Agent skill

Yida Get Schema

确定性解析表单字段 ID、子表路径和表单行为语义；agent 按字段引用、完整字段映射或反向分析场景选择对应 contract。

MITAuto-check passed

Install Yida Get Schema

skills CLI

$ npx skills add openyida/openyida --skill yida-get-schema -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install openyida/openyida yida-get-schema --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/openyida/openyida.git skills-src && mkdir -p .claude/skills && cp -r skills-src/yida-skills/skills/yida-get-schema .claude/skills/yida-get-schema && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "yida-get-schema" agent skill from https://github.com/openyida/openyida/tree/main/yida-skills/skills/yida-get-schema into .claude/skills/yida-get-schema/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "yida-get-schema", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/openyida/openyida/tree/main/yida-skills/skills/yida-get-schema

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add openyida/openyida --skill yida-get-schema -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install openyida/openyida yida-get-schema --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/openyida/openyida.git skills-src && mkdir -p .agents/skills && cp -r skills-src/yida-skills/skills/yida-get-schema .agents/skills/yida-get-schema && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "yida-get-schema" agent skill from https://github.com/openyida/openyida/tree/main/yida-skills/skills/yida-get-schema into .agents/skills/yida-get-schema/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "yida-get-schema", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add openyida/openyida --skill yida-get-schema -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install openyida/openyida yida-get-schema --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/openyida/openyida.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/yida-skills/skills/yida-get-schema .cursor/skills/yida-get-schema && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "yida-get-schema" agent skill from https://github.com/openyida/openyida/tree/main/yida-skills/skills/yida-get-schema into .cursor/skills/yida-get-schema/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "yida-get-schema", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/openyida/openyida.git --path yida-skills/skills/yida-get-schema

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add openyida/openyida --skill yida-get-schema -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install openyida/openyida yida-get-schema --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/openyida/openyida.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/yida-skills/skills/yida-get-schema .gemini/skills/yida-get-schema && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "yida-get-schema" agent skill from https://github.com/openyida/openyida/tree/main/yida-skills/skills/yida-get-schema into .gemini/skills/yida-get-schema/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "yida-get-schema", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install openyida/openyida yida-get-schema

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add openyida/openyida --skill yida-get-schema -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/openyida/openyida.git skills-src && mkdir -p .github/skills && cp -r skills-src/yida-skills/skills/yida-get-schema .github/skills/yida-get-schema && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "yida-get-schema" agent skill from https://github.com/openyida/openyida/tree/main/yida-skills/skills/yida-get-schema into .github/skills/yida-get-schema/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "yida-get-schema", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add openyida/openyida --skill yida-get-schema -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install openyida/openyida yida-get-schema --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/openyida/openyida.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/yida-skills/skills/yida-get-schema .opencode/skills/yida-get-schema && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "yida-get-schema" agent skill from https://github.com/openyida/openyida/tree/main/yida-skills/skills/yida-get-schema into .opencode/skills/yida-get-schema/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "yida-get-schema", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: yida-get-schema
GitHub stars: 220
Token cost: ~2k tokens
SKILL.md length: 462 words
Files: 1
Skills in repo: 58
Repo updated: Sep 30, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

确定性解析表单字段 ID、子表路径和表单行为语义；agent 按字段引用、完整字段映射或反向分析场景选择对应 contract。

SKILL.md covers 严格禁止 (NEVER DO), 严格要求 (MUST DO), 适用场景 and 触发条件, plus 3 more sections
Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Yida Get Schema is an agent skill from openyida/openyida. 确定性解析表单字段 ID、子表路径和表单行为语义；agent 按字段引用、完整字段映射或反向分析场景选择对应 contract。

Its SKILL.md is about 2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: Your own personal YiDA AI assistant! The licence is MIT.

Example prompts

“/yida-get-schema”

What it can do on your machine

Read from SKILL.md and the folder at commit 3dd4693. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are bash and json).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Yida Get Schema loads about 2k tokens when it runs. Until then it costs about 20 tokens; SKILL.md has 462 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~20
When it runs · the whole SKILL.md, loaded when a task matches: ~2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from openyida/openyida at commit 3dd4693, republished under its MIT licence (© openyida). 462 words, ~2,019 tokens.

