ms-customer-stories

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Microsoft Customer Stories

Overview

概述

Search and retrieve customer stories from Microsoft's official Customer Stories site via its internal API.

通过微软官方客户案例网站的内部API搜索并获取客户案例。

Important: Script Location

重要提示：脚本位置

The

scripts/

directory and

references/

directory are located in the same directory as this SKILL.md file. Before running any commands, locate the directory where this SKILL.md resides and use it as the base path for all script references below.

For example, if this SKILL.md is at

<skill_dir>/SKILL.md

, then:

Search script:
```
<skill_dir>/scripts/search_stories.py
```
Fetch script:
```
<skill_dir>/scripts/fetch_story.py
```
Filter reference:
```
<skill_dir>/references/filters.md
```

scripts/

目录和

references/

目录与本SKILL.md文件位于同一目录。在运行任何命令前，请找到本SKILL.md所在的目录，并将其作为以下所有脚本引用的基础路径。

例如，如果本SKILL.md位于

<skill_dir>/SKILL.md

，则：

搜索脚本：
```
<skill_dir>/scripts/search_stories.py
```
获取脚本：
```
<skill_dir>/scripts/fetch_story.py
```
过滤参考文档：
```
<skill_dir>/references/filters.md
```

Important: Python Execution

重要提示：Python执行方式

Before running scripts, determine the correct way to invoke Python in the current project. Check in this order:

uv
is available and
.venv/
exists: Use
```
uv run python <script>
```
Virtual environment (
.venv/
) exists without
uv
: Activate it or use
```
.venv/Scripts/python <script>
```
(Windows) /
```
.venv/bin/python <script>
```
(macOS/Linux)
System Python: Use
```
python <script>
```
or
```
python3 <script>
```

Use the detected Python command (referred to as

{python}

below) for all script executions.

在运行脚本前，请确定当前项目中调用Python的正确方式。请按以下顺序检查：

uv
可用且存在
.venv/
目录：使用
```
uv run python <script>
```
存在虚拟环境（
.venv/
）但无
uv
：激活虚拟环境，或使用
```
.venv/Scripts/python <script>
```
（Windows系统）/
```
.venv/bin/python <script>
```
（macOS/Linux系统）
系统Python：使用
```
python <script>
```
或
```
python3 <script>
```

请使用检测到的Python命令（以下简称

{python}

）执行所有脚本。

Prerequisites

前置条件

Install the

requests

package in the Python environment. Choose the method that matches your setup:

uv:
```
uv pip install requests
```
pip (venv):
```
pip install requests
```
(after activating the virtual environment)

pip (system):

pip install requests

pip3 install requests

在Python环境中安装

requests

包，请选择与你的环境匹配的安装方式：

uv：
```
uv pip install requests
```
pip（虚拟环境）：激活虚拟环境后执行
```
pip install requests
```

pip（系统Python）：执行

pip install requests

或

pip3 install requests

Workflow

工作流程

Locate the directory containing this SKILL.md to determine script paths (
```
<skill_dir>
```
)
Determine the Python execution command (
```
{python}
```
) as described above
Analyze the user's request to determine appropriate filters
Run
```
{python} <skill_dir>/scripts/search_stories.py
```
with selected filters to find matching stories
Review results and optionally run
```
{python} <skill_dir>/scripts/fetch_story.py
```
on specific stories for full details
Summarize findings for the user

找到本SKILL.md所在的目录以确定脚本路径（
```
<skill_dir>
```
）
按照上述方法确定Python执行命令（
```
{python}
```
）
分析用户请求以确定合适的过滤条件
运行
```
{python} <skill_dir>/scripts/search_stories.py
```
并传入选定的过滤条件，查找匹配的案例
查看结果，可选地对特定案例运行
```
{python} <skill_dir>/scripts/fetch_story.py
```
以获取完整详情
为用户总结查找结果

Step 1: Map User Request to Filters

步骤1：将用户请求映射为过滤条件

Translate the user's natural language request into API filter parameters. Consult

<skill_dir>/references/filters.md

for the complete list of available filter values.

Mapping guidelines:

User mentions	Filter to use
Country/region names (Japan, US, etc.)	`--region` (e.g., `asia/japan` )
Product names (Azure, Teams, etc.)	`--products` (e.g., `azure/azure-openai` )
Industry terms (healthcare, finance, etc.)	`--industry` (e.g., `healthcare` )
Business concepts (AI, automation, etc.)	`--business-need` (e.g., `artificial-intelligence` )
Company size (SMB, enterprise, etc.)	`--org-size` (e.g., `50-999-employees` )
Specific technology terms (RAG, etc.)	`--query` (free text search)

Common mappings:

