Yida Cool Card logo

Yida Cool Card

Organization
openyida
yida-cool-card

仅在用户明确要求宜搭原生酷卡片(交互卡片、置顶卡片),或继续该上下文时使用。集团版不支持酷卡片搭建,先核对认证环境。提供创建、读取、查询模板、导出配置和样式设计。样式限于钉钉原生组件,不能运行任意 HTML/CSS/React;超出能力时说明限制并提供替代方案。返回官方编辑器链接,由用户配置保存;CLI 不保存、发布或发送。原生数据卡片、Canvas 展示卡片及泛称卡片不触发。

Overview

Publisheropenyida
Repositoryopenyida
Skill nameyida-cool-card
Stars
228
Forks
50
Bundled files
2
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.

  • 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 openyida on GitHub. Read the source before you install it.

Installation

Install the Yida Cool Card 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-cool-card
  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-cool-card .claude/skills/yida-cool-card
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Yida Cool Card 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 Cool Card 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 Cool Card 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.

宜搭原生酷卡片

用户明确选择宜搭原生酷卡片(交互卡片、置顶卡片),或继续已明确的酷卡片上下文时使用。通用“卡片”“指标卡”“向群发送”不自动选择本能力,完整应用搭建也不自动创建酷卡片。

先按实际资源确认类型:

对象标识和入口处理方式
原生酷卡片cardPageCode(如 form...)、cardTemplateId;coolCardManage;钉钉卡片编辑器 scene=yida_card本技能;im 交互卡片,onebox 置顶卡片
原生数据卡片CARD-...;dataCardManage、dataCardDesigner.html?cardCode=...yida-data-card,独立数据集、图表、保存发布和播报
自定义页面的展示卡片页面源码中的 React/Canvas 指标卡或卡片引用外层页面开发、数据绑定或外观改造;不能因此修改源原生卡片

用户名称与链接不一致时说明链接的实际资源,核对目标后操作,不能将两个原生接口互换。ID 只是核对线索:数据卡片也引用 FORM 数据源,页面也可能引用 CARD。

操作

先用 openyida login --check-only --json 核对目标组织、用户和环境,再复用用户指定的应用。用户要求读取已有卡片时不新建;已有标识不明时先列出核对。

集团版不支持酷卡片搭建。 用户要求创建或搭建酷卡片时,先依据认证连接的实际 baseUrl 判断环境;复用 CLI 的环境识别语义,alibaba 为集团版(包括 yida-group.alibaba-inc.com 及已识别的内网宜搭环境)。已确认集团版时,直接告知“集团版不支持酷卡片搭建”,结束搭建流程,不创建应用或卡片、不查询模板或提供编辑器链接,也不引导安装 dws 绕过限制。环境不明时先查登录状态,不凭应用名称、组织名称或公有云付费版本猜测。CLI 的 COOL_CARD_UNSUPPORTED_ENVIRONMENT 同样按此处理。

bash
openyida app-settings APP_XXX --section cool-card --json
openyida cool-card list APP_XXX --type im --json
openyida cool-card templates APP_XXX --type onebox --json
openyida cool-card create APP_XXX --type im --name '订单交互卡片' --json
openyida cool-card create APP_XXX --type onebox --name '订单群置顶卡片' --json
openyida cool-card get APP_XXX form真实标识 --out .cache/cool-card/snapshot.json --json

list 可省略类型查看全部;templates 必须指定类型,只查询模板目录,不会实例化模板。分页参数为 --page、--size,搜索为 --search。get 保留完整 card.cardSchema,另外解析 template、editorData、变量及组件类型;--out 导出带应用和卡片标识的完整快照,已有文件拒绝覆盖。不能把快照传给 data-card save。

create 只新建资源,回读校验应用、名称和类型。readbackVerified=true 只代表资源元数据回读成功;当平台尚未创建模板时返回 completion=resource-only、schemaReadbackVerified=false 及原始 schemaReadbackError,不把失败伪装成空配置。空壳不是卡片搭建完成,configurationVerified、deliveryVerified 均为 false。超时或创建后回读失败时先按 cardPageCode 或列表核查,不自动再次创建。

设计与默认视觉质量

用户要求设计、搭建效果或美化时,先读取 默认设计、模板与数据契约。优先选择匹配业务的信息布局与原生模板,结合头部、指标/循环区块、标签、富文本、折叠面板和真实动作;不把连续基础文本和大量背景框作为默认设计。组件按需要选,不以数量判断复杂度或美观。

