}.json      # 原始数据
├── x-posts-{date}.md        # 帖子列表表格
├── AI简报-{date}.md         # 完整简报
└── ai-digest-{date}.png     # 公众号分享图片
{output_dir}/
├── x-posts-{date}.json      # Raw data
├── x-posts-{date}.md        # Post list table
├── AI-Digest-{date}.md      # Complete digest
└── ai-digest-{date}.png     # WeChat official account share image

简报结构

Digest Structure

markdown
undefined
markdown
undefined

AI 每日简报 | {date}

Daily AI Digest | {date}

一、今日热点话题

1. Today's Hot Topics

🔥 话题1

🔥 Topic 1

🆕 话题2

🆕 Topic 2

...
...

二、精选帖子及回复建议

2. Selected Posts and Reply Suggestions

1. 作者 - 话题

1. Author - Topic

原文：... 链接：... 建议回复（语言）：... 中文说明：...（如非中文）
Original: ... Link: ... Suggested Reply (Language): ... Chinese Explanation: ... (if non-Chinese)

三、今日金句

3. Quote of the Day

...
...

四、值得关注的账号

4. Accounts Worth Following

...
undefined
...
undefined

资源

Resources

  • 抓取实现指南：
    references/scraping-guide.md
  • AI 关键词列表：
    references/ai-keywords.md
  • 简报模板：
    assets/digest-template.md
  • 分享卡片模板：
    assets/share-card-template.html
  • 分享卡片生成指南：
    references/share-card-guide.md
  • Scraping implementation guide: 
    references/scraping-guide.md
  • AI keyword list: 
    references/ai-keywords.md
  • Digest template: 
    assets/digest-template.md
  • Share card template: 
    assets/share-card-template.html
  • Share card generation guide: 
    references/share-card-guide.md