SuperAPI AI Directory
Partner with us中文AI newsFavorites
Skillswecomcli-workflow-business-advisor

wecomcli-workflow-business-advisor

Office & productivity

View repository

Updated 10-15 23:59

About this skill

WeCom AI Business Advisory Board

Through 8 AI advisor roles, automatically analyze business data and generate a comprehensive business analysis report.

Initial Configuration (Automatic Initialization)

Before performing any operation, first check whether the business advisory board configuration already exists in memory. If not, automatically create it according to the following process:

Step 1: Create a smart sheet

wecom-cli doc create_doc '{"doc_type": 10, "doc_name": "商业顾问团"}'

Obtain from the returned result docid。

Step 2: Create subtables and fields

# 创建子表1: 顾问分析记录
wecom-cli doc smartsheet_add_sheet '{"docid": "<DOCID>", "sheet_name": "分析记录"}'

# 创建子表2: 用户反馈
wecom-cli doc smartsheet_add_sheet '{"docid": "<DOCID>", "sheet_name": "用户反馈"}'

Analysis record fields:

wecom-cli doc smartsheet_add_fields '{"docid": "<DOCID>", "sheet_id": "<SHEET_ID>", "fields": [
  {"field_title": "分析日期", "field_type": "FIELD_TYPE_TEXT"},
  {"field_title": "顾问角色", "field_type": "FIELD_TYPE_SINGLE_SELECT"},
  {"field_title": "分析摘要", "field_type": "FIELD_TYPE_TEXT"},
  {"field_title": "优先级", "field_type": "FIELD_TYPE_SINGLE_SELECT"},
  {"field_title": "状态", "field_type": "FIELD_TYPE_SINGLE_SELECT"}
]}'

User feedback fields:

wecom-cli doc smartsheet_add_fields '{"docid": "<DOCID>", "sheet_id": "<SHEET_ID>", "fields": [
  {"field_title": "分析ID", "field_type": "FIELD_TYPE_TEXT"},
  {"field_title": "用户选择", "field_type": "FIELD_TYPE_TEXT"},
  {"field_title": "展开详情", "field_type": "FIELD_TYPE_TEXT"},
  {"field_title": "处理时间", "field_type": "FIELD_TYPE_TEXT"}
]}'

Step 3: Save the configuration to memory

Save the following information to the memory file business-advisor-config.md：

---
name: business-advisor-config
description: 商业顾问团智能表格配置信息
type: project
---

## 商业顾问团表配置

- docid: <DOCID>
- url: <创建时返回的URL>
- 表格名称: 商业顾问团
- 分析记录 sheet_id: <SHEET_ID>
- 用户反馈 sheet_id: <SHEET_ID>

Operation Process

In the following commands, <DOCID> and each <SHEET_ID> are read from business-advisor-config in memory. For advisor role Prompt templates, see prompt-templates.md。

Mode 1: Run Full Analysis

Step 1: Collect all available data

# 联系人数据（如果个人 CRM 已初始化）
wecom-cli doc smartsheet_get_records '{"docid": "<个人CRM_DOCID>", "sheet_id": "<联系人SHEET_ID>"}'

# 社交数据（如果社交追踪已初始化）
wecom-cli doc smartsheet_get_records '{"docid": "<社交追踪_DOCID>", "sheet_id": "<每日快照SHEET_ID>"}'
wecom-cli doc smartsheet_get_records '{"docid": "<社交追踪_DOCID>", "sheet_id": "<内容表现SHEET_ID>"}'

# 创意库数据（如果内容管道已初始化）
wecom-cli doc smartsheet_get_records '{"docid": "<内容管道_DOCID>", "sheet_id": "<创意库SHEET_ID>"}'

# 投资数据（如果股票分析已初始化）
wecom-cli doc smartsheet_get_records '{"docid": "<股票分析_DOCID>", "sheet_id": "<自选股SHEET_ID>"}'
wecom-cli doc smartsheet_get_records '{"docid": "<股票分析_DOCID>", "sheet_id": "<分析记录SHEET_ID>"}'

# 待办数据
wecom-cli todo get_todo_list '{}'

# 日程数据
wecom-cli schedule get_schedule_list_by_range '{"start_time": "<今天>", "end_time": "<今天>"}'

Step 2: 8 advisors analyze in parallel

The AI uses 8 advisor role prompt templates (see references/prompt-templates.md), and each advisor independently analyzes the available data.

If a data source is not initialized, the corresponding advisor is marked "insufficient data, skipped".

Step 3: Summarize, deduplicate, and sort

The AI uses the summary secretary prompt to merge all advisors' suggestions, deduplicate, and sort them.

