Now liveThe Skillselion MCP - thousands of ranked skills, loaded into your agent mid-task. No install.Get it →
breath57 avatar

Dingtalk Ai Table

  • 596 installs
  • 97 repo stars
  • Updated June 26, 2026
  • breath57/dingtalk-skills

dingtalk-ai-table is an agent skill that reads, writes, and updates structured tables in DingTalk for developers who need AI-driven automation against DingTalk workplace data.

About

dingtalk-ai-table is a breath57/dingtalk-skills agent integration listed on skills.sh with 513 installs that lets coding agents interact with DingTalk AI Tables. Agents can read rows, write new records, and update existing structured table data inside DingTalk workflows without bespoke API clients for every automation script. Developers reach for dingtalk-ai-table when building internal bots, approval flows, or ops automations that must sync with DingTalk spreadsheets used by teams in China-centric enterprise chat environments. The skill targets agent-tooling scenarios where table state is the system of record for lightweight business processes.

  • Agent skill that connects Claude, Cursor and other LLMs directly to DingTalk AI tables
  • Supports reading table data, creating records, and updating cells via natural language
  • Exposes structured data operations as MCP-compatible tools
  • 513 developers have installed this integration
  • Designed for Chinese enterprise collaboration environments using DingTalk

Dingtalk Ai Table by the numbers

  • 596 all-time installs (skills.sh)
  • Ranked #1,595 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
  • Data as of Aug 4, 2026 (Skillselion catalog sync)
npx skills add https://github.com/breath57/dingtalk-skills --skill dingtalk-ai-table

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

Listed on Skillselion
Installs596
repo stars97
Last updatedJune 26, 2026
Repositorybreath57/dingtalk-skills

How do agents read and write DingTalk AI tables?

Let their AI coding agent read from, write to, and update structured tables inside DingTalk for automated workflows.

Who is it for?

Developers building agent automations that must sync operational data with DingTalk AI Tables in enterprise chat environments.

Skip if: Teams outside DingTalk ecosystems, heavy relational database migrations, or products with no DingTalk workplace dependency.

When should I use this skill?

A developer asks an agent to read, write, or update structured DingTalk AI Table records in an automated workflow.

What you get

Agent-driven DingTalk AI Table reads, inserts, and row updates inside DingTalk automated workflows.

  • Table row reads
  • Table row writes
  • Automated table updates

By the numbers

  • 513 installs per skills.sh listing in readme excerpt
  • skills.sh rank 9370 for dingtalk-ai-table slug

Files

SKILL.mdMarkdownGitHub ↗

钉钉 AI 表格技能

负责钉钉 AI 表格(.able 格式多维表格)的所有操作。本文件为策略指南,仅包含决策逻辑和工作流程。完整 API 请求格式见文末「references/api.md 查阅索引」。

核心概念

  • AI 表格.able 文件):多维表格,使用 Notable API(/v1.0/notable),不是普通电子表格
  • base_id:AI 表格文件的 nodeId,从分享链接 https://alidocs.dingtalk.com/i/nodes/<base_id> 提取
  • 工作表(Sheet):表格内的单张表,包含字段和记录
  • 字段(Field):列定义,有名称和类型(textnumberdate
  • 记录(Record):数据行,fields 中用字段名称(非 ID)作键
  • operatorId:所有接口必须的 unionId 参数,通过 dt_helper.sh --to-unionid 自动转换

工作流程(每次执行前)

1. 先识别本次任务类型 → 例如:列工作表、创建字段、查询记录、更新记录、删除记录 2. 按本次任务校验所需配置 → 通过 bash scripts/dt_helper.sh --get KEY 读取;仅校验本任务必须项 3. 仅收集缺失配置 → 若缺少某项,一次性询问用户所有缺失值,用 bash scripts/dt_helper.sh --set KEY=VALUE 写入 4. 获取 Token / operatorId → 直接调用 bash scripts/dt_helper.sh,token 获取与缓存细节无需关心 5. 执行操作 → 凡是包含变量替换、管道或多行逻辑的命令,写入 /tmp/<task>.shbash /tmp/<task>.sh 执行。不要把多行命令直接粘到终端里(终端工具会截断),也不要用 <<'EOF' 语法(heredoc 在工具中同样会被截断导致变量丢失)

按任务校验配置(必须先做)

