Yida Data Card logo

Yida Data Card

Organization
openyida
yida-data-card

仅在用户明确要求操作宜搭原生数据卡片资源时使用,支持创建、读取、配置保存、发布及投放播报。自定义页面展示卡片、仅修改原生卡片引用外层及泛称卡片、指标卡、看板或播报不触发;已明确的原生卡片操作可继续沿用。

Overview

Publisheropenyida
Repositoryopenyida
Skill nameyida-data-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 Data 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-data-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-data-card .claude/skills/yida-data-card
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Yida Data 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 Data 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 Data 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.

宜搭原生数据卡片

先核对用户是否显式选择本能力:明确要求“宜搭原生数据卡片”,或主动提供原生卡片管理、设计、投放链接并要求操作该资源;已明确的原生卡片上下文可继续沿用,无需重复确认。仅有“卡片、数据卡片、指标卡、看板、投放、数据播报、发送到群”等泛称,或环境中存在 CARD 资源,均不能自动触发。用户明确不使用原生卡片时不进入此技能;按实际页面、图表或自动化任务选择相应技能,意图仍不清楚时再澄清。

按用户选择、资源类型和配置归属区分同名“数据卡片”:

  • 宜搭原生数据卡片是独立 CARD-xxx 资源,组件、数据集和布局归卡片 Schema,使用本技能保存、发布及配置播报。
  • 宜搭原生酷卡片使用 cardPageCode、cardTemplateId,包含交互卡片 im 与置顶卡片 onebox,由独立 yida-cool-card Skill 处理。dataCardDesigner.html?cardCode=CARD-... 仍属原生数据卡片,不能因为用户口头叫“酷卡片”就切换接口。
  • 自定义页面里的指标卡、统计卡是 Canvas/React 页面组件,随所属页面源码和页面发布;页面通常有 FORM-xxx 标识,仍需核实页面类型和源码。已有页面中新增展示卡片走页面开发,接真实数据走页面数据绑定,只改外观走现有 UI 改造流程,不自动创建 CARD 资源。
  • 页面引用 CARD-xxx 时,页面是展示位置,原生卡片仍是独立资源。只改引用外层布局或页面配置,按页面任务处理;用户明确要求修改所引用卡片自身指标、数据源或布局时,才进入本技能。不因发现引用而获得修改源卡片的授权;不据此宣称已支持门户自动挂载。

不能仅扫描 ID 前缀判断操作对象:原生卡片也会引用 FORM-xxx 作为数据源,自定义页面也可能含 CARD 引用。缺少明确上下文时先澄清类型,不自动新建任何一种卡片。

多组件搭建先读 图表配置与验收:支持九类原生组件、多指标、日期维度、同源下拉筛选和运行时探测;包含错误引导和当前能力缺口。

已满足上述原生卡片触发条件,再处理其投放、播报或使用记录时读 投放与播报。publish 不会启用播报;启用和测试发送还需明确发送授权。门户目前只支持使用记录查询与入口,不自动挂载组件。

先用 auth snapshot 核对目标组织和应用。已有 cardCode 时复用;用户要求新建时使用 create。卡片与表单、页面是不同资源,不调用 create-page 或 publish 页面命令替代。

Skill 与 CLI 执行边界

  • 应用搭建由本 Skill 编排,通过 OpenYida CLI 完成字段查询、卡片创建、组件配置、保存和发布。基础指标卡优先使用 save --config;完整配置使用 save --schema,由已核实的原生契约生成,不能要求用户先在浏览器拖拽出样本。
  • 开发 OpenYida 能力时,可以用浏览器分析接口、参数、组件类型、配置选项和原生行为;核实后将可复用实现落入 CLI,并把操作方法、支持范围和验收规则写入 Skill。
  • 正式搭建中的浏览器用于预览、原生可编辑性和真实取数验收。若某个组件或配置尚无 CLI 路径,明确说明缺口;在开发任务中补齐 CLI 与 Skill 后,再验证搭建,不用浏览器代替该步骤并宣称已支持。
  • 验证记录区分浏览器调研、CLI 搭建和浏览器验收;全 CLI 搭建必须能从配置与真实元数据完成,不依赖本轮浏览器保存或临时控制台脚本。

配置入口

用户只询问配置位置时,执行下列只读命令并返回其中 url,不触发设置变更:

bash
openyida app-settings APP_XXX --section theme --json
openyida app-settings APP_XXX --section basic --json
openyida app-settings APP_XXX --section data-card --json

