SuperAPI AI Directory
Partner with us中文AI newsFavorites
Skillslark-workflow-personal-crm

lark-workflow-personal-crm

Office & productivity

View repository

Updated 10-15 23:59

About this skill

Personal CRM Workflow

CRITICAL — Before starting, you MUST first use the Read tool to read ../lark-shared/SKILL.md, which contains authentication and permission handling

Applicable Scenarios

  • "Who contacted me last month?" / "Who have I interacted with recently"
  • "What was the last thing I talked about with the person from Company XX?" / "How is my relationship with Zhang San"
  • "Are there any important relationships I haven't contacted in over 3 months?" / "Who should I follow up with"
  • "Help me create contact profiles" / "Import contacts from email/calendar"
  • "What is this person's heat score" / "Update contact information"

Prerequisites

Only supports user identity. Before execution, ensure authorization has been granted:

lark-cli auth login --domain mail,calendar,contact,base,im

Email module degradation note: If the user has not enabled Feishu email (themail command returns error code 1230003), then:

  • The "import from email" mode is unavailable; skip the email scanning step
  • Use "import from calendar" and "supplement from contacts" as the main data sources
  • Note in the briefing that "email is not enabled; contact data comes only from calendar and contacts"

Workflow Overview

数据导入：
  ├── mail +messages ───────► 扫描邮箱 → 提取联系人 + 互动记录
  ├── calendar +agenda ─────► 扫描日历 → 提取会议参与者 + 互动记录
  └── contact +search-user ─► 补充飞书通讯录信息

数据存储：
  └── base +record-upsert ──► 多维表格（联系人 + 互动记录）

数据查询：
  └── base +record-list ────► 自然语言查询联系人

智能提醒：
  └── base +data-query ────► 筛选冷门联系人
  └── im +messages-send ───► 飞书消息提醒

Data Initialization

On first use, create the multi-dimensional table data structure:

Base Table Structure

Table 1: Contacts Main Table (contacts)

Field Name Type Description
Name Text Contact name
Company Text Company/organization
Position Text Position/role
Email Text Email address
Mobile Text Contact information
Source Single select Email/Calendar/Contacts/Manual
Relationship Type Single select Client/Partner/Colleague/Friend/Industry connection/Other
Importance Level Single select High/Medium/Low
Heat Score Number 0-100, calculated based on interaction frequency and most recent interaction time
Last Contact Time Date Time of the most recent interaction
Last Contact Content Text Summary of the most recent interaction
Notes Text Free-form notes
Creation Time Date First entry time

Table 2: Interaction Records (interactions)

Field Name Type Description
Related Contact Association Associate with "Contacts Main Table"
Interaction Time Date Time when the interaction occurred
Interaction Type Single select Email (Sent) / Email (Received) / Meeting / Message / Phone Call / Other
Interaction Summary Text A brief description of the interaction content
Topics Involved Text Topics or projects discussed
Email ID File The associated email message_id (if any)
Meeting ID Text The associated meeting_id (if any)

Initialization Command

# 1. 创建多维表格
# 注意：+table-create 可能部分成功（表创建成功但字段创建失败），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 "联系人" --fields '[
  {"name":"姓名","type":"text"},
  {"name":"公司","type":"text"},
  {"name":"职位","type":"text"},
  {"name":"邮箱","type":"text"},
  {"name":"手机","type":"text"},
  {"name":"来源","type":"select","multiple":false,"options":[{"name":"邮件"},{"name":"日历"},{"name":"通讯录"},{"name":"手动"}]},
  {"name":"关系类型","type":"select","multiple":false,"options":[{"name":"客户"},{"name":"合作伙伴"},{"name":"同事"},{"name":"朋友"},{"name":"行业人脉"},{"name":"其他"}]},
  {"name":"重要程度","type":"select","multiple":false,"options":[{"name":"高"},{"name":"中"},{"name":"低"}]},
  {"name":"热度分","type":"number"},
  {"name":"最后联系时间","type":"datetime"},
  {"name":"最后联系内容","type":"text"},
  {"name":"备注","type":"text"},
  {"name":"创建时间","type":"datetime"}
]'
lark-cli base +table-create --name "互动记录" --fields '[
  {"name":"互动时间","type":"datetime"},
  {"name":"互动类型","type":"select","multiple":false,"options":[{"name":"邮件(发)"},{"name":"邮件(收)"},{"name":"会议"},{"name":"消息"},{"name":"电话"},{"name":"其他"}]},
  {"name":"互动摘要","type":"text"},
  {"name":"涉及主题","type":"text"},
  {"name":"邮件ID","type":"text"},
  {"name":"会议ID","type":"text"}
]'
# 注：关联联系人字段需单独用 +field-create 创建（type="lookup" 需要关联目标表 ID）

# 2. 记录 base_token 和各 table_id

On first use, prompt the user to provide a Base URL or create a new multi-dimensional table.