  • 所有任务通用必需DINGTALK_APP_KEYDINGTALK_APP_SECRETDINGTALK_MY_USER_ID
  • 涉及任何 AI 表格 API 调用:必须有 DINGTALK_MY_OPERATOR_ID(若缺失,先用 bash scripts/dt_helper.sh --to-unionid 自动转换并写回)
  • 工作表/字段/记录相关操作:必须有 DINGTALK_AI_TABLE_BASE_ID(若缺失,要求用户提供 AI 表格链接并提取 /nodes/<base_id>
规则:未通过“本次任务配置校验”前,不得进入 API 调用步骤。
凭证禁止在输出中完整打印,确认时仅显示前 4 位 + ****

所需配置

配置键必填说明如何获取
DINGTALK_APP_KEY应用 AppKey钉钉开放平台 → 应用管理 → 凭证信息
DINGTALK_APP_SECRET应用 AppSecret同上
DINGTALK_MY_USER_ID当前用户的企业员工 ID(userId)管理后台 → 通讯录 → 成员管理 → 点击姓名查看
DINGTALK_MY_OPERATOR_ID当前用户的 unionId(operatorId)首次由 bash scripts/dt_helper.sh --to-unionid 自动转换并写入
DINGTALK_AI_TABLE_BASE_IDAI 表格的 nodeId从 AI 表格分享链接 /nodes/<id> 提取

身份标识说明

标识说明
userId(= staffId企业内部员工 ID,可通过管理后台 -> 通讯录 -> 成员管理 -> 点击姓名查看
unionId跨企业/跨应用唯一标识,可通过 bash scripts/dt_helper.sh --to-unionid <userid> 获取

执行脚本模板

#!/bin/bash
set -e
HELPER="./scripts/dt_helper.sh"
NEW_TOKEN=$(bash "$HELPER" --token)
OPERATOR_ID=$(bash "$HELPER" --get DINGTALK_MY_OPERATOR_ID)
BASE_ID=$(bash "$HELPER" --get DINGTALK_AI_TABLE_BASE_ID)

# 在此追加具体 API 调用,例如列出工作表:
SHEETS=$(curl -s -X GET "https://api.dingtalk.com/v1.0/notable/bases/${BASE_ID}/sheets?operatorId=${OPERATOR_ID}" \
  -H "x-acs-dingtalk-access-token: $NEW_TOKEN")
echo "工作表列表: $SHEETS"
Token 失效处理:dt_helper 仅按时间缓存,无法感知 token 被提前吊销。若 API 返回 401(token 无效/过期),用 --nocache 跳过缓存强制重新获取:
```bash
NEW_TOKEN=$(bash "$HELPER" --token --nocache)
```

references/api.md 查阅索引

确定好要做什么之后,用以下命令从 references/api.md 中提取对应章节的完整 API 细节(请求格式、参数说明、返回值示例):

grep -A 20 "^## 1. 列出工作表" references/api.md
grep -A 15 "^## 2. 查询单个工作表" references/api.md
grep -A 30 "^## 3. 创建工作表" references/api.md
grep -A 15 "^## 4. 删除工作表" references/api.md
grep -A 25 "^## 5. 列出字段" references/api.md
grep -A 28 "^## 6. 创建字段" references/api.md
grep -A 15 "^## 7. 更新字段" references/api.md
grep -A 15 "^## 8. 删除字段" references/api.md
grep -A 25 "^## 9. 新增记录" references/api.md
grep -A 40 "^## 10. 查询记录列表" references/api.md
grep -A 18 "^## 11. 更新记录" references/api.md
grep -A 15 "^## 12. 删除记录" references/api.md
grep -A 10 "^## 错误码" references/api.md
grep -A 6  "^## 所需应用权限" references/api.md

Related skills

FAQ

What can dingtalk-ai-table do?

dingtalk-ai-table lets an AI coding agent read from, write to, and update structured tables inside DingTalk. That supports automated workflows where table rows hold operational or approval data.

How popular is dingtalk-ai-table on skills.sh?

dingtalk-ai-table shows 513 installs on skills.sh from breath57/dingtalk-skills. The skill targets agent-driven DingTalk AI Table automation for workplace data sync.

AI & Agent Buildingagentsautomation

This week in AI coding

Five minutes, every Monday - the tools, releases and tactics for developers.

unsubscribe anytime.