TypingMindTypingMindThe best frontend for AI
Dingtalk Knowledge Search logo

Dingtalk Knowledge Search

Community
breath57
dingtalk-knowledge-search

钉钉知识库搜索与读取。用于在钉钉沉淀知识里快速查资料、理解项目背景、梳理团队/部门信息、回答制度问题、整理新人入门材料、读取文档正文、导出 Markdown、下载文件，并可带图片和 diagram。

Overview

Publisherbreath57
Repositorydingtalk-skills
Skill namedingtalk-knowledge-search
Stars
102
Forks
10
Bundled files
2
Links
Skill sourceRepository
  • 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 Knowledge Search 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-knowledge-search
  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-knowledge-search .claude/skills/dingtalk-knowledge-search
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Dingtalk Knowledge Search 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 Knowledge Search 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 Knowledge Search 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.

用法

bash
cd <the_skill_dir_path>/scripts
python3 cli.py config check
python3 cli.py search "关键词1 关键词2 关键词3"
python3 cli.py read "https://alidocs.dingtalk.com/i/nodes/<node_id>"
python3 cli.py read <node_id>

配置

先运行配置校验：

bash
python3 cli.py config check

需要这些配置：

配置用途获取方式
DINGTALK_APP_KEY调用钉钉开放平台 API钉钉开放平台 -> 应用管理 -> 企业内部应用 -> 凭证与基础信息
DINGTALK_APP_SECRET获取 API token同上，应用凭证信息中查看
DINGTALK_MY_USER_ID当前操作者身份管理后台 -> 通讯录 -> 成员管理 -> 点击成员查看 userId
DINGTALK_MY_OPERATOR_ID文档 API 的 operatorId/unionId有 DINGTALK_MY_USER_ID 后可自动转换

缺少 DINGTALK_MY_OPERATOR_ID 时执行：

bash
python3 cli.py config to-unionid

得到什么

  • search：返回匹配文档列表；可用 --limit <n> 控制数量
  • read：返回 Markdown；长内容会写到文件并返回路径；非 ALIDOC 文件会下载原文件
  • PDF 转文本：read <pdf_node_or_url> --mode pdf2text 会先下载 PDF，再用系统 pdftotext -layout 输出 .txt；如果系统没有 pdftotext，会提示安装 poppler-utils，并退回返回 PDF 路径
  • 默认输出：写到 skill workspace 下的 .skills-workspace/dingtalk-knowledge-search/outputs/
  • 项目沉淀：用 --output-dir "$PWD/dingtalk-docs" --output-path 把结果写到当前项目
  • 输出缓存：下载/转换结果会在用户级缓存目录保留一份，远端 modifiedTime 未变化时复用；默认用硬链接写入 --output-dir，用 --output-strategy copy 可复制隔离
  • 图片本地化：用 --with img-local，图片会下载到 Markdown 同目录 .assets/<文档名>/
  • 图片代理：用 --with img，节约本地空间，但依赖代理服务和原链接有效期
  • diagram：用 --with diagram 一起导出

例子

bash
python3 cli.py search "项目背景 年假 晋升" --limit 10
python3 cli.py read "https://alidocs.dingtalk.com/i/nodes/<node_id>" --output-dir "$PWD/dingtalk-docs" --output-path
python3 cli.py read "https://alidocs.dingtalk.com/i/nodes/<node_id>" --with img-local --with diagram --output-dir "$PWD/dingtalk-docs" --output-path
python3 cli.py read "https://alidocs.dingtalk.com/i/nodes/<file_node_id>" --output-dir "$PWD/dingtalk-docs"
python3 cli.py read "https://alidocs.dingtalk.com/i/nodes/<pdf_node_id>" --mode pdf2text --output-dir "$PWD/dingtalk-docs"
python3 cli.py read "https://alidocs.dingtalk.com/i/nodes/<pdf_node_id>" --mode pdf2text --output-dir "$PWD/dingtalk-docs" --output-strategy copy

缓存

  • search 不缓存，每次直接查远端
  • node、resolve-url、blocks 仍使用 SQLite API 缓存，受 --cache-ttl 影响
  • 输出文件缓存不受 TTL 影响，使用远端 modifiedTime 判断是否复用
  • 输出缓存默认位置：~/.dingtalk-skills/dingtalk-knowledge-search/output-cache/
  • 默认 --output-strategy link：把全局缓存硬链接到当前 --output-dir，节省空间；编辑任一硬链接文件会影响同一份内容
  • --output-strategy copy：复制到当前 --output-dir，和全局缓存隔离
  • python3 cli.py cache clear --namespace output --yes 会删除输出缓存记录和关联本地文件

登录

  • 需要扫码时，命令会返回 loginRequired: true 和 screenshotPath
  • 扫码后重新执行同一个命令

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 Knowledge Search AI skill do?

钉钉知识库搜索与读取。用于在钉钉沉淀知识里快速查资料、理解项目背景、梳理团队/部门信息、回答制度问题、整理新人入门材料、读取文档正文、导出 Markdown、下载文件，并可带图片和 diagram。

Why use Dingtalk Knowledge Search on TypingMind?

Because you install it once and use it with any model. Dingtalk Knowledge Search 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 Knowledge Search in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/breath57/dingtalk-skills/tree/main/.agents/skills/dingtalk-knowledge-search. 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 Knowledge Search?

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 Knowledge Search?

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

Is the Dingtalk Knowledge Search 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.

Related AI Skills

View all
openclaw logo

Acp Router

openclaw
OrganizationPopular

Route plain-language requests for Claude Code, Cursor, Copilot, OpenClaw ACP, OpenCode, Gemini CLI, Qwen, Kiro, Kimi, iFlow, Factory Droid, Kilocode, or explicit ACP harness work into either OpenClaw…

82.2K
391K
Instructions
View
openclaw logo

Diffs

openclaw
OrganizationPopular

Use the diffs tool to produce real, shareable diffs (viewer URL, file artifact, or both) instead of manual edit summaries.

82.2K
391K
Instructions
View
openclaw logo

Feishu Doc

openclaw
OrganizationPopular

Feishu document read/write workflows. Activate when the user mentions Feishu docs, cloud docs, or docx links.

82.2K
391K
1 files
View
openclaw logo

Feishu Drive

openclaw
OrganizationPopular

Feishu cloud-storage and comment workflows. Activate when the user mentions cloud space, folders, Drive files, or document comments.

82.2K
391K
Instructions
View

Set up your own AI workspace now

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