Token导航 LogoToken导航TokenDH.com
开发external-servicegithub未标认证来源可访问许可证需确认审计提醒

orchestrate-multi-target-sdks编排多目标 SDK

Agent Skill

orchestrate-multi-target-sdks 用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要围绕仓库状态、代码变更或协作事项进行整理时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

950

周安装

40

GitHub Stars

13

下载量

333
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:orchestrate-multi-target-sdks(编排多目标 SDK)
来源仓库:https://github.com/speakeasy-api/skills
仓库路径:skills/orchestrate-multi-target-sdks
安装命令:
npx skills add https://github.com/speakeasy-api/skills --skill orchestrate-multi-target-sdks
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/speakeasy-api/skills --skill orchestrate-multi-target-sdks

简介

orchestrate-multi-target-sdks 用于处理 GitHub 仓库、Issue 和 Pull Request。

  • 适合围绕代码变更和协作事项进行整理与协调。
  • 可结合来源仓库和原始 README 核验具体用法。
  • 安装前建议确认权限范围、维护状态及是否触发联网或文件操作。
  • 适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

SKILL.md

Orchestrate Multi-Target SDKs

Generate SDKs for multiple languages or variants from a single repository using CLI commands.

When to Use

  • Generating SDKs for multiple languages from the same API spec
  • Creating SDK variants (Azure, GCP, regional) from different specs
  • Setting up an SDK monorepo
  • User says: "generate SDKs for multiple languages", "SDK for each language", "multi-target"

Quick Start: Multiple Languages

Always use CLI commands. Never create .speakeasy directories manually.

# Step 1: Initialize first target (creates .speakeasy/workflow.yaml)
speakeasy quickstart --skip-interactive --output console \
  -s openapi.yaml -t typescript -n "MySDK" -p "my-sdk"

# Step 2: Add more language targets using configure
speakeasy configure targets \
  --target-type python \
  --source my-source \
  --output ./sdks/python

speakeasy configure targets \
  --target-type go \
  --source my-source \
  --output ./sdks/go

# Step 3: Generate all SDKs
speakeasy run --output console

CLI Reference

speakeasy configure sources

Add a new OpenAPI source to an existing workflow:

speakeasy configure sources \
  --location ./openapi.yaml \
  --source-name my-api

# With authentication header
speakeasy configure sources \
  --location https://api.example.com/openapi.yaml \
  --source-name my-api \
  --auth-header "Authorization"
FlagShortDescription
--location-lOpenAPI document location (file or URL)
--source-name-sName for the source
--auth-headerAuthentication header name (optional)
--output-oOutput path for compiled source (optional)
--non-interactiveForce non-interactive mode

speakeasy configure targets

Add a new SDK target to an existing workflow:

speakeasy configure targets \
  --target-type typescript \
  --source my-api \
  --output ./sdks/typescript

# With all options
speakeasy configure targets \
  --target-type go \
  --source my-api \
  --target-name my-go-sdk \
  --sdk-class-name MyAPI \
  --package-name github.com/myorg/myapi-go \
  --output ./sdks/go
FlagShortDescription
--target-type-tLanguage: typescript, python, go, java, csharp, php, ruby, terraform
--source-sName of source to generate from
--target-nameName for the target (defaults to target-type)
--sdk-class-nameSDK class name (optional)
--package-namePackage name (optional)
--base-server-urlBase server URL (optional)
--output-oOutput directory (optional)
--non-interactiveForce non-interactive mode

Example: Multi-Language SDKs

Single OpenAPI spec → TypeScript, Python, Go SDKs:

# Initialize with first target
speakeasy quickstart --skip-interactive --output console \
  -s ./openapi.yaml -t typescript -n "MySDK" -p "my-sdk" -o ./sdks/typescript

# Add Python
speakeasy configure targets \
  --target-type python \
  --source my-source \
  --sdk-class-name MySDK \
  --package-name my-sdk \
  --output ./sdks/python

# Add Go
speakeasy configure targets \
  --target-type go \
  --source my-source \
  --sdk-class-name MySDK \
  --package-name github.com/myorg/my-sdk-go \
  --output ./sdks/go