"中小企業" / "SMB" →

--org-size 50-999-employees

--org-size 1-49-employees

"大企業" / "Enterprise" →
```
--org-size 10000-employees
```

"RAG" / "検索拡張生成" →

--query RAG

--products azure/azure-openai

"日本" →
```
--region asia/japan
```

将用户的自然语言请求转换为API过滤参数。请查阅

<skill_dir>/references/filters.md

获取所有可用过滤值的完整列表。

映射指南：

用户提及内容	使用的过滤参数
国家/地区名称（日本、美国等）	`--region` （例如： `asia/japan` ）
产品名称（Azure、Teams等）	`--products` （例如： `azure/azure-openai` ）
行业术语（医疗、金融等）	`--industry` （例如： `healthcare` ）
业务概念（AI、自动化等）	`--business-need` （例如： `artificial-intelligence` ）
企业规模（中小企业、大型企业等）	`--org-size` （例如： `50-999-employees` ）
特定技术术语（RAG等）	`--query` （自由文本搜索）

常见映射：

"中小企業" / "SMB" →

--org-size 50-999-employees

或

--org-size 1-49-employees

"大企業" / "Enterprise" →
```
--org-size 10000-employees
```

"RAG" / "検索拡張生成" →

--query RAG

--products azure/azure-openai

"日本" →
```
--region asia/japan
```

Step 2: Search Stories

步骤2：搜索案例

Run the search script:

bash

{python} <skill_dir>/scripts/search_stories.py --products azure/azure-openai --region asia/japan --query "RAG" --top 10

Arguments:

```
--query
```
/
```
-q
```
: Free text search

--products

-p

: Product filter (e.g.,

azure/azure-openai

azure/azure-ai-search

)

```
--region
```
/
```
-r
```
: Region filter (e.g.,
```
asia/japan
```
,
```
europe/germany
```
)
```
--industry
```
/
```
-i
```
: Industry filter (e.g.,
```
healthcare
```
,
```
manufacturing
```
)

--business-need

-b

: Business need (e.g.,

artificial-intelligence

)

```
--org-size
```
/
```
-o
```
: Organization size (e.g.,
```
50-999-employees
```
)
```
--service
```
/
```
-s
```
: Service filter (e.g.,
```
fasttrack
```
)
```
--includes
```
: Stories that include (e.g.,
```
videos,partners
```
)
```
--top
```
/
```
-t
```
: Number of results (default: 12)
```
--skip
```
: Pagination offset

Output is JSON with

totalCount

hasMorePages

, and

stories

array.

运行搜索脚本：

bash

{python} <skill_dir>/scripts/search_stories.py --products azure/azure-openai --region asia/japan --query "RAG" --top 10

参数说明：

```
--query
```
/
```
-q
```
：自由文本搜索

--products

-p

：产品过滤（例如：

azure/azure-openai

、

azure/azure-ai-search

）

```
--region
```
/
```
-r
```
：地区过滤（例如：
```
asia/japan
```
、
```
europe/germany
```
）
```
--industry
```
/
```
-i
```
：行业过滤（例如：
```
healthcare
```
、
```
manufacturing
```
）

--business-need

-b

：业务需求过滤（例如：

artificial-intelligence

）

```
--org-size
```
/
```
-o
```
：企业规模过滤（例如：
```
50-999-employees
```
）
```
--service
```
/
```
-s
```
：服务过滤（例如：
```
fasttrack
```
）
```
--includes
```
：包含特定内容的案例（例如：
```
videos,partners
```
）
```
--top
```
/
```
-t
```
：返回结果数量（默认：12）
```
--skip
```
：分页偏移量

输出为JSON格式，包含

totalCount

、

hasMorePages

和

stories

数组。

Step 3: Fetch Story Details

步骤3：获取案例详情

For interesting stories, fetch the full content:

bash

{python} <skill_dir>/scripts/fetch_story.py 25666-softbank-corp-azure-ai-foundry

Accepts a story slug or full URL. Returns JSON with

title

description

content

对于感兴趣的案例，获取完整内容：

bash

{python} <skill_dir>/scripts/fetch_story.py 25666-softbank-corp-azure-ai-foundry

接受案例slug或完整URL。返回JSON格式，包含

title

、

description

和

content

。

Output Format

输出格式

Always respond in the same language the user used. If the user asks in Japanese, reply in Japanese. If in English, reply in English.

Present results to the user in this format:

undefined

始终使用用户提问的语言进行回复。如果用户用日语提问，就用日语回复；如果用英语提问，就用英语回复。

请按照以下格式向用户展示结果：

undefined

Search Results: {totalCount} stories

搜索结果：{totalCount} 个案例

1. {title}

Industry: {industry}
URL: {url}
Summary: {summary from content}

行业：{industry}
链接：{url}
摘要：{content中的摘要}

2. {title}

...


When the user asks for details on a specific story, provide a more detailed summary of the story content including key challenges, solutions, and outcomes.

...


当用户要求获取特定案例的详情时，请提供更详细的案例内容摘要，包括关键挑战、解决方案和成果。