Yida Process Rule logo

Yida Process Rule

Organization
openyida
yida-process-rule

配置已有宜搭流程的节点、分支、人员、字段权限、跳转规则、操作按钮及官方组件高级透传;共用节点参数按需加载 yida-flow-node-config。

Overview

Publisheropenyida
Repositoryopenyida
Skill nameyida-process-rule
Stars
228
Forks
50
Bundled files
3
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.

  • 3 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 Process Rule 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-process-rule
  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-process-rule .claude/skills/yida-process-rule
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Yida Process Rule 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 Process Rule 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 Process Rule 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.

流程规则配置

本技能负责已有流程的读取、完整定义、保存发布和结果核对。目标不明时先只读确认或询问用户;使用前必须按以下门槛确定目标和操作入口。

Resource-First 使用门槛

本技能是已有流程/表单上下文的默认流程修改入口,必须遵守以下限制:

  • 已有流程表单、processCode、流程 URL、已绑定流程或可确认的 workflow form 时,审批节点、条件分支、字段权限、抄送、跳转规则等配置默认使用本技能;不得另建同类流程表单。
  • 已有普通表单 formUuid,用户要求“配置审批/转为审批流程”时,先确认是否对该表单启用流程。只有尚无流程且已确认转流程时,才由 yida-create-process --formUuid 复用该表单;已有流程则继续使用本技能,不得新建同名表单。
  • 只有没有目标表单/流程,且用户明确要求从零创建审批系统时,才改用 yida-create-process 新建;目标不明不能作为新建理由。
  • 多个流程候选按根技能的资源来源优先级选择;同级冲突或仍无法确定目标时,必须先询问用户,目标确认前不得写入。

严格禁止 (NEVER DO)

  • 不要在流程定义中使用猜测的 fieldId,必须先用 yida-get-schema 获取。
  • 不要在未加载本技能内容的情况下编写流程定义 JSON,格式复杂且易出错。
  • 不要用此技能创建流程表单,应使用 yida-create-process。
  • 不要用 shell heredoc、cat/echo/printf/tee 或重定向生成流程定义 JSON。
  • 已有 process/form context 时不要新建同类流程表单;在原流程上配置或更新。
  • 不要把 configure-process 当作局部 patch;它会替换完整流程图。已有 PUBLISHED 流程或 SAVED 草稿时,未获得用户对替换摘要的明确确认,不得传 --replace。
  • NON_IDEMPOTENT_RESULT_UNKNOWN 或 PUBLISHED_UNVERIFIED 后不得自动重试 draft/save/publish;先只读核对平台状态。

严格要求 (MUST DO)

  • 发布前必须确认:执行流程发布操作前,必须向用户展示流程配置摘要(节点数、审批人、条件分支),获得用户明确同意后再发布。
  • 字段 ≥ 3 且审批节点 ≥ 2 时,必须为每个节点配置字段权限。
  • 存在回退/循环流转语义时,必须配置 routeRules 跳转规则。
  • 根据需求生成流程定义时,必须阅读并遵守 AI 自动生成流程规范;达到上述字段和节点数量时,behaviorList 必须覆盖所有字段,未明确归属的字段默认只读。
  • 嵌套条件分支不超过 3 层;超过时拆分流程结构,不得省略条件。条件分支由 CLI 补“其他情况”默认分支,不手写猜测底层 conditionNode。
  • 流程必须先保存再发布,由 CLI 按顺序执行。本技能不读写 memory,资源 ID 以真实命令返回与当前平台查询为准。
  • 配置前先用 yida-get-schema 获取所有字段 ID。
  • 流程定义 JSON 必须用结构化文件写入工具创建到 <projectRoot>/.cache/openyida/<项目名或任务名>/;不要写仓库根目录、系统临时目录或 .cache/ 顶层。
  • 必须以表单 binding 只读结果证明 processCode 属于目标 formUuid;CONFIGURE_PROCESS_OWNERSHIP_UNVERIFIED 时停止,不得换一个 processCode 猜测重试。
  • 命令成功必须同时返回 verificationLevel: "PLATFORM_VIEW_VERIFIED" 和 platformViewVerified: true;它证明平台可见 view 的节点、组件、名称、顺序、审批模式、按钮权限及加签参数等已启用检查通过,不代表完整 processJson 已独立回读,也不代表运行结果已经验证。

