dingtalk-document
breath57/dingtalk-skills
Manage DingTalk knowledge bases and documents—create, read, write, and control member access.
What is dingtalk-document?
This skill handles all DingTalk document and knowledge base operations. Use it when users mention creating documents, reading/writing content, managing folders, or controlling member permissions in DingTalk's document system.
- Create and query knowledge bases (workspaces)
- Create documents and folders within workspaces
- Read and write document content
- Delete documents and manage node hierarchies
- Add, update, and remove document members with permission control
- Query document lists and node information
How to install dingtalk-document
npx skills add https://github.com/breath57/dingtalk-skills --skill dingtalk-document- DingTalk enterprise account with app credentials (AppKey and AppSecret)
- Current user's enterprise employee ID (userId)
- Access to DingTalk Open Platform to retrieve application credentials
How to use dingtalk-document
- 1.Identify the task type (list workspaces, create document, read content, manage members, etc.)
- 2.Validate required configuration using `bash scripts/dt_helper.sh --get KEY`
- 3.Collect any missing configuration values in one pass using `bash scripts/dt_helper.sh --set KEY=VALUE`
- 4.Obtain access token and operatorId via `bash scripts/dt_helper.sh`
- 5.Execute the operation by writing multi-line commands to `/tmp/<task>.sh` and running `bash /tmp/<task>.sh`
- 6.For token expiration, use `--nocache` flag to force token refresh: `bash scripts/dt_helper.sh --token --nocache`
Use cases
- Create a new document in a DingTalk knowledge base and add team members with specific permissions
- Read the full content of an existing document and extract information
- Update document content by overwriting or appending text to paragraphs
- List all documents in a workspace and navigate folder structures
- Manage document access by adding or removing team members
- DingTalk workspace administrators
- Team leads managing shared documentation
- Enterprise users automating document workflows
- Knowledge base curators
dingtalk-document FAQ
docKey and dentryUuid are used for reading/writing document content. nodeId is used for deletion and document management operations. The create document response returns all three; wiki/nodes returns nodeId which is actually dentryUuid and can be used directly for content operations.
Use `bash scripts/dt_helper.sh --to-unionid <userid>` to automatically convert and write the unionId back to configuration.
All tasks require DINGTALK_APP_KEY, DINGTALK_APP_SECRET, DINGTALK_MY_USER_ID, and DINGTALK_MY_OPERATOR_ID. Use `bash scripts/dt_helper.sh --get KEY` to check what's missing and `--set KEY=VALUE` to configure.
If an API returns 401 (token invalid/expired), use `bash scripts/dt_helper.sh --token --nocache` to bypass caching and force a fresh token.
Use grep commands to extract sections from `references/api.md`, e.g., `grep -A 30 '^## 1. 查询知识库列表' references/api.md` for the knowledge base list API details.
Full instructions (SKILL.md)
Source of truth, from breath57/dingtalk-skills.
name: dingtalk-document description: 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。
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
- 创建文档响应会返回:
- 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)
- 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
- 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 - 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 - 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 - 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
#!/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: $WORKSPACES"
Token 失效处理:dt_helper 仅按时间缓存,无法感知 token 被提前吊销。若 API 返回 401(token 无效/过期),用
--nocache跳过缓存强制重新获取:NEW_TOKEN=$(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 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
Related skills
More from breath57/dingtalk-skills and the wider catalog.

dingtalk-message
Send DingTalk messages via Webhook robots, enterprise apps, work notifications, and more.

crawl4ai
Use when scraping JavaScript-heavy pages or SPAs, crawling multiple URLs concurrently, extracting structured data with reusable CSS/JSON schemas, or building automated web data pipelines. Wraps the Crawl4AI library (`crwl` CLI and Python SDK) with schema-generation patterns for LLM-free extraction. Triggers on crawl4ai, crwl, scrape JS-heavy site, scrape SPA, headless browser scrape, schema-based extraction, batch crawl, sitemap crawl, web data pipeline. SKIP when a static HTML page can be read with `defuddle` / `fetch-web` — those are faster cold-start and don't need a browser.

deslop
Remove AI-generated code slop like unnecessary comments, defensive checks, and type casts from your branch.

simplify
Simplify and refine recently modified code for clarity and consistency without changing functionality.

bright-data-best-practices
Reference documentation for building production-ready Bright Data integrations with best practices.

bright-data-mcp
|