Download SKILL.mdSave it as .claude/skills/yida-get-schema/SKILL.md (or your agent's skills folder).

name: yida-get-schema
description: 确定性解析表单字段 ID、子表路径和表单行为语义；agent 按字段引用、完整字段映射或反向分析场景选择对应 contract。

获取表单 Schema

严格禁止 (NEVER DO)

绝对禁止猜测或编造 fieldId，宜搭字段 ID 由平台随机生成（格式如 textField_eftt1aa5m、selectField_fix024y92），无法从字段名称推断，必须通过此命令获取
不要在未获取 Schema 的情况下执行任何涉及字段 ID 的操作
不要假设字段 ID 格式，即使看起来像 textField_xxx，也必须通过命令确认
不要跳过 Schema 获取步骤直接进行数据操作，即使用户催促也必须先获取
不要在 Schema 获取失败时继续执行后续操作，必须先解决问题
不要缓存过期的 Schema 信息，表单结构变更后必须重新获取
不要把进程内状态或 CLI 自动派生索引当作跨调用缓存；查询新字段时允许重新拉取完整 Schema
不要把 openyida get-schema 的 stdout 通过 shell 重定向保存成 JSON，也不要用 heredoc、cat/echo/printf/tee 生成 Schema 文件
不要把 openyida get-schema 的 stdout 再接 head、tail、grep、sed、awk 等截断/筛选命令作为 Schema 证据；这会丢字段、选项或子表路径，导致后续重复拉取
不要在同一阶段对同一个 formUuid 连续执行 --compact、--field-map-json、完整 Schema 等多轮“探一段 stdout”式查询；除非表单刚被修改、上次命令失败/不完整，或排障需要完整组件 props

严格要求 (MUST DO)

凡是需要用到字段 ID（fieldId）的操作，必须先执行此命令，不得跳过
页面开发、数据查询、报表配置或流程规则只需要字段身份时，先执行 openyida get-schema <appType> <formUuid> --compact --resolve-fields "<字段1,字段2>"，不要拉取完整 Schema
页面开发默认使用 compact 输出，只读取必要字段契约，不内联完整 Schema
完整应用页面、看板、列表或详情页需要一个表单的大部分字段，或需要跨多个表单建立 dataBinding 时，优先对每个表单执行一次 openyida get-schema <appType> <formUuid> --field-map-json，消费完整 JSON 后解析所需字段，不用 shell 截断 stdout
分析、复刻或迁移已有表单时，执行一次 openyida get-schema <appType> <formUuid> --analysis-json，同时消费字段与 semantics.actions/fieldBehaviors/associationRuleCount；不得只凭 field map 推断原表单没有生命周期、联动、公式、关联或数据源行为
多表单场景同一阶段同一 formUuid 默认最多拉取一次字段映射；把 appType、formUuid、fieldId、label、componentName、options 等合并写入 <projectRoot>/.cache/<项目名>-schema.json，后续 page-spec.json 和源码复用该本地 ID 映射
执行 compact 查询后，只消费唯一命中的 fields[]；missingFields 或 ambiguousFields 非空时停止，不得猜测或继续写操作
只有用户明确需要完整组件 props、布局结构、字段数据源配置，或 compact/summary 无法排障时，才执行不带 --compact/--summary-json 的完整 Schema 输出；拿到完整 Schema 后只读取必要片段，不内联完整 Schema
已有 <projectRoot>/.cache/<项目名>-schema.json 等本地 ID 映射文件可显式复用；目标字段缺失、重名、结构已变或无法确认新鲜度时，必须重新执行 compact 查询
如需保存关键字段 ID 映射，使用结构化文件写入工具；这是 agent 管理的本地工件，不是 OpenYida CLI 自动缓存
如需保存完整 Schema 文件，先执行命令获取 stdout，再用 create_file / Write / file edit tool 写入 <projectRoot>/.cache/openyida/<项目名或任务名>/<表单名>-schema.json；从 workspace 根执行后续命令时传 project/.cache/...
录入/更新数据后，必须用 openyida data query --size 1 抽查一条记录，确认 formData 中字段有实际值（非空 ""），若全部为空说明字段 ID 有误，需重新排查

适用场景

在执行以下操作前必须使用：

新增/录入表单数据（yida-data-management create）← 最常见的遗漏场景，必须先 get-schema
更新表单数据（yida-data-management update）
配置数据查询条件（yida-data-management query searchFieldJson）
更新表单字段结构（yida-create-form-page update 模式）
配置流程字段权限（yida-process-rule）
自定义页面中引用字段 ID 常量（ yida-canvas-custom-page）

触发条件

正向触发：

任何需要用到 fieldId 的操作前（自动前置触发）
"查看表单结构"、"获取字段 ID"、"查看 Schema"
"分析/复刻/迁移已有表单"、"比较表单行为"、"查看生命周期/联动/公式/数据源"
其他技能（yida-data-management、yida-process-rule、页面源码维护技能）执行前的字段 ID 前置步骤
"批量获取所有表单 Schema"、"导出应用下所有字段 ID"、"不知道 formUuid 先全量看一遍"