用户要求“样式完全不一样”时,按以下规则处理:

  • 原生组件能实现:重做布局、配色和信息层级,不因用户说“自定义”就拒绝。
  • 部分效果超出能力:明确告知“受限于钉钉端内交互卡片的组件和样式能力,不能直接运行任意 HTML、CSS 或 React”,指出具体受限的效果,再提供原生近似设计、图片补充静态视觉、卡片链接打开独立页面等方案。
  • 要求所有效果留在消息卡片内,原生组件又无法实现:直接说明该部分效果无法实现,不承诺写代码或安装 dws 就能解决。

保留用户选择的原生卡片类型。改成静态图片或新增独立页面前,说明对展示和交互的影响;沿用用户已有的明确选择,没有授权时只提供方案。配置保存成功不代表自定义样式已生效,具体判断见 代码与样式边界。

交付链接,由用户配置保存

CLI 负责创建、读取、模板查询及返回链接;官方编辑器中的配置、模板选择和保存交给用户操作。create/get 返回 nextAction,包含操作人、入口及保存后的 verificationCommand。给用户输出可点击的 Markdown 链接,不只展示 JSON 字段或笼统地说“不支持”。

  • 新建成功:使用 nextAction.url 提供“打开酷卡片编辑器”,说明“资源已创建,请在官方编辑器中配置并点击保存”。没有直接编辑器地址时,该字段退回当前租户的管理入口。
  • 修改已有卡片:使用 nextAction.url 提供“打开酷卡片管理”,引导找到对应名称的卡片 → 编辑 → 配置 → 保存。平台的编辑操作会准备模板版本,不直接拿读取结果的旧模板链接代替该流程。
  • 用户确认已保存后:执行返回的 verificationCommand 回读同一卡片的配置和状态;不重新创建。回读成功只证明配置可读,不证明发送或客户端效果已验收。
  • 新建后模板暂不存在或为空:仍交付已验证资源的入口,明确“资源已创建,待用户配置保存”;不把这一状态说成配置失败后需要重建,也不宣称搭建完成。

capabilities.save/publish/send=false 表示 CLI 不执行这些操作,并不妨碍交付官方入口。链接不携带登录凭证;用户使用自己的平台登录态,服从官方权限和权益判断。无需为这个交付流程继续索取编辑器源码或额外申请权限。协议研究见 配置协议与验证。浏览器可用于接口分析及最终验收,不用浏览器拖拽后宣称完成 CLI 搭建。

可选外部 dws

钉钉 Workspace CLI 是独立产品,不是 OpenYida 内部模块,也不是当前酷卡片流程的必需依赖。用户需要钉钉侧卡片能力时,按 外部工具安装与调用边界 检查已有安装、给出官方安装指引及核对所需命令。不要把仓库、二进制、SDK 或整套 Skill 复制进 OpenYida,不在 OpenYida 安装脚本中静默安装、升级或改写 dws 的路径与登录配置。

只有命令确实支持目标模板及宜搭场景时,才能将它接入同一 cardTemplateId 的保存流程。现有 A2UI 的消息 bizId 更新不是模板保存;不能调用发送命令来替代保存验收。缺少所需能力时继续交付官方编辑器链接,不让用户安装 dws 后误以为就能自动保存宜搭模板。

权限和权益由服务端裁决,保留平台错误码和提示。禁止修改版本、额度、授权、应用标记、可见范围或官方卡片开关来绕过限制。数据卡片数量/播报权益不等于酷卡片权益,不复用其硬编码额度或角色矩阵。创建、保存、发布配置与实际发送分开授权;配置需求不等于允许给群或人员发测试消息。

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 Yida Cool Card AI skill do?

仅在用户明确要求宜搭原生酷卡片(交互卡片、置顶卡片),或继续该上下文时使用。集团版不支持酷卡片搭建,先核对认证环境。提供创建、读取、查询模板、导出配置和样式设计。样式限于钉钉原生组件,不能运行任意 HTML/CSS/React;超出能力时说明限制并提供替代方案。返回官方编辑器链接,由用户配置保存;CLI 不保存、发布或发送。原生数据卡片、Canvas 展示卡片及泛称卡片不触发。

Why use Yida Cool Card on TypingMind?

Because you install it once and use it with any model. Yida Cool Card 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 Cool Card in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/openyida/openyida/tree/main/yida-skills/skills/yida-cool-card. 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 Yida Cool Card?

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 Cool Card?

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

Is the Yida Cool Card 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 👇