# Generate all
speakeasy run --output console

Example: SDK Variants (Multiple Sources)

Different OpenAPI specs → variant SDKs:

# Initialize with main API
speakeasy quickstart --skip-interactive --output console \
  -s ./openapi.yaml -t typescript -n "MySDK" -p "my-sdk"

# Add Azure variant source
speakeasy configure sources \
  --location ./openapi-azure.yaml \
  --source-name azure-api

# Add Azure target
speakeasy configure targets \
  --target-type typescript \
  --source azure-api \
  --target-name typescript-azure \
  --sdk-class-name MySDKAzure \
  --package-name "@myorg/my-sdk-azure" \
  --output ./packages/azure

# Generate all
speakeasy run --output console

Repository Structure

my-api-sdks/
├── openapi.yaml              # Source spec
├── .speakeasy/
│   └── workflow.yaml         # Multi-target config (created by CLI)
├── sdks/
│   ├── typescript/
│   │   ├── .speakeasy/
│   │   │   └── gen.yaml      # Created by configure
│   │   └── src/
│   ├── python/
│   │   ├── .speakeasy/
│   │   │   └── gen.yaml
│   │   └── src/
│   └── go/
│       ├── .speakeasy/
│       │   └── gen.yaml
│       └── go.mod
└── .github/workflows/
    └── sdk_generation.yaml

Running Generation

# Generate all targets
speakeasy run --output console

# Generate specific target only
speakeasy run -t typescript --output console
speakeasy run -t python --output console

CI Workflow

# .github/workflows/sdk_generation.yaml
name: Generate SDKs
on:
  push:
    branches: [main]
    paths: ['openapi.yaml']
  workflow_dispatch:

jobs:
  generate:
    uses: speakeasy-api/sdk-generation-action/.github/workflows/workflow-executor.yaml@v15
    with:
      mode: pr
    secrets:
      github_access_token: ${{ secrets.GITHUB_TOKEN }}
      speakeasy_api_key: ${{ secrets.SPEAKEASY_API_KEY }}

What NOT to Do

  • Do NOT create .speakeasy/ directories manually - Use speakeasy quickstart and speakeasy configure
  • Do NOT write workflow.yaml or gen.yaml files directly - Use CLI commands
  • Do NOT copy .speakeasy/ directories between projects - Each needs its own config

Incorrect

# WRONG: Do not do this
mkdir -p .speakeasy
cat > .speakeasy/workflow.yaml << 'EOF'
...
EOF

Correct

# RIGHT: Use CLI commands
speakeasy quickstart --skip-interactive --output console \
  -s openapi.yaml -t typescript -n "MySDK" -p "my-sdk"

speakeasy configure targets --target-type python --source my-source

Troubleshooting

IssueSolution
Wrong target generatedSpecify -t target-name in speakeasy run
Source not foundRun speakeasy configure sources to add it
Target not foundRun speakeasy configure targets to add it
Config out of syncRun speakeasy run to regenerate

After Making Changes

After adding sources or targets, regenerate:

speakeasy run --output console

After Making Changes

After modifying workflow.yaml or per-target gen.yaml, prompt the user to regenerate the SDK(s):

Configuration complete. Would you like to regenerate the SDK(s) now with speakeasy run?

If the user confirms, run:

# Generate all targets
speakeasy run --output console

# Or generate a specific target
speakeasy run -t <target-name> --output console

Changes to workflow.yaml and gen.yaml only take effect after regeneration.

Related Skills

  • start-new-sdk-project - Initial SDK setup for single target
  • configure-sdk-options - Language-specific gen.yaml options
  • manage-openapi-overlays - Spec customization with overlays
  • orchestrate-multi-repo-sdks - Separate repository per language

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

32.62%
按下载量换算109

Claude

31.62%
按下载量换算105

Cursor

18.22%
按下载量换算61

Gemini CLI

10.05%
按下载量换算33

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

可疑

权限和风险

external-service

该 Skill 可能调用第三方服务、云服务或外部模型 API,使用前需要确认账号、额度、数据发送范围和服务条款。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills