Yida Nav Group logo

Yida Nav Group

Organization
openyida
yida-nav-group

整理宜搭已有的导航菜单时使用。支持查看菜单、新建或调整分组、移动和排序页面、隐藏或显示菜单项。

Overview

Publisheropenyida
Repositoryopenyida
Skill nameyida-nav-group
Stars
228
Forks
50
Bundled files
Instructions only
LicenseMIT
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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

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

Installation

Install the Yida Nav Group 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/openyida/openyida/tree/main/yida-skills/skills/yida-nav-group
  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/openyida/openyida.git /tmp/openyida
mkdir -p .claude/skills
cp -r /tmp/openyida/yida-skills/skills/yida-nav-group .claude/skills/yida-nav-group
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Yida Nav Group 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 Yida Nav Group 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 Yida Nav Group 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.

应用导航分组

严格要求

  • 操作前必须已知 appType;不要编造。
  • 移动页面前先执行 openyida nav-group list <appType> 确认 navUuid / formUuid 和目标分组。
  • 完整应用首次生成后,基于 PRD 的导航顺序决定根导航顺序,页面实现交付顺序和资源创建顺序不直接等同于导航顺序。
  • 完整应用排序时机:等待本轮全部页面开发、发布及资源创建完成,再统一执行一次排序;逐页发布不使用 --auto-nav-order。用户单独要求调整已有导航时直接按本次要求执行。
  • PRD 导航优先:PRD 写明页面/表单清单顺序时,使用 openyida nav-group order <appType> <页面/表单...>;PRD 只写宽泛分组或缺少导航顺序时,使用 openyida nav-group auto-order <appType> 或发布命令的 --auto-nav-order 兜底。两种排序互斥,同一 Run 只执行一次,不生成逐项 move 循环。
  • 兜底自动排序优先级:门户/首页/工作台入口 > 自定义展示页面 > 流程表单 > 普通表单。这是工具兜底顺序,不替代 PRD 导航顺序。
  • 默认原则:面向决策者的总览/驾驶舱看板作为应用门面靠前,数据录入/明细表单在其后。 仅适用于已确认的管理概览需求,不自动创建首页,也不将独立访客首页混入管理端。判断某个看板是否靠前,看它是不是主要「查看/决策」入口:
    • 有独立总览首页看板时:总览首页看板 → 专题看板 → 核心业务表单 → 明细/配置表单。
    • 没有独立首页、专题看板本身就是主要决策视图时(如「双11看板/618看板」面向运营主管只读查看):这些专题看板靠前,数据录入/明细表单在后。
  • "不要无脑把看板全置顶"针对的是:当存在明确操作旅程(先录入后查看)、且看板只是次要报表时,按旅程排;不要把与主流程无关的次要看板也塞最前。多数带看板的应用,决策看板应先于录入表单。
  • 删除分组默认只删除空分组;非空分组必须先移动子项,除非用户明确要求 --force。
  • 分组节点是 navType: "NAV",普通页面是 navType: "PAGE",外链是 navType: "LINK",系统节点不要移动或删除。

前后台双入口的排序以 访问态入口契约 的管理菜单为准;auto-order 不理解业务身份,不能用于双入口的管理菜单决策。隐藏项同时影响共享平台菜单,不是按角色隐藏,也不是权限拒绝。

命令

查询导航树

bash
openyida nav-group list <appType>
openyida nav-group list <appType> --flat

输出为 JSON。树形结果中 type=group 的节点即分组;navUuid 是后续重命名、删除、移动的稳定标识。

创建分组

bash
openyida nav-group create <appType> "分组名" [--icon auto|<iconName>]
openyida nav-group create <appType> "子分组名" --parent <groupNavUuid>

分组只能创建在根目录或一级分组下。默认根据分组标题选择业务图标,复用页面/表单导航的图标库和语义匹配,例如客户、财务、项目、看板分组分别匹配对应业务图标;不要为所有分组统一指定文件夹,也不为追求差异随机换图标。同一语义允许复用同一图标。

通常省略 --icon 或传 auto;明确需要某个图标时可传合法的平台图标名。平台导航图标与页面内容的 Lucide/Ant Design 组件是两套协议,不能传组件名、emoji 或应用图标的 xian-*%%color。

创建后 CLI 唯一定位本次新增节点,保留导航节点字段更新图标,并回读验证;结果中的 group.icon、iconSource、readbackVerified 用于核对。若返回 NAV_GROUP_CREATE_INCOMPLETE,先执行 nextStep 查询,不重试 create;分组可能已创建,仅图标尚未完成。更新 OpenYida 不会自动修改已有分组,重命名保留原图标。

重命名分组

bash
openyida nav-group rename <appType> <groupNavUuid|groupName> "新分组名"

同名分组可能歧义,优先使用 navUuid。

移动页面或分组

bash
openyida nav-group move <appType> <formUuid|navUuid|name> --to <groupNavUuid|groupName|root>
openyida nav-group move <appType> <formUuid> --to <groupNavUuid> --before <siblingNavUuid>
openyida nav-group move <appType> <formUuid> --to root --after <siblingNavUuid>

目标分组必须通过 --to 传入,不能作为第三个位置参数。

常见场景:把新建表单放入已有分组:

bash
openyida nav-group list APP_XXX --flat
openyida nav-group move APP_XXX FORM_XXX --to NAV_XXX

按业务顺序整理根导航

bash
openyida nav-group order <appType> <formUuid|navUuid|name> [more items...]
openyida nav-group auto-order <appType>

order 会把列出的导航项按给定顺序移动到根导航靠前位置,未列出的系统导航、表单、页面、分组保持相对顺序并跟在后面。适合消费 yida-design 的 prd.md 导航顺序,一次性整理用户入口。

auto-order 会读取当前根导航并按默认优先级排序:门户/首页/工作台入口 > 自定义展示页面 > 流程表单 > 普通表单;系统导航保持在系统区域,未识别分组和其他项排在后面。适合 PRD 没有明确页面清单时做轻量兜底。

order 和 auto-order 写前会比较完整导航结构;顺序已正确时返回 changed=false 且不写入。写入后只有完整回读一致才成功,并返回 readbackVerified=true。结果不确定时不要重试,只执行返回的 nextStep 查询当前导航。

示例 A:电商销售系统只有「销售数据表单 + 双11看板 + 618看板」,看板是运营主管的主要决策视图,把看板作为门面靠前、录入表单在后:

bash
openyida nav-group order APP_XXX 双11看板 618看板 销售数据

示例 B:应用另有独立「首页总览看板」,且双11/618 只是次要专题、主流程是先在订单/商品表录入再看板,则按旅程排、不要把每个专题看板都塞最前:

bash
openyida nav-group order APP_XXX 首页总览看板 订单表 商品表 客户表 双11看板 618看板

删除分组

bash
openyida nav-group delete <appType> <groupNavUuid>

非空分组会报错,先把子页面移动到其他分组或 root。

隐藏 / 显示导航项

bash
openyida nav-group hide <appType> <navUuid|formUuid|name>
openyida nav-group show <appType> <navUuid|formUuid|name>

隐藏会同时设置 PC 与移动端导航隐藏。

接口事实

  • 查询:/dingtalk/web/{appType}/query/formnav/getFormNavigationListByOrder.json
  • 创建:/dingtalk/web/{appType}/query/formnav/saveFormNavigation.json
  • 重命名:/dingtalk/web/{appType}/query/formnav/updateNavigationTitle.json
  • 移动排序:/dingtalk/web/{appType}/query/formnav/updateFormNavigationOrderNew.json
  • 删除:/dingtalk/web/{appType}/query/formnav/deleteFormNavigation.json

ROOT 分组的后端标识是 NAV-SYSTEM-PARENT-UUID,命令中可用 root 代替。

Frequently asked questions

What does the Yida Nav Group AI skill do?

整理宜搭已有的导航菜单时使用。支持查看菜单、新建或调整分组、移动和排序页面、隐藏或显示菜单项。

Why use Yida Nav Group on TypingMind?

Because you install it once and use it with any model. Yida Nav Group 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 Yida Nav Group in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/openyida/openyida/tree/main/yida-skills/skills/yida-nav-group. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Yida Nav Group?

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 Yida Nav Group?

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

Is the Yida Nav Group AI skill free?

Yes. It is published on GitHub by openyida under the MIT license. 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 👇