CRITICAL — Before starting, you MUST first use the Read tool to read ../lark-shared/SKILL.md, which contains authentication and permission handling
Use Cases
- "Help me record today's social data" / "Data snapshot"
- "Which platform grew fastest this week?" / "Follower trends"
- "Which content performed best recently?" / "Content performance analysis"
- "What are the differences in engagement trends between YouTube and Instagram?" / "Cross-platform comparison"
- "Add/remove social accounts" / "Account management"
Prerequisites
Only supports user identity. Ensure authorization before execution:
lark-cli auth login --domain base,sheets,im
Data source description: At the framework stage, social media data is obtained through the following methods:
- AI WebSearch: Search publicly available social media data (such as Social Blade)
- Manual user entry: Users provide data directly, and AI records it into the multidimensional table
- API integration (future): Reserve external API integration points, which can later connect to official APIs of various platforms
Workflow Overview
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
Data Initialization
Base Table Structure
Table 1: Account Configuration (social_accounts)
| Field Name | Type | Description |
|---|---|---|
| Platform | Single select | YouTube/Instagram/Twitter(X)/TikTok/WeChat Official Account/Bilibili/Other |
| Account Name | Text | Account display name |
| Account ID | Text | Platform unique identifier (@handle or numeric ID) |
| Homepage Link | URL | Account homepage URL |
| Category | Single select | Personal/Brand/Company/Project |
| Status | Single select | Active/Paused/Closed |
| Notes | Text | Free-form notes |
| Tracking Start Date | Date | Date tracking started |
Table 2: Daily Snapshots (daily_snapshots)
| Field Name | Type | Description |
|---|---|---|
| Platform | Text | Platform name |
| Account ID | Text | Associated account |
| Snapshot Date | Date | Data date |
| Follower Count | Number | Total followers/followers count |
| Following Count | Number | How many accounts are followed |
| Total Content | Number | Total number of published content |
| New Followers | Number | Number of new followers that day (compared with the previous day) |
| New content | Number | Number of content published that day |
| Engagement rate | Number | Engagement rate that day (%), if available |
| Total likes | Number | Total likes across all content |
| Total comments | Number | Total comments across all content |
| Notes | Text | Special events that day (such as trending) |
| Data source | Single select | WebSearch/Manual entry/API |
Table 3: Content performance (content_performance)
| Field name | Type | Description |
|---|---|---|
| Platform | Text | Platform name |
| Account ID | Text | Associated account |
| Content ID | Text | Unique identifier of the content |
| Content title | Text | Title or description |
| Content type | Single select | Video/Image-text/Live/Short video/Post/Article |
| Publish date | Date | Publish time |
| Likes | Number | Likes that day |
| Comments | Number | Comments that day |
| Shares | Number | Shares/reposts that day |
| Views | Number | Plays/views |
| Engagement rate | Number | Engagement rate (%) |
| Notes | Text | Such as trending/recommended, etc. |
| Data source | Single select | WebSearch/Manual entry/API |
Initialization command
# 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"}]}
]'
Rate limit handling: If +table-create partially fails due to rate limiting, the table will still be created successfully. In this case:
- Use
base +table-listto get the table_id- Use
base +field-create --table-id <id> --json '{"name":"字段名","type":"text"}'to add fields one by one, with an interval of 1-2 seconds each time
Mode 1: Account management
Add account
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"
}'
View account list
lark-cli base +record-list --table-id "<accounts_table_id>" --filter '...状态 = "活跃"'
Mode 2: Daily snapshot
Method A: WebSearch retrieval (framework stage)
AI processing:
- Get the list of active accounts
- Search for each account's public data via WebSearch
- Search keywords such as: "@handle Social Blade", "@handle subscribers count"
- Extract data such as follower count and content count
- Compare with the previous day's snapshot and calculate the increment
Method B: Manual entry
The user provides data directly:
- "YouTube reached 1000 followers today"
- "Instagram gained 50 followers yesterday"
AI processing:
- Parse the numbers provided by the user
- Look up the previous day's snapshot
- Calculate the delta
- Record to the snapshot table
Record snapshot
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"
}'
Mode 3: Content performance recording
Record content data
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
}'
Mode 4: Trend analysis
Cross-platform comparison
# 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 analysis:
- Calculate the growth rate and growth trend of each platform
- Compare the engagement rates of different platforms
- Identify the fastest-growing platform and the slowest-growing platform
- Analyze the relationship between posting frequency and growth
Output format
## 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% |
...
Generate report (optional)
Save the trend analysis as a Feishu spreadsheet:
lark-cli sheets +create --title "社交媒体趋势 ({日期范围})" --data "<表格数据>"
Mode 5: Milestone notifications
Send a Feishu message notification when an important change is detected:
- Follower count reaches an integer milestone (1000, 5000, 10000...)
- Single-day new followers hit a record high
- A piece of content performs exceptionally well (engagement rate exceeds 3 times the average)
- Negative growth occurs (losing followers)
lark-cli im +messages-send --chat-id "<chat_id>" --markdown "<通知内容>"
Mode 6: Scheduled snapshots
Use CronCreate to set up daily automatic collection:
# 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
Future extension: API integration
The following are reserved external API integration points that can be gradually implemented later:
| Platform | API | Data type |
|---|---|---|
| YouTube | YouTube Data API v3 | Follower count, play count, engagement |
| Instagram Graph API | Follower count, engagement, Stories data | |
| Twitter/X | Twitter API v2 | Follower count, tweet engagement |
| TikTok | TikTok Content Posting API | Follower count, video data |
| Bilibili | Bilibili API | Follower count, play count, engagement |
| WeChat Official Account | WeChat Official Platform API | Follower count, read count |
After the API is integrated, update the
数据来源field from "WebSearch" to "API", and snapshot collection will become automated.
Permissions table
| Command | Required scope |
|---|---|
base +table-create |
bitable:app |
base +record-list |
bitable:app:read |
base +record-upsert |
bitable:app:write |
sheets +create |
sheets:spreadsheet:create |
sheets +write |
sheets:spreadsheet:write |
im +messages-send |
im:message:send_as_bot |
Reference
lark-shared— Authentication, permissions (required reading)lark-base—+table-create、+record-list、+record-upsertDetailed usagelark-sheets—+create、+writeDetailed usagelark-im—+messages-sendDetailed usagelark-workflow-business-advisor— Business advisory group (data linkage)