Lark Workflow Social Tracker logo

Lark Workflow Social Tracker

Community
liangdabiao
lark-workflow-social-tracker

社交媒体数据追踪:维护社交媒体账号配置,通过AI获取公开数据生成每日快照,支持长期趋势分析。当用户需要'社交数据'、'平台数据'、'粉丝趋势'、'内容表现'、'数据追踪'时使用。

Overview

Publisherliangdabiao
Repositorylark-workflow-feishu-cli
Skill namelark-workflow-social-tracker
Stars
68
Forks
10
Bundled files
Instructions only
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by liangdabiao on GitHub. Read the source before you install it.

Installation

Install the Lark Workflow Social Tracker AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/liangdabiao/lark-workflow-feishu-cli/tree/main/.claude/skills/lark-workflow-social-tracker
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/liangdabiao/lark-workflow-feishu-cli.git /tmp/lark-workflow-feishu-cli
mkdir -p .claude/skills
cp -r /tmp/lark-workflow-feishu-cli/.claude/skills/lark-workflow-social-tracker .claude/skills/lark-workflow-social-tracker
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Lark Workflow Social Tracker in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Lark Workflow Social Tracker on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Lark Workflow Social Tracker is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

社交媒体数据追踪工作流

CRITICAL — 开始前 MUST 先用 Read 工具读取 ../lark-shared/SKILL.md,其中包含认证、权限处理

适用场景

  • "帮我记录今天的社交数据" / "数据快照"
  • "这周哪个平台增长最快?" / "粉丝趋势"
  • "最近哪条内容表现最好?" / "内容表现分析"
  • "YouTube 和 Instagram 的互动趋势有什么不同?" / "跨平台对比"
  • "添加/删除社交账号" / "账号管理"

前置条件

仅支持 user 身份。执行前确保已授权:

bash
lark-cli auth login --domain base,sheets,im

数据来源说明: 框架阶段,社交媒体数据通过以下方式获取:

  1. AI WebSearch:搜索公开可用的社交媒体数据(如 Social Blade)
  2. 用户手动录入:用户直接提供数据,AI 记录到多维表格
  3. API 接入(未来):预留外部 API 接入点,后续可接入各平台官方 API

工作流总览

账号管理:
  base +record-upsert ──► 维护账号配置

数据采集:
  ├── WebSearch ──────────► 获取公开数据(框架阶段)
  ├── 用户手动输入 ────────► 直接录入数据
  └── [未来] API 调用 ────► 官方 API

数据存储:
  base +record-upsert ──► 每日快照 + 内容表现

趋势分析:
  base +record-list ──► 历史数据 ──► AI 分析趋势
  sheets +write ──────► 生成分析报表

通知:
  im +messages-send ──► 里程碑/异常通知

数据初始化

Base 表结构

表 1:账号配置 (social_accounts)

字段名类型说明
平台单选YouTube/Instagram/Twitter(X)/TikTok/微信公众号/B站/其他
账号名文本账号显示名
账号ID文本平台唯一标识(@handle 或数字ID)
主页链接URL账号主页 URL
类别单选个人/品牌/公司/项目
状态单选活跃/暂停/已关闭
备注文本自由备注
追踪开始日期日期开始追踪的日期

表 2:每日快照 (daily_snapshots)

字段名类型说明
平台文本平台名称
账号ID文本关联账号
快照日期日期数据日期
粉丝数数字总粉丝/关注者数
关注数数字关注了多少账号
内容总数数字发布的内容总数
新增粉丝数字当日新增粉丝数(与前一天对比)
新增内容数字当日发布的内容数
互动率数字当日互动率(%),如可获取
总点赞数字所有内容总点赞数
总评论数字所有内容总评论数
备注文本当日特别事件(如上了热门)
数据来源单选WebSearch/手动录入/API

表 3:内容表现 (content_performance)

字段名类型说明
平台文本平台名称
账号ID文本关联账号
内容ID文本内容的唯一标识
内容标题文本标题或描述
内容类型单选视频/图文/直播/短视频/推文/文章
发布日期日期发布时间
点赞数数字当日点赞
评论数数字当日评论
分享数数字当日分享/转发
播放数数字播放/浏览次数
互动率数字互动率(%)
备注文本如上了热门/被推荐等
数据来源单选WebSearch/手动录入/API