三项依次为主题与导航、基础设置(业务前后台配置所在入口)、原生数据卡片管理。使用实际应用的返回地址,不固定示例域名或应用。地址生成不证明接收者拥有管理权限。

卡片操作

bash
openyida data-card list APP_XXX --size 50 --json
openyida data-card create APP_XXX --name '销售数据卡片' --out .cache/openyida/data-card/new.json --json
openyida data-card get APP_XXX CARD-xxx --out .cache/openyida/data-card/draft.json --json
openyida data-card save APP_XXX CARD-xxx --config .cache/openyida/data-card/indicators.json --expected-hash <get返回的schemaHash> --json
openyida data-card publish APP_XXX CARD-xxx --expected-hash <最新草稿schemaHash> --json
openyida data-card get APP_XXX CARD-xxx --published --json
openyida data-card probe APP_XXX CARD-xxx --published --json

get 默认读取草稿,可通过 --version 读取指定版本。输出 card.schemaBody 为完整配置,--out 单独导出该 Schema;输出文件已存在时拒绝覆盖。平台初始 Schema 可以没有 schemaType/schemaVersion,保留其实际结构。

使用 --schema 保存是完整 Schema 替换:在本次读取的副本上编辑,保留未知键、pages、动作、组件映射、数据集和多语言引用。保存和发布都要求原始草稿摘要,写前自动备份并再次读取检查;平台没有原子锁,摘要不是并发事务。backupPath 可用于恢复前取证;不要无条件覆盖发生变化的卡片。

原生组件使用 Youshu 图表、基础指标卡、基础表格、下拉或时间筛选等物料。数据在 props.dataSetModelMap 及 dataViewQueryModel,样式在 settings。字段与数据集引用必须来自真实配置或已核实元数据;不根据展示名称臆造 cubeCode 或字段 ID。开启筛选涉及头部及筛选容器节点和联动引用,不是添加任意 enableFilter 键。支持完整 Schema 读写不等于已经支持任意自然语言自动生成图表。

config.i18nKeyList 与组件内词条引用一起保留;词条集合改变时 CLI 在保存前同步 dataCard 词条绑定。绑定成功、草稿写入失败时保留备份并核对远程状态,不盲目重放。

完成证据

  • create 必须返回真实 cardCode 并读取其初始配置;创建空壳不等于配置完成。
  • save 必须返回 readbackVerified=true;它只证明草稿配置回读一致,不证明发布成功。published=false 表示本次操作没有发布,不表示平台一定没有旧发布版。
  • publish 发布当前已保存草稿,不自动读取并保存本地文件;必须返回 published=true、发布版本及已发布 Schema 回读证据。
  • urls.designerUrl/previewUrl/dataCardManageUrl 可用于验收;渲染、编辑和真实取数需分别验证。

写请求不自动重放。创建超时或回读失败时先按返回 cardCode 或列表核对,不能直接再次新建。权限、卡片数量和图表数量权益失败时保留平台错误码,建议管理员处理或升级;不修改应用标记、版本、额度或权益。卡片发布不包含播报,播报使用独立 release 命令;不包含删除。

通过 CLI 搭建指标卡

创建、读取、配置保存和发布默认通过 CLI 完成,浏览器用于最终查看与编辑验收。新卡片无需先在浏览器拖拽生成 Schema。先用 get-schema APP_XXX FORM-xxx --field-map-json 核对真实字段,再准备配置文件:

json
{
  "indicators": [{
    "title": "报名统计",
    "formUuid": "FORM-真实表单ID",
    "fieldId": "serialNumberField_真实字段ID",
    "aggregate": "COUNT",
    "label": "报名总数"
  }]
}
bash
openyida data-card save APP_XXX CARD-xxx --config indicators.json --expected-hash <当前草稿schemaHash> --json

--config 与 --schema 二选一。上例 indicators 是兼容格式;复杂卡片使用参考文档中的 charts/filters 格式。CLI 校验真实字段,生成原生组件、查询模型、组件映射和布局,追加到当前卡片并保存草稿;已有组件及未知配置保留,再次保存相同配置会再次追加。单卡现有加新增最多五个图表。数字字段支持 COUNT/SUM/AVG/MIN/MAX;文本计数、分类维度和日期粒度按参考文档约束。子表、跨源筛选和未注册组件明确拒绝;权限和权益仍由平台校验,失败停止,不更改应用标记或额度。

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 Data Card AI skill do?

仅在用户明确要求操作宜搭原生数据卡片资源时使用,支持创建、读取、配置保存、发布及投放播报。自定义页面展示卡片、仅修改原生卡片引用外层及泛称卡片、指标卡、看板或播报不触发;已明确的原生卡片操作可继续沿用。

Why use Yida Data Card on TypingMind?

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

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

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

Is the Yida Data 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 👇