Back to Details

juicebro-content-hub

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

juicebro-content-hub Skill

juicebro-content-hub Skill

概述

Overview

本 Skill 是"果汁哥内容聚合中台"，安装后 Agent 可以回答以下类型的问题：
  • 全平台总查：今天/最近 N 天/最近一周，全平台有什么更新
  • 平台单查：指定微博/小红书/抖音/B站/雪球/头条/公众号/小宇宙/喜马拉雅等平台的查询
  • 主题查询：过滤比特币、黄金、美股、AI、特朗普等特定主题的内容
  • 内容形态查询：过滤视频/文章/音频/短帖/图文等内容类型
  • 汇总报告：生成日报、周报、按平台/主题/形态的结构化摘要
  • 导航推荐：推荐适合特定内容类型的平台
重要说明：本 Skill 依赖 Agent 的公开网页访问能力获取内容，不包含内置数据爬取逻辑。部分平台存在公开索引限制，查询结果因访问环境而异。
This Skill serves as the "Juicebro Content Aggregation Platform". After installation, Agents can answer the following types of questions:
  • Full-platform Search: What updates are available across all platforms today/in the last N days/in the last week?
  • Single-platform Query: Queries for specified platforms such as Weibo, Xiaohongshu, Douyin, Bilibili, Xueqiu, Toutiao, WeChat Official Account, Xiaoyuzhou, Ximalaya, etc.
  • Topic Query: Filter content on specific topics like Bitcoin, Gold, US Stocks, AI, Trump, etc.
  • Content Type Query: Filter content types such as video, article, audio, short post, image-text post, etc.
  • Summary Report: Generate structured summaries in the form of daily reports, weekly reports, or summaries by platform/topic/content type.
  • Navigation Recommendation: Recommend platforms suitable for specific content types.
Important Note: This Skill relies on the Agent's public web access capabilities to obtain content and does not include built-in data crawling logic. Some platforms have public indexing restrictions, and query results may vary depending on the access environment.

账号矩阵（权威数据源）

Account Matrix (Authoritative Data Source)

加载 
data/accounts.json
获取完整的账号矩阵。
快速参考：
平台账号类别可查询
微博果汁哥6688日常分享✅
小红书guozhige日常分享✅
抖音果汁哥的知识分享 / Roaring_Kitty日常分享✅
快手果汁哥日常分享✅
bilibili果汁哥juicebro日常分享✅
元宝果汁哥日常分享⚠️ 待确认
微信（私域）guozhige2024日常分享❌ 私域
雪球juicebro投资主题✅
知识星球果汁哥私享圈投资主题（付费）❌ 付费
今日头条果汁哥的知识分享投资主题✅
微信公众号果汁哥的知识分享投资主题⚠️ 部分
喜马拉雅果汁哥juicebro播客✅
小宇宙果汁哥播客✅
Load 
data/accounts.json
to get the complete account matrix.
Quick Reference:
PlatformAccountCategoryQueryable
Weibo果汁哥6688Daily Sharing✅
XiaohongshuguozhigeDaily Sharing✅
Douyin果汁哥的知识分享 / Roaring_KittyDaily Sharing✅
Kuaishou果汁哥Daily Sharing✅
Bilibili果汁哥juicebroDaily Sharing✅
Yuanbao果汁哥Daily Sharing⚠️ Pending Confirmation
WeChat (Private Domain)guozhige2024Daily Sharing❌ Private Domain
XueqiujuicebroInvestment Topics✅
Zhishi Xingqiu果汁哥私享圈Investment Topics (Paid)❌ Paid
Toutiao果汁哥的知识分享Investment Topics✅
WeChat Official Account果汁哥的知识分享Investment Topics⚠️ Partial
Ximalaya果汁哥juicebroPodcast✅
Xiaoyuzhou果汁哥Podcast✅

使用流程

Usage Flow

步骤 1：意图识别

Step 1: Intent Recognition

收到用户查询后，参照 
data/query_intents.json
识别意图类型：
intent_type: all_platform_query | platform_single_query | topic_query |
             content_type_query | aggregation_report | navigation_recommend
并提取：
  • platforms
    ：用户指定的平台（无则全选 is_queryable=true 的平台）
  • time_range
    ：today / last_3_days / last_7_days / last_30_days
  • topic
    ：主题标签（参照 
    data/topic_keywords.json
    ）
  • content_type
    ：video / article / audio / short_post / image_post
  • output_format
    ：list / digest / report
After receiving a user query, refer to 
data/query_intents.json
to identify the intent type:
intent_type: all_platform_query | platform_single_query | topic_query |
             content_type_query | aggregation_report | navigation_recommend
And extract:
  • platforms
    : Platforms specified by the user (select all platforms with is_queryable=true if none specified)
  • time_range
    : today / last_3_days / last_7_days / last_30_days
  • topic
    : Topic tags (refer to 
    data/topic_keywords.json
    )
  • content_type
    : video / article / audio / short_post / image_post
  • output_format
    : list / digest / report