初始化命令

bash
# 注意:+table-create 可能部分成功,需捕获错误后用 +field-create 补字段
# 注意:连续创建字段会触发限流(错误码 800004135),每次调用间隔至少 1 秒
lark-cli base +table-create --name "社交账号" --fields '[
  {"name":"平台","type":"select","multiple":false,"options":[{"name":"YouTube"},{"name":"Instagram"},{"name":"Twitter(X)"},{"name":"TikTok"},{"name":"微信公众号"},{"name":"B站"},{"name":"其他"}]},
  {"name":"账号名","type":"text"},
  {"name":"账号ID","type":"text"},
  {"name":"主页链接","type":"link"},
  {"name":"类别","type":"select","multiple":false,"options":[{"name":"个人"},{"name":"品牌"},{"name":"公司"},{"name":"项目"}]},
  {"name":"状态","type":"select","multiple":false,"options":[{"name":"活跃"},{"name":"暂停"},{"name":"已关闭"}]},
  {"name":"备注","type":"text"},
  {"name":"追踪开始日期","type":"datetime"}
]'
lark-cli base +table-create --name "每日快照" --fields '[
  {"name":"平台","type":"text"},
  {"name":"账号ID","type":"text"},
  {"name":"快照日期","type":"datetime"},
  {"name":"粉丝数","type":"number"},
  {"name":"关注数","type":"number"},
  {"name":"内容总数","type":"number"},
  {"name":"新增粉丝","type":"number"},
  {"name":"新增内容","type":"number"},
  {"name":"互动率","type":"number"},
  {"name":"总点赞","type":"number"},
  {"name":"总评论","type":"number"},
  {"name":"备注","type":"text"},
  {"name":"数据来源","type":"select","multiple":false,"options":[{"name":"WebSearch"},{"name":"手动录入"},{"name":"API"}]}
]'
lark-cli base +table-create --name "内容表现" --fields '[
  {"name":"平台","type":"text"},
  {"name":"账号ID","type":"text"},
  {"name":"内容ID","type":"text"},
  {"name":"内容标题","type":"text"},
  {"name":"内容类型","type":"select","multiple":false,"options":[{"name":"视频"},{"name":"图文"},{"name":"直播"},{"name":"短视频"},{"name":"推文"},{"name":"文章"}]},
  {"name":"发布日期","type":"datetime"},
  {"name":"点赞数","type":"number"},
  {"name":"评论数","type":"number"},
  {"name":"分享数","type":"number"},
  {"name":"播放数","type":"number"},
  {"name":"互动率","type":"number"},
  {"name":"备注","type":"text"},
  {"name":"数据来源","type":"select","multiple":false,"options":[{"name":"WebSearch"},{"name":"手动录入"},{"name":"API"}]}
]'

限流处理:如果 +table-create 因限流部分失败,表仍会创建成功。此时:

  1. 用 base +table-list 获取 table_id
  2. 用 base +field-create --table-id <id> --json '{"name":"字段名","type":"text"}' 逐个补字段,每次间隔 1-2 秒

模式一:账号管理

添加账号

bash
lark-cli base +record-upsert --table-id "<accounts_table_id>" --json '{
  "平台": "YouTube",
  "账号名": "MyChannel",
  "账号ID": "@mychannel",
  "主页链接": "https://youtube.com/@mychannel",
  "类别": "个人",
  "状态": "活跃",
  "追踪开始日期": "2026-03-31"
}'

查看账号列表

bash
lark-cli base +record-list --table-id "<accounts_table_id>" --filter '...状态 = "活跃"'

模式二:每日快照

方式 A:WebSearch 获取(框架阶段)

AI 处理:

  1. 获取活跃账号列表
  2. 通过 WebSearch 搜索各账号的公开数据
  3. 搜索关键词如:"@handle Social Blade"、"@handle subscribers count"
  4. 提取粉丝数、内容数等数据
  5. 与前一天快照对比,计算增量

方式 B:手动录入

用户直接提供数据:

  • "YouTube 今天 1000 粉丝了"
  • "Instagram 昨天涨了 50 个粉丝"

AI 处理:

  1. 解析用户提供的数字
  2. 查找前一天的快照
  3. 计算增量
  4. 记录到快照表

记录快照

bash
lark-cli base +record-upsert --table-id "<snapshots_table_id>" --json '{
  "平台": "YouTube",
  "账号ID": "@mychannel",
  "快照日期": "2026-03-31",
  "粉丝数": 1000,
  "关注数": 50,
  "内容总数": 45,
  "新增粉丝": 12,
  "新增内容": 1,
  "数据来源": "WebSearch"
}'