命令

bash

openyida get-schema <appType> <formUuid> --compact [--resolve-fields <labelOrFieldId,...>]
openyida get-schema <appType> <formUuid> [--summary-json|--field-map-json]
openyida get-schema <appType> <formUuid> --analysis-json
openyida get-schema <appType> --all [--summary-json|--analysis-json] [--output-dir <dir>] [--keyword <text>] [--concurrency N] [--retries N]

两个位置参数顺序固定：先传 appType，再传 formUuid，不得调换。

参数	必填	说明
`appType`	是	应用 ID
`formUuid`	单表模式必填	表单 UUID
`--compact`	否	输出 `yida_schema_field_resolution` contract v1，不输出完整 Schema
`--resolve-fields <query,...>`	否	按精确 label、fieldId、alias、稳定 ID 路径或 `子表/字段` 可读路径筛选；可重复，自动启用 compact
`--all`	批量模式必填	获取应用下所有表单/页面的 Schema
`--output-dir <dir>`	否	将每个 Schema 写入独立 JSON 文件，并生成 `index.json`
`--keyword <text>`	否	仅批量导出名称、UUID、类型或路径匹配关键词的表单
`--concurrency N`	否	批量并发数，默认 3，范围 1-10
`--retries N`	否	单个 Schema 失败后的重试次数，默认 1，范围 0-5
`--summary-json` / `--field-map-json`	否	只输出字段摘要 JSON，不把完整 Schema 放入 stdout；`--field-map-json` 是语义别名
`--analysis-json`	否	输出 `yida_schema_semantic_analysis` contract v1：字段摘要、动作函数/绑定、URL 参数、字段 mutation、只读/隐藏、校验、公式/联动、关联和数据源摘要；不回显动作源码

Show full SKILL.md (173 more words)Show less

单表模式

bash

openyida get-schema APP_XXX FORM-XXX --compact --resolve-fields "访客姓名,状态"
openyida get-schema APP_XXX FORM-XXX --field-map-json
openyida get-schema APP_XXX FORM-XXX --analysis-json

Agent 只需要少量字段 ID 时，默认使用 --compact --resolve-fields，读取 fields[].label、fields[].fieldId、fields[].componentType、fields[].valueType、fields[].path、fields[].labelPath 和 fields[].parentFieldId。path 是稳定的 fieldId 数组，labelPath 是可读路径；所有可用语言的 label 都参与精确匹配。同名字段会进入 ambiguousFields[].matches，必须使用完整 labelPath、稳定 path 或已返回的 fieldId 重新精确选择，禁止取第一个。

需要全量字段摘要和选项时继续使用 --summary-json。只有需要组件完整 props、布局结构、字段数据源配置或排障时，才执行不带 compact/summary 参数的完整 Schema 输出。

反向分析时读取 --analysis-json，重点区分：源码字节数大不等于业务行为多；以 urlParams、fieldMutations、动作绑定、字段行为、关联规则和数据源摘要判断业务语义。需要等价迁移时，把字段结构与行为结构分别交给 yida-create-form-page，不要把缺失行为误报成“字段已创建所以表单完成”。

消费输出时读取完整 JSON，再由 agent / 脚本解析字段；不要用 tail -20、head -30 或 grep 只看局部 stdout。局部查看可以作为人工调试，但不能作为后续写页面、写数据或配置流程的字段证据。

如需复用输出，使用 agent 的结构化文件写入工具创建：

text

<projectRoot>/.cache/openyida/customer/customer-schema.json
<projectRoot>/.cache/customer-schema.json   # 仅保存 appType/formUuid/fieldId/reportId 等 ID 映射

批量模式

bash

openyida get-schema APP_XXX --all --summary-json --output-dir .cache/openyida/customer/schemas
openyida get-schema APP_XXX --all --analysis-json --output-dir .cache/openyida/customer/schema-analysis
openyida get-schema APP_XXX --all --keyword 客户 --concurrency 5 --retries 2

批量模式会先读取应用导航中的表单/页面列表，再逐个请求 getFormSchema。如果指定 --output-dir：

每个成功的 Schema 会写入 <表单名>-<formUuid>.json
index.json 会记录 formUuid、名称、类型、字段摘要、失败原因和 schema 文件路径
stdout 仍输出汇总 JSON，便于脚本继续处理