步骤 2：平台适配

Step 2: Platform Adaptation

对每个目标平台：
  1. 查 
    data/accounts.json
    获取账号信息
  2. 查 
    data/platform_rules.json
    确认查询策略
  3. 参照 
    adapters/{platform}.md
    了解字段提取方式和失败处理
  4. 若平台 
    is_queryable: false
    ，直接输出限制说明，跳过该平台
  5. 若平台可查询但访问结果不足，明确说明，不推测或补充内容
For each target platform:
  1. Retrieve account information from 
    data/accounts.json
  2. Check query strategies in 
    data/platform_rules.json
  3. Refer to 
    adapters/{platform}.md
    for field extraction methods and failure handling
  4. If the platform has 
    is_queryable: false
    , directly output restriction instructions and skip this platform
  5. If the platform is queryable but access results are insufficient, clearly state this without speculating or supplementing content

步骤 3：内容规范化

Step 3: Content Normalization

将各平台内容规范化为 
NormalizedPost
格式（见 
schemas/normalized_post.schema.json
）：
json
{
  "platform": "weibo",
  "account": "果汁哥6688",
  "publish_time": "2024-01-15T10:30:00+08:00",
  "title": null,
  "summary": "今天聊聊比特币最新走势...",
  "content_type": "short_post",
  "topic_tags": ["bitcoin", "crypto"],
  "source_locator": "https://weibo.com/...",
  "dedupe_hash": "a3f2c1..."
}
Normalize content from each platform into the 
NormalizedPost
format (see 
schemas/normalized_post.schema.json
):
json
{
  "platform": "weibo",
  "account": "果汁哥6688",
  "publish_time": "2024-01-15T10:30:00+08:00",
  "title": null,
  "summary": "今天聊聊比特币最新走势...",
  "content_type": "short_post",
  "topic_tags": ["bitcoin", "crypto"],
  "source_locator": "https://weibo.com/...",
  "dedupe_hash": "a3f2c1..."
}

步骤 4：去重与汇总

Step 4: Deduplication & Aggregation

  • 计算 
    dedupe_hash
    ，合并跨平台重复内容
  • 根据意图选择汇总提示：
    • 时间汇总 → 
      prompts/summarize_recent_posts.md
    • 平台汇总 → 
      prompts/summarize_by_platform.md
    • 主题汇总 → 
      prompts/summarize_by_topic.md
    • 字段提取 → 
      prompts/extract_post_fields.md
    • 无结果或受限 → 
      prompts/fallback_response.md
  • Calculate 
    dedupe_hash
    to merge duplicate content across platforms
  • Select aggregation prompts based on intent:
    • Time-based aggregation → 
      prompts/summarize_recent_posts.md
    • Platform-based aggregation → 
      prompts/summarize_by_platform.md
    • Topic-based aggregation → 
      prompts/summarize_by_topic.md
    • Field extraction → 
      prompts/extract_post_fields.md
    • No results or restricted → 
      prompts/fallback_response.md

步骤 5：输出

Step 5: Output

按 
schemas/normalized_result.schema.json
格式输出，使用 Markdown 美化。
Output in the format specified by 
schemas/normalized_result.schema.json
, formatted with Markdown for readability.

重要约束

Important Constraints

  1. 不编造内容：若平台无法访问或公开结果不足，说明原因，不推测或虚构内容
  2. 不绕过登录：付费/需登录内容直接说明受限，不尝试绕过
  3. 标注来源：每条内容必须标注 platform + account + source_locator
  4. 去重优先：跨平台相同内容合并展示，不重复列举
  5. 说明访问状态：每次查询在输出中标注各平台的访问状态（成功/受限/无内容）
  1. No Content Fabrication: If a platform is inaccessible or public results are insufficient, explain the reason without speculating or inventing content
  2. No Login Bypassing: Directly state restrictions for paid/login-required content without attempting to bypass login
  3. Source Labeling: Each piece of content must be labeled with platform + account + source_locator
  4. Deduplication Priority: Merge identical content across platforms for display, do not list duplicates
  5. Access Status Disclosure: Label the access status (success/restricted/no content) of each platform in the output for every query

扩展点

Extension Points

  • 新增平台：添加 
    adapters/{platform}.md
    + 更新 
    data/accounts.json
    和 
    data/platform_rules.json
  • 新增主题：更新 
    data/topic_keywords.json
  • 改进输出：优化 
    prompts/*.md
    中的提示模板
  • 接入真实数据源（V2）：实现 
    scripts/optional_fetcher.py
    中的平台方法
  • Add New Platforms: Add 
    adapters/{platform}.md
    + update 
    data/accounts.json
    and 
    data/platform_rules.json
  • Add New Topics: Update 
    data/topic_keywords.json
  • Improve Output: Optimize prompt templates in 
    prompts/*.md
  • Connect Real Data Sources (V2): Implement platform methods in 
    scripts/optional_fetcher.py

参考文档

Reference Documents

  • 账号矩阵
  • 平台规则
  • 查询意图
  • 主题关键词
  • 标准化 Schema
  • 架构说明
  • 支持查询列表
  • 安全声明
  • Account Matrix
  • Platform Rules
  • Query Intents
  • Topic Keywords
  • Normalized Schema
  • Architecture Description
  • Supported Queries List
  • Safety Statement