Step 4: Send the numbered list

wecom-cli msg send_message '{"chat_type": 1, "chatid": "<USERID>", "msgtype": "text", "text": {"content": "## 今日商业顾问团报告（4/2）\n\n### 总览\n今日共 6 条建议，来自 5 位顾问。\n数据来源：CRM(有)、社交追踪(有)、创意库(有)、投资(无)\n\n### 建议清单\n1. 【关系】张三（XX科技）已 45 天未联系，建议主动跟进\n2. 【财务】投资组合本周下跌 5%，建议检查持仓比例\n3. 【内容】本周发布频率下降 40%，建议安排时间完成选题\n4. 【运营】7 个任务已过期未完成\n5. 【风险】竞品 YY 本周发布新功能\n6. 【增长】Instagram 增长势头良好，建议加大投入\n\n回复编号展开详细分析"}}'

Step 5: Save the analysis record

wecom-cli doc smartsheet_add_records '{"docid": "<DOCID>", "sheet_id": "<分析记录SHEET_ID>", "records": [
  {"values": {"分析日期": [{"type":"text","text":"2026-04-02"}], "顾问角色": [{"text":"关系BD顾问"}], "分析摘要": [{"type":"text","text":"张三已45天未联系"}], "优先级": [{"text":"高"}], "状态": [{"text":"待读"}]}},
  {"values": {"分析日期": [{"type":"text","text":"2026-04-02"}], "顾问角色": [{"text":"财务顾问"}], "分析摘要": [{"type":"text","text":"投资组合本周下跌5%"}], "优先级": [{"text":"中"}], "状态": [{"text":"待读"}]}}
]}'

Mode 2: Expand Detailed Analysis

The user replies with a number, and the AI expands the detailed analysis of that suggestion.

Interaction process:

  1. User: "Tell me more about item 3"
  2. The AI finds the corresponding suggestion
  3. Uses the source advisor's prompt for in-depth analysis
  4. Outputs a detailed analysis (original suggestion, data support, recommended action steps)

Output format:

## 第 3 条展开分析

### 原始建议
本周内容发布频率下降 40%，建议安排时间完成待执行选题。

### 来源顾问：内容策略顾问

### 详细分析
- 上周发布 5 条内容，本周仅 3 条
- 创意库中有 4 个"方案已完成"状态但未执行
- YouTube 表现最好的内容类型是教程类（互动率 4.2%）

### 建议行动步骤
1. 优先执行创意库中评分最高的"AI编程工具对比"选题
2. 本周至少发布 2 条教程类内容
3. 安排 30 分钟完成"企业微信自动化"选题的资料整理

Mode 3: Save Archived Report

Save the daily analysis as a WeCom document archive.

wecom-cli doc create_doc '{"doc_type": 3, "doc_name": "商业顾问团报告 2026-04-02"}'

wecom-cli doc edit_doc_content '{"docid": "<报告DOCID>", "content": "# 商业顾问团报告 — 2026年4月2日\n\n## 总览\n...\n\n## 各顾问分析\n### 财务顾问\n...\n### 营销顾问\n...\n\n## 汇总建议清单\n1. ...\n2. ...", "content_type": 1}'

8 Advisor Roles

Role Focus Area Data Source
Financial Advisor Revenue trends, investment performance Stock analysis
Marketing Advisor Content performance, engagement rate Social tracking + content pipeline
Growth Advisor Follower growth, channel efficiency Social tracking
Operations Advisor Task completion rate, schedule density To-dos + schedule
Content Strategy Advisor Topic quality, publishing cadence Content pipeline + social tracking
Relationship/BD Advisor Network activity, partnership opportunities Personal CRM
Competition/Industry Advisor Industry trends, competitor activity Knowledge base + WebSearch
Comprehensive Risk Advisor Potential risks, weak points All data

Field Type Writing Format (General Rules)

For the complete field type format description, see crm-schema

Field Type Writing Format Example
TEXT [{"type":"text","text":"值"}] Analysis summary, etc.
SINGLE_SELECT [{"text":"选项文本"}] Advisor role, priority, status, etc.

Practical Notes

Common Pitfalls

  1. Not passing key_type when updating — must include "key_type": "CELL_VALUE_KEY_TYPE_FIELD_TITLE"
  2. When an API call fails — check the error code: 301085 means the docid is invalid (use url instead); 2022004 means the field was not found (call add_fields first); 2022003 means the record does not exist (call add_records first). When encountering an error, first use smartsheet_get_sheet '{"url": "<URL>"}' to verify the table structure.
  3. Data source not initialized — The linked Skill may not be initialized, and the AI needs to degrade gracefully (label "insufficient data" rather than report an error)
  4. Message length limit — Numbered list messages need to be concise; detailed content is provided when expanded
  5. Analysis record deduplication — When analysis is run multiple times on the same day, only keep the latest record
  6. SINGLE_SELECT options do not take effect at creation time — smartsheet_add_fields The passed-in property.options will not pre-create options; options are automatically created via [{"text": "选项"}] when a record is first written. When creating the field, the property parameter can be omitted.

Scheduled Automation Suggestions

Task Suggested Time Cron
Run the business advisor group analysis Workdays 22:00 0 22 * * 1-5
Archive daily reports Workdays 22:30 30 22 * * 1-5

Data Linkage Dependencies

This Skill reads data from the following Skills (only effective if initialized):

  • wecomcli-workflow-personal-crm — Contact activity
  • wecomcli-workflow-social-tracker — Social data
  • wecomcli-workflow-content-pipeline — Creative/content data
  • wecomcli-workflow-stock-analyzer — Investment data