节点选择

配置节点时加载 use_skill("yida-flow-node-config", "流程;所需节点类别或配置项"),只读取任务需要的参考。

类别流程中的节点本入口保留的差异
发起自动生成的 ApplyNode字段权限用顶层 startFormConfig;谁能发起用 START 权限组
人工处理approval、operator、multiApproval、carbon审批用 approver,办理用 executor,抄送用 receiver
流转控制route、parallel、循环条件/并行可直接生成;循环需已有真实配置
数据操作查询、新增、更新、删除流程内采用原生组件配置,不接收自动化 spec
通知消息、邮件、卡片消息可按通用说明生成;邮件/卡片需已有真实配置
扩展执行连接器、子流程、代码、AI使用真实节点配置;不得猜测动作、输入输出结构

“可直接生成配置”指 CLI 有已明确的输入契约;“需要已有真实配置才能透传”只说明编译器可接收该结构,不代表能从一句需求补齐全部参数。按金额等条件选择审批人、办理人或抄送人,统一读取 人员选择。同一节点选谁处理,与改变处理路线的条件分支分别配置。

基本步骤

涉及原生校验、业务关联或节点公式时,先通过 use_skill 加载 yida-formula,查看“写配置前先处理这些易错点”。校验保留原文、预处理内容、提示和阻断设置;节点表达式保留真实上游引用及编辑器内容。普通字段取值公式仍通过表单配置处理;当前简化 DSL 没有覆盖的全局规则或节点属性,沿用已读取的真实配置及明确支持的入口。

  1. 确认目标 appType/formUuid 和当前流程 binding,证明 processCode 属于该表单;不猜测 ID。
  2. 字段 ID 由 yida-get-schema 获取。配置字段权限或诊断字段来源时,先执行 process fields。
  3. 按需读取通用节点说明,组织完整的 nodes 与分支;保留未修改部分。字段 ≥ 3 且审批节点 ≥ 2 时,为每个处理节点配置字段权限。
  4. 用结构化文件写入工具创建 <projectRoot>/.cache/openyida/<任务名>/process-definition.json。不要用 shell heredoc 或重定向生成配置。
  5. 展示节点、处理人、条件、字段权限及替换范围,按上方严格要求获得用户明确同意后执行。CLI 负责本地编译、保存、发布和平台 view 回读。
  6. 保存真实资源 ID 与返回的验证等级。配置回读通过不代表实际审批、字段编辑或通知送达已验证。
bash
openyida process fields <appType> <formUuid> --json
openyida configure-process <appType> <formUuid> <processDefinitionFile> [processCode] [--replace]

文件路径按实际 project 根目录解析。已有流程不要通过更换 processCode 绕过归属或替换检查。

命令参数与输出

参数必填说明
appType是目标应用 ID
formUuid是目标流程表单 UUID
processDefinitionFile是完整流程定义 JSON 文件路径
processCode否流程 Code;不传时 CLI 从目标表单 binding 获取,仍须验证归属
--replace条件必填已有 PUBLISHED 流程或 SAVED 草稿时,须先获得整图替换确认;未确认时零写入退出
bash
openyida configure-process APP_XXX FORM_XXX .cache/openyida/order/process-definition.json

示例中的 ID 使用查询结果替换。上方路径从 OpenYida project 工作目录执行;从 workspace 根执行时加 project/ 前缀。执行前确认有效 token session;Node.js 版本按 OpenYida 包要求(当前 ≥ 18)。

