SkillFoxx

dingtalk-ai-table skill

An OpenClaw skill for DingTalk AI tables via mcporter: creates bases, reads the schema and adds rows and fields in bulk.

  • 110 ★ on the repository
  • Last commit
Skill

Extended access

Why this level

  • The MCP server address gives the agent read and write access to organisation tables.
  • The skill creates, changes and deletes rows and fields through bulk scripts.
All reasons and checks

aliramw/dingtalk-ai-tableAuthor:aliramw

Install

In your terminal, with SkillFoxx CLI

npx skillfoxx add skills/dingtalk-ai-table

Detects the agents on your machine, shows the access level and pins the version.

Other ways to install

Access and checks

How we review

Extended accessThe tool runs code or makes network calls and only reads external data.

  • The MCP server address gives the agent read and write access to organisation tables.
  • The skill creates, changes and deletes rows and fields through bulk scripts.

This is third-party code. Review the repository files before installing.

What it does

dingtalk-ai-table is a skill for the OpenClaw agent that manages DingTalk AI tables through the `mcporter` CLI and the official DingTalk MCP server. The agent creates and searches bases, reads table structure, adds, updates and deletes rows, and creates and changes fields. Work follows the identifiers of the new schema: `baseId`, `tableId`, `fieldId` and `recordId`. The skill covers 20 MCP tools. It ships the `bulk_add_fields.py` and `import_records.py` scripts for bulk field creation and row import, a schema-version check script, seven bash examples and an error reference.

Who it is for. Teams that keep data in DingTalk AI tables and want to manage them from an agent: create tables, load data in bulk and change fields.

Good fit when

  • A base in DingTalk AI tables must be created and filled at once.
  • A CSV with data is loaded into a table in bulk through `import_records.py`.
  • Dozens of fields are added to a table in one pass through `bulk_add_fields.py`.
  • The agent reads the table structure before changing rows.
  • An old script built on `dentryUuid` broke after the new MCP version and is being moved to the new identifiers.

Not a fit when

  • Data lives in another system, for example Excel or Google Sheets.
  • The agent cannot run `mcporter` or Python 3.
  • There is no DingTalk MCP server address for the `DINGTALK_MCP_URL` variable.

Example request

List my DingTalk AI tables, create a base named "Project" and load rows from `data.csv` into it.

Limitations

The skill is written for OpenClaw; connection paths for other agents are not documented. It needs `mcporter` 0.8.1 or newer, `python3` and the `DINGTALK_MCP_URL` variable; `OPENCLAW_WORKSPACE` is recommended for the script sandbox. The old schema with `dentryUuid` and `sheetIdOrName` is declared deprecated. The scripts rely on the OpenClaw workspace sandbox and paths from `OPENCLAW_WORKSPACE`. No licence is stated in the repository. The last commit is dated March 2026.

How to disable. Remove the skill from the OpenClaw skill directory, drop the `DINGTALK_MCP_URL` variable and the `dingtalk-ai-table` server registration in `mcporter`.

FAQ

How do I install the skill?

The skill is published on ClawHub: `https://clawhub.ai/aliramw/dingtalk-ai-table`. The documentation gives no separate install command.

What is required to run it?

`mcporter` 0.8.1 or newer, `python3` and the `DINGTALK_MCP_URL` variable with the MCP server address. The `OPENCLAW_WORKSPACE` variable is recommended for the script sandbox.

How do I tell whether the MCP server is the new version?

Run `mcporter list dingtalk-ai-table --schema`. If tools such as `create_base_app` or `list_base_tables` remain in the answer, the server is on the old schema.

How do I load data in bulk?

Run `python3 scripts/import_records.py base_xxx tbl_xxx data.csv`, substituting your own base and table identifiers.

What should I do with old scripts built on `dentryUuid`?

Rewrite them for the new schema: `baseId`, `tableId`, `fieldId`, `recordId`. The old identifier system is declared deprecated.

Discussion

No questions or reviews yet.

Skills

Eight skills for working with DingTalk from chat: documents, AI tables, messages, calendar, to-dos and knowledge-base search.

SkillExtended access102

DingTalk Workspace CLI (dws)

DingTalk Workspace CLI

Official

Official DingTalk CLI with agent skills: chats, calendar, todos, mail, docs and approvals of your organization from the terminal

CLIBroad access4K

Skill linking an agent to the 得到大脑 notes service: saves links and images, searches by meaning, files notes in knowledge bases.

SkillExtended access140

An installer that sets up one set of rules, skills, hooks and MCP servers across Claude Code, Codex, Cursor and more.

CLIBroad access129

A library of 229 skills for work and life: sales, marketing, finance, engineering, design and parallel agent runs

SkillBroad access428

A desktop app and skm CLI: one copy of each skill in a central hub, symlinked into every AI tool

CLIExtended access1.1K

README in short

The documentation leads from a five-minute start to `GETTING_STARTED.md`, the full `SKILL.md`, an API reference and error troubleshooting. 25 security and functional tests are claimed.

README badge

Original SKILL.md

---
name: dingtalk-ai-table
description: 钉钉 AI 表格（多维表）操作技能。使用 mcporter CLI 连接钉钉官方新版 AI 表格 MCP server，基于 baseId / tableId / fieldId / recordId 体系执行 Base、Table、Field、Record 的查询与增删改。适用于创建 AI 表格、搜索表格、读取表结构、批量增删改记录、批量建字段、更新字段配置、按模板建表等场景。需要配置 DINGTALK_MCP_URL 或直接使用 Streamable HTTP URL。
version: 0.6.0
metadata:
  author: Marila@Dingtalk
  category: productivity
  tags:
    - dingtalk
    - spreadsheet
    - mcp
    - automation
    - data-management
  documentation: https://github.com/aliramw/dingtalk-ai-table
  support: https://github.com/aliramw/dingtalk-ai-table/issues
  openclaw:
    requires:
      env:
        - DINGTALK_MCP_URL
        - OPENCLAW_WORKSPACE
      bins:
        - mcporter
        - python3
    primaryEnv: DINGTALK_MCP_URL
    homepage: https://github.com/aliramw/dingtalk-ai-table
---

# 钉钉 AI 表格操作（新版 MCP）

## 🚀 5 分钟快速开始

### 1️⃣ 列出我的表格
```bash
mcporter call '<DINGTALK_MCP_URL>' .list_bases limit=5
```

### 2️⃣ 创建新表格
```bash
mcporter call '<DINGTALK_MCP_URL>' .create_base baseName='我的项目'
```

### 3️⃣ 添加记录
```bash
mcporter call '<DINGTALK_MCP_URL>' .create_records \
  --args '{"baseId":"base_xxx","tableId":"tbl_xxx","records":[{"cells":{"fld_name":"张三"}}]}'

Report a problem