Dingtalk Document logo

Dingtalk Document

Community
breath57
dingtalk-document

钉钉知识库和文档管理操作。当用户提到"钉钉文档"、"知识库"、"新建文档"、"查看文档目录"、"读取文档内容"、"写入文档"、"更新文档"、"文档成员"、"dingtalk doc"、"knowledge base"时使用此技能。支持:创建知识库、查询知识库列表、新建文档/文件夹、读取/写入文档正文内容、管理成员权限等全部文档类操作。

Overview

Publisherbreath57
Repositorydingtalk-skills
Skill namedingtalk-document
Stars
102
Forks
10
Bundled files
2
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 2 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by breath57 on GitHub. Read the source before you install it.

Installation

Install the Dingtalk Document AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/breath57/dingtalk-skills/tree/main/.agents/skills/dingtalk-document
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/breath57/dingtalk-skills.git /tmp/dingtalk-skills
mkdir -p .claude/skills
cp -r /tmp/dingtalk-skills/.agents/skills/dingtalk-document .claude/skills/dingtalk-document
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Dingtalk Document in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Dingtalk Document on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Dingtalk Document is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

钉钉文档技能

负责钉钉知识库和文档的所有操作。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」。

dt_helper.sh 位于本 SKILL.md 同级目录的 scripts/dt_helper.sh。

核心概念

  • 知识库(Workspace):文档容器,有 workspaceId 和 rootNodeId
  • 节点(Node):文件或文件夹,type 为 FILE 或 FOLDER
  • 文档标识(用于 /v1.0/doc/suites/documents/{id}):可用 docKey 或 dentryUuid
    • 创建文档响应会返回:docKey、dentryUuid、nodeId
    • 其中 docKey / dentryUuid 可用于读写正文;nodeId 用于删除和文档管理类接口
    • wiki/nodes 返回的 nodeId 实际上是 dentryUuid,可直接用于正文读写
  • operatorId:所有接口必须的 unionId 参数,通过 bash scripts/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:列知识库、读文档、写文档、创建文档、成员管理
  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>.sh 再 bash /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_KEY、DINGTALK_APP_SECRET、DINGTALK_MY_USER_ID
  • 涉及任何文档/知识库 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)
  • 创建/读取/写入/删除/成员管理:除上述通用项外,无额外固定配置键;workspaceId/nodeId/docKey 属于任务参数,运行时从用户输入或 API 响应中获取

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

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

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

# 在此追加具体 API 调用,例如查询知识库列表:
WORKSPACES=$(curl -s -X GET "https://api.dingtalk.com/v2.0/wiki/workspaces?operatorId=${OPERATOR_ID}&maxResults=20" \
  -H "x-acs-dingtalk-access-token: $NEW_TOKEN")
echo "知识库列表: $WORKSPACES"

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):

bash
grep -A 30 "^## 1. 查询知识库列表" references/api.md
grep -A 10 "^## 2. 查询知识库信息" references/api.md
grep -A 35 "^## 3. 查询节点列表" references/api.md
grep -A 10 "^## 4. 查询单个节点" references/api.md
grep -A 15 "^## 5. 通过 URL 查询节点" references/api.md
grep -A 28 "^## 6. 创建文档" references/api.md
grep -A 10 "^## 7. 删除文档" references/api.md
grep -A 30 "^## 8. 读取文档内容" references/api.md
grep -A 15 "^## 9. 覆盖写入文档内容" references/api.md
grep -A 12 "^## 10. 追加文本到段落" references/api.md
grep -A 18 "^## 11. 添加文档成员" references/api.md
grep -A 12 "^## 12. 更新文档成员权限" references/api.md
grep -A 10 "^## 13. 移除文档成员" references/api.md
grep -A 10 "^## 错误码" references/api.md
grep -A 10 "^## 所需应用权限" references/api.md

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Dingtalk Document AI skill do?

钉钉知识库和文档管理操作。当用户提到"钉钉文档"、"知识库"、"新建文档"、"查看文档目录"、"读取文档内容"、"写入文档"、"更新文档"、"文档成员"、"dingtalk doc"、"knowledge base"时使用此技能。支持:创建知识库、查询知识库列表、新建文档/文件夹、读取/写入文档正文内容、管理成员权限等全部文档类操作。

Why use Dingtalk Document on TypingMind?

Because you install it once and use it with any model. Dingtalk Document is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Dingtalk Document in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/breath57/dingtalk-skills/tree/main/.agents/skills/dingtalk-document. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Dingtalk Document?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Dingtalk Document?

As many as you like. As long as a model supports skills, you can use Dingtalk Document with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Dingtalk Document AI skill free?

It is published on GitHub by breath57. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