输出

Agent compact 模式输出共享 contract，不包含完整 Schema 或 props：

json

{
  "kind": "yida_schema_field_resolution",
  "contractVersion": 1,
  "resource": {
    "appType": "APP_XXX",
    "formUuid": "FORM-XXX",
    "schemaHash": "sha256:<64位小写十六进制>"
  },
  "fields": [
    {
      "query": "订单明细/商品名称",
      "label": "商品名称",
      "fieldId": "textField_xxx",
      "componentType": "TextField",
      "valueType": "custom",
      "path": ["tableField_xxx", "textField_xxx"],
      "labelPath": ["订单明细", "商品名称"],
      "parentFieldId": "tableField_xxx",
      "alias": ""
    }
  ],
  "missingFields": [],
  "ambiguousFields": []
}

--compact 不带 --resolve-fields 时按 Schema 顺序返回全部正规化字段。指定 --resolve-fields 时，fields 只含唯一命中项，未命中和重名分别进入 missingFields、ambiguousFields。

单表模式默认仍将完整的 Schema JSON 输出到 stdout，包含 pages、componentsMap 等字段结构；兼容摘要模式可用 --summary-json 或 --field-map-json：

json

{
  "success": true,
  "appType": "APP_XXX",
  "formUuid": "FORM-XXX",
  "fieldCount": 2,
  "fields": [
    {
      "label": "访客姓名",
      "componentName": "TextField",
      "fieldId": "textField_xxx",
      "alias": "visitorName",
      "reportFieldCode": "textField_xxx",
      "options": [],
      "optionCount": 0,
      "optionsTruncated": false
    }
  ]
}

批量模式将汇总 JSON 输出到 stdout；指定 --output-dir 时，完整 Schema 写入文件，stdout 中的 forms[].schemaFile 指向对应文件。加 --summary-json 时，stdout 和 index.json 都只保留字段摘要与 schemaFile 指针，不内联完整 Schema。

编码前可用此命令确认表单中各字段的 fieldId。

异常处理

异常场景	处理方式
命令返回失败	确认 appType 和 formUuid 正确，检查登录态
输出被终端截断	优先改用 `--summary-json`；确需完整 Schema 时，再将 stdout 通过结构化文件写入工具保存到 `<projectRoot>/.cache/openyida/<项目名或任务名>/<表单名>-schema.json`；不要使用 shell 重定向
需要多个表单字段 ID	使用批量摘要或每表单完整字段映射：`openyida get-schema <appType> --all --summary-json --output-dir .cache/openyida/<项目名或任务名>/schemas`，或对目标表单逐个执行一次 `--field-map-json`；默认只读完整 JSON / `index.json` 字段摘要，不用 `head`/`tail`/`grep` 截断
批量部分失败	查看 stdout 的 `failedCount` 和 `forms[].errorMsg`，必要时提高 `--retries` 或缩小 `--keyword` 范围
找不到目标字段	查看 `missingFields`，确认字段已创建后重新查询；不能手写猜测 fieldId
同名字段无法唯一确定	查看 `ambiguousFields[].matches[].labelPath` 和稳定 `path`，使用完整路径或 fieldId 重新查询；不得默认取第一个
Schema 输出为空	表单可能没有字段，先用 `yida-create-form-page` 创建字段

Files

Just SKILL.md in yida-skills/skills/yida-get-schema of openyida/openyida.

Open the folder on GitHubat commit 3dd4693

Compare with similar skills

Yida Get Schema next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Yida Get Schema compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Yida Get Schema this skillopenyida/openyida	220	—	~2k	Automated safety check: Pass	MIT	8 days ago
Yida DevLeoYeAI/openclaw-master-skills	2.2k	—	~5k	Automated safety check: Pass	MIT	2 mo ago
Yida Dashboardopenyida/openyida	220	—	~1.4k	Automated safety check: Pass	MIT	8 days ago
Yida Appopenyida/openyida	220	—	~2.2k	Automated safety check: Pass	MIT	8 days ago
Yida I18nopenyida/openyida	220	—	~909	Automated safety check: Pass	MIT	8 days ago
Yida Tingjiopenyida/openyida	220	—	~283	Automated safety check: Pass	MIT	8 days ago