模式三:内容表现记录

记录内容数据

bash
lark-cli base +record-upsert --table-id "<content_table_id>" --json '{
  "平台": "YouTube",
  "账号ID": "@mychannel",
  "内容ID": "abc123",
  "内容标题": "如何使用飞书CLI",
  "内容类型": "视频",
  "发布日期": "2026-03-30",
  "点赞数": 150,
  "评论数": 30,
  "分享数": 10,
  "播放数": 5000
}'

模式四:趋势分析

跨平台对比

bash
# 获取指定时间范围的快照
lark-cli base +record-list --table-id "<snapshots_table_id>" --filter '...快照日期 >= "30天前"'

AI 分析:

  1. 计算各平台的增长率和增长趋势
  2. 对比不同平台的互动率
  3. 识别增长最快的平台和最慢的平台
  4. 分析发布频率与增长的关系

输出格式

## 社交媒体趋势报告({日期范围})

### 增长概览
| 平台 | 起始粉丝 | 结束粉丝 | 增长率 | 新增内容 | 互动率 |
|------|---------|---------|--------|---------|--------|
| YouTube | 800 | 1000 | +25% | 4 | 3.2% |
| Instagram | 500 | 550 | +10% | 10 | 5.1% |
| Twitter | 200 | 230 | +15% | 25 | 1.8% |

### 关键发现
- 增长最快:YouTube(+25%)
- 互动率最高:Instagram(5.1%)
- 发布最活跃:Twitter(25条内容)
- 建议:YouTube虽然增长快,但内容产出较少,考虑增加发布频率

### 内容表现 TOP 5
| 平台 | 内容标题 | 点赞 | 评论 | 互动率 |
|------|---------|------|------|--------|
| YT | 如何使用飞书CLI | 150 | 30 | 3.6% |
...

生成报表(可选)

将趋势分析保存为飞书电子表格:

bash
lark-cli sheets +create --title "社交媒体趋势 ({日期范围})" --data "<表格数据>"

模式五:里程碑通知

当检测到重要变化时发送飞书消息通知:

  • 粉丝数达到整数里程碑(1000、5000、10000...)
  • 单日新增粉丝创历史新高
  • 某内容表现异常好(互动率超过平均值 3 倍)
  • 出现负增长(掉粉)
bash
lark-cli im +messages-send --chat-id "<chat_id>" --markdown "<通知内容>"

模式六:定时快照

使用 CronCreate 设置每日自动采集:

# 每天晚上 22:30 自动采集社交媒体数据
CronCreate: cron="30 22 * * *", prompt="采集今天的社交媒体数据快照,记录到多维表格", recurring=true

未来扩展:API 接入

以下为预留的外部 API 接入点,后续可逐步实现:

平台API数据类型
YouTubeYouTube Data API v3粉丝数、播放量、互动
InstagramInstagram Graph API粉丝数、互动、Stories 数据
Twitter/XTwitter API v2粉丝数、推文互动
TikTokTikTok Content Posting API粉丝数、视频数据
B站B站 API粉丝数、播放量、互动
微信公众号微信公众平台 API粉丝数、阅读量

当 API 接入后,将 数据来源 字段从 "WebSearch" 更新为 "API",快照采集将变为自动化。


权限表

命令所需 scope
base +table-createbitable:app
base +record-listbitable:app:read
base +record-upsertbitable:app:write
sheets +createsheets:spreadsheet:create
sheets +writesheets:spreadsheet:write
im +messages-sendim:message:send_as_bot

参考

Frequently asked questions

What does the Lark Workflow Social Tracker AI skill do?

社交媒体数据追踪:维护社交媒体账号配置,通过AI获取公开数据生成每日快照,支持长期趋势分析。当用户需要'社交数据'、'平台数据'、'粉丝趋势'、'内容表现'、'数据追踪'时使用。

Why use Lark Workflow Social Tracker on TypingMind?

Because you install it once and use it with any model. Lark Workflow Social Tracker is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Lark Workflow Social Tracker in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/liangdabiao/lark-workflow-feishu-cli/tree/main/.claude/skills/lark-workflow-social-tracker. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Lark Workflow Social Tracker?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Lark Workflow Social Tracker?

As many as you like. As long as a model supports skills, you can use Lark Workflow Social Tracker with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Lark Workflow Social Tracker AI skill free?

It is published on GitHub by liangdabiao. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