日志写入 stderr,JSON 结果写入 stdout。成功结果示例:

json
{
  "success": true,
  "processCode": "TPROC--XXX",
  "processId": "83145794990",
  "processVersion": 2,
  "appType": "APP_XXX",
  "formUuid": "FORM_XXX",
  "verificationLevel": "PLATFORM_VIEW_VERIFIED",
  "platformViewVerified": true
}

最小定义与发起设置

CLI 自动生成发起和结束节点;nodes 只写中间节点,不添加 start/end。

json
{
  "startFormConfig": {
    "behaviorList": [
      {"fieldId":"<真实申请说明字段ID>","fieldBehavior":"NORMAL"},
      {"fieldId":"<真实成本字段ID>","fieldBehavior":"HIDDEN"}
    ]
  },
  "nodes": [
    {"type":"approval","name":"负责人审批","approver":"originator"}
  ]
}

发起、审批、办理等节点的字段权限共用 NORMAL/READONLY/HIDDEN;具体位置与子表规则统一见 use_skill("yida-flow-node-config", "字段权限")。控制谁能发起时,查询 get-permission --package-type FORM_PACKAGE_START,再交给 yida-form-permission。

结果与异常

成功需同时返回 verificationLevel: "PLATFORM_VIEW_VERIFIED" 和 platformViewVerified: true,这只证明平台 view 与本次目标配置匹配,不代表完整运行定义已独立回读。

配置前必须取得真实字段、人员和条件信息;保存失败时只读核对 binding、版本及登录态,字段或分支错误按对应参考修正,不能猜 ID。发布未生效时核对保存和发布阶段与流程版本,结果未知时不得重放写入。

结果处理
CONFIGURE_PROCESS_REPLACE_REQUIRED未获得整图替换授权时先展示摘要;已授权后补 --replace
CONFIGURE_PROCESS_OWNERSHIP_UNVERIFIED只读核对表单 binding,停止写入
PROCESS_PERMISSION_FIELD_NOT_FOUND / 字段来源错误修正真实字段或绑定,不覆盖表单
PROCESS_PLATFORM_VIEW_*_MISMATCH保留已返回资源,报告配置未验证
NON_IDEMPOTENT_RESULT_UNKNOWN / PUBLISHED_UNVERIFIED先只读核对平台状态,不自动重试保存或发布
权益不足保留平台错误;根据明确提示说明所需版本或权益包,不修改权益

普通指定角色不需要配置权限矩阵。涉及矩阵时,先按 yida-form-permission 的 CLI 步骤检查可用性;其他配置按 CLI 返回处理,明确提示权益不足时再引导开通。

需要完整业务流程示例时读 流程示例;配置官方组件时读 高级透传规则与节点示例。根据需求生成流程时必须遵守上方严格要求和 生成规则。新建流程仍由 yida-create-process 编排,本技能不创建应用或维护数据记录。

与其他技能配合

需要处理的资源使用方式
应用复用已解析的 appType;仅无应用且用户允许创建时使用 yida-create-app
表单复用已解析的 formUuid;普通表单字段由 yida-create-form-page 维护,首次转流程按使用门槛调用 yida-create-process --formUuid
流程规则已有流程使用本技能;yida-create-process 完成后仍可回到本技能补充复杂规则
自定义页面用户需要时才用 yida-canvas-custom-page 编写或更新源码,再用 yida-publish-page 发布

从零创建流程表单可由 yida-create-process 编排表单与流程两步;该快捷入口不能绕过已有资源的复用限制。

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 Process Rule AI skill do?

配置已有宜搭流程的节点、分支、人员、字段权限、跳转规则、操作按钮及官方组件高级透传;共用节点参数按需加载 yida-flow-node-config。

Why use Yida Process Rule on TypingMind?

Because you install it once and use it with any model. Yida Process Rule 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 Process Rule in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/openyida/openyida/tree/main/yida-skills/skills/yida-process-rule. 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 Process Rule?

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 Process Rule?

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

Is the Yida Process Rule 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 👇