Similar skills

Yida Dev
LeoYeAI/openclaw-master-skills
钉钉宜搭低代码开发助手。用于创建表单和自定义页面、编写 JS 动作面板、使用 JS-API、配置数据源、设计流程自动化。适用于宜搭表单开发、JS 代码调试、API 集成等场景。
2.2k GitHub stars~5k tokensUpdated 2 mo ago
Auto-check passed
Yida Dashboard
openyida/openyida
经营分析看板/驾驶舱/数据大屏产品化交付；用于指标判断、趋势分析或投屏监控，不用于普通待办工作台和办事门户。含真实数据、筛选联动、卡片截图、组织内短链和钉钉待办闭环。常规图表使用 yida-rechart；明确 ECharts、复杂 ECharts option 或维护旧图表时使用 yida-chart。普通统计优先 yida-report。
220 GitHub stars~1.4k tokensUpdated 8 days ago
Frontend & DesignAuto-check passed
Yida App
openyida/openyida
创建完整宜搭应用，或补齐已有应用时使用。先确认核心功能和实际用法；Fast 直接搭建，Plan 先确认方案。由 yida-prd 和 yida-design 同时准备业务与基础视觉，校验后创建或复用资源；表单/流程先于自定义页面。页面 UI 按已确认设计实现，代码示例按需参考；前后台都规划菜单顺序与默认页面，发布后分别验收实际入口。
220 GitHub stars~2.2k tokensUpdated 8 days ago
Product & Project ManagementAuto-check passed
Yida I18n
openyida/openyida
应用多语言管理。查询和维护宜搭应用的语言配置、文案词条、翻译状态、一键翻译和多语言升级。适用于全球化设置 / 多语言管理页面；需要应用已开通国际化能力包，或运行在 Global YiDA 环境（默认入口为 www.yidaapps.com，且支持客户自定义二级域名）。
220 GitHub stars~909 tokensUpdated 8 days ago
Frontend & DesignAuto-check passed
Yida Tingji
openyida/openyida
按 taskUuid 获取钉钉听记、会议录音转写、会议纪要或 AI 听记的完整详情；只负责读取内容。若用户要求转 PRD，先用本技能取内容，再交给 yida-flash-note-to-prd。
220 GitHub stars~283 tokensUpdated 8 days ago
Product & Project ManagementAuto-check passed
Yida Chart
openyida/openyida
ECharts 高级可视化报表。依赖宜搭原生报表 getDataAsync.json 接口获取聚合数据，禁止前端聚合。触发词：「更美观」「ECharts」「大屏」「定制化」。普通「报表」「统计」需求默认由 yida-report 处理。
220 GitHub stars~1.7k tokensUpdated 8 days ago
Auto-check passed

Questions about Yida Get Schema

What does Yida Get Schema do?

确定性解析表单字段 ID、子表路径和表单行为语义；agent 按字段引用、完整字段映射或反向分析场景选择对应 contract。. Yida Get Schema is an agent skill from openyida/openyida.

How do I install Yida Get Schema in Claude Code?

Run `npx skills add openyida/openyida --skill yida-get-schema -a claude-code`. Or copy the skill folder (yida-skills/skills/yida-get-schema in openyida/openyida) into .claude/skills/yida-get-schema in your project. Claude Code loads it when a task matches its description.

How do I install Yida Get Schema in Codex?

Run `npx skills add openyida/openyida --skill yida-get-schema -a codex`. Or copy the skill folder (yida-skills/skills/yida-get-schema in openyida/openyida) into .agents/skills/yida-get-schema in your project. Codex loads it when a task matches its description.

Can I use Yida Get Schema in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add openyida/openyida --skill yida-get-schema -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/yida-get-schema, .gemini/skills/yida-get-schema, .github/skills/yida-get-schema and .opencode/skills/yida-get-schema in your project.

What does Yida Get Schema need to run?

SKILL.md names no scripts, command-line tools or credentials: Yida Get Schema is instructions for the agent only.

Does Yida Get Schema access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Yida Get Schema safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Yida Get Schema use?

Yida Get Schema is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Yida Get Schema use?

About 2k tokens (SKILL.md is roughly 8.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Yida Get Schema?

Skills that share tags, products or a category with Yida Get Schema: Yida Dev (LeoYeAI/openclaw-master-skills, 2.2k stars), Yida Dashboard (openyida/openyida, 220 stars), Yida App (openyida/openyida, 220 stars) and Yida I18n (openyida/openyida, 220 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Yida Get Schema?

openyida (a GitHub organization) maintains it in openyida/openyida, which has 220 GitHub stars. The repository holds 58 skills in this directory. The repository was last updated on September 30, 2026.

Source: openyida/openyida on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Yida Get Schema

Facts

At a glance

What it does

Example prompts

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

获取表单 Schema

严格禁止 (NEVER DO)

严格要求 (MUST DO)

适用场景

触发条件

命令

单表模式

批量模式

输出

异常处理

Files

Compare with similar skills

Similar skills

More from openyida/openyida

Questions about Yida Get Schema