Rate Limit Handling: If +table-create partially fails due to rate limiting, the table will still be created successfully. In this case:

  1. Use base +table-list to get the table_id
  2. 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: Data Import

Import from Mailbox

# 搜索指定时间范围的邮件
lark-cli mail +messages --folder INBOX --start-date "<YYYY-MM-DD>" --end-date "<YYYY-MM-DD>"

AI Processing Logic:

  1. Extract contact information from senders and recipients (name, email, company signature)
  2. Analyze email subject and body to generate an interaction summary (1-2 sentences)
  3. Identify interaction topics (project names, topic keywords)
  4. For each new contact: create a contact record
  5. For each interaction: create an interaction record and associate it with the contact

Filtering Rules:

  • Automatically filter out advertising emails, system notifications, and noreply addresses
  • Filter out internal automated notifications (CI/CD, calendar invitations, etc.)
  • Keep interpersonal communications with substantive content

Import from Calendar

# 获取指定时间范围的日程
lark-cli calendar +agenda --start "<ISO8601>" --end "<ISO8601>"

AI Processing Logic:

  1. Extract contacts from the event's participant list
  2. Use contact +search-user to supplement Feishu contacts information (position, department, etc.)
  3. Generate an interaction summary (meeting topic)
  4. Create/update contact records and interaction records

Supplement from Feishu Contacts

lark-cli contact +search-user --query "<联系人姓名>"

When contact information is incomplete, supplement company, position, and other information through Feishu Contacts.

Mode 2: Heat Score Calculation

Heat score calculation formula (0-100):

热度分 = 频率分(0-40) + 近期分(0-40) + 重要度分(0-20)

频率分（过去 90 天互动次数）：
  0次 → 0分
  1-3次 → 10分
  4-10次 → 20分
  11-20次 → 30分
  20次以上 → 40分

近期分（最后一次互动距今天数）：
  7天内 → 40分
  14天内 → 32分
  30天内 → 24分
  60天内 → 16分
  90天内 → 8分
  90天以上 → 0分

重要度分：
  高 → 20分
  中 → 12分
  低 → 4分

The heat score is automatically recalculated after each import of new interactions.

Mode 3: Natural Language Query

Supported natural language query types:

Query Type Example Query Method
By time "Who contacted me last month?" base +record-list Interaction records table + time filter
By company "What have I discussed with people from Company XX?" base +record-list Contacts table + company filter
By person name "How has Zhang San been lately?" base +record-list Contacts table + name filter
By heat "Who should I follow up with?" base +data-query Contacts with heat score < 30
By topic "What discussions are there about the AI project?" base +record-list Interaction records table + topic keywords
Comprehensive query "Are there any important relationships that haven't been contacted in over 3 months?" base +data-query Last contact > 90 days AND importance level = "High"

Query execution example

# 查询冷门联系人（聚合查询）
lark-cli base +data-query --base-token "<base_token>" --dsl '{
  "datasource": {"type": "table", "table": {"tableId": "<contacts_table_id>"}},
  "dimensions": [{"field_name": "姓名", "alias": "name"}, {"field_name": "重要程度", "alias": "importance"}],
  "measures": [{"field_name": "热度分", "aggregation": "avg", "alias": "avg_score"}],
  "filters": {"type": 1, "conjunction": "and", "conditions": [{"field_name": "重要程度", "operator": "is", "value": ["高"]}, {"field_name": "热度分", "operator": "isLess", "value": ["30"]}]},
  "shaper": {"format": "flat"}
}'

# 查询特定公司的联系人
lark-cli base +record-list --table-id "<contacts_table_id>" --filter '...公司 = "XX公司"'

# 查询最近互动
lark-cli base +record-list --table-id "<interactions_table_id>" --sort '互动时间 DESC' --page-size 20

Pattern 4: Smart reminders

Scheduled reminders

Filter contacts that need follow-up:

lark-cli base +data-query --base-token "<base_token>" --dsl '{
  "datasource": {"type": "table", "table": {"tableId": "<contacts_table_id>"}},
  "dimensions": [{"field_name": "姓名", "alias": "name"}],
  "measures": [{"field_name": "热度分", "aggregation": "avg", "alias": "avg_score"}],
  "filters": {"type": 1, "conjunction": "and", "conditions": [{"field_name": "重要程度", "operator": "isNot", "value": ["低"]}, {"field_name": "热度分", "operator": "isLess", "value": ["30"]}]},
  "shaper": {"format": "flat"}
}'

Generate reminder messages and send them via Feishu:

lark-cli im +messages-send --chat-id "<chat_id>" --markdown "..."

Reminder message format:

关系维护提醒

以下联系人已超过 60 天未联系：
| 姓名 | 公司 | 最后联系 | 热度分 | 建议 |
|------|------|---------|--------|------|
| 张三 | XX科技 | 75天前 | 12 | 发个消息打个招呼 |
| 李四 | YY投资 | 90天前 | 4 | 约个会议聊聊近况 |

Pattern 5: Manual operations

Add/update contacts

lark-cli base +record-upsert --table-id "<contacts_table_id>" --json '{"字段名":"值"}'

Manually add interaction records

lark-cli base +record-upsert --table-id "<interactions_table_id>" --json '{"字段名":"值"}'

Permissions table

Command Required scope
mail +messages mail:mail:read
calendar +agenda calendar:calendar.event:read
contact +search-user contact:employee.id:readonly
contact +get-user contact:employee.id:readonly
base +table-create bitable:app
base +record-list bitable:app:read
base +record-upsert bitable:app:write
base +data-query bitable:app:read
im +messages-send im:message:send_as_bot

Reference

  • lark-shared — Authentication, permissions (required reading)
  • lark-mail — Email reading, security rules
  • lark-calendar — +agenda Detailed usage
  • lark-contact — +search-user、+get-user Detailed usage
  • lark-base — +table-create、+record-list、+record-upsert、+data-query Detailed usage
  • lark-im — +messages-send Detailed usage