用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt;运行前请先检查来源。
npx skills add https://github.com/Azure/azure-sdk-for-net --skill generate-code-cs命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地?可下载 SkillsMP 当前能够提供的文件。
正在显示 SKILL.md
Analyze Azure SDK CI/CD pipeline failures into a structured diagnosis, and define the required output format. Load this skill before calling azsdk_analyze_pipeline, which returns raw failure data that this skill interprets and formats. USE FOR: "pipeline failed", "build failure", "CI check failing", "tests failing in CI", "analyze pipeline", "debug SDK pipeline". DO NOT USE FOR: local build issues without pipeline context, API design review, SDK publishing, applying code fixes (instead use azsdk-common-pipeline-fixer). INVOKES: azure-sdk-mcp:azsdk_analyze_pipeline, azure-sdk-mcp:azsdk_get_pipeline_llm_artifacts, azure-sdk-mcp:azsdk_get_failed_test_run_data, azure-sdk-mcp:azsdk_get_failed_test_case_data, azure-sdk-mcp:azsdk_get_pr_checks, azure-sdk-mcp:azsdk_get_pipeline_status.
Review Azure SDK management-plane pull requests, check naming conventions, API compatibility, and code quality.
Headless, bounded repair of custom-code build failures in an already-generated Azure SDK PR. Thin wrapper over the shared azure-sdk-mcp:azsdk_customized_code_update engine in custom-code-only scope (editScope: CustomCode); the skill owns the iterate-until-green loop, capped by a per-language `maxIterations` read from repair-config.yml. WHEN: Copilot cloud agent runs on a release-planner Auto SDK PR labeled `auto-sdk-build-fix` that fails to build because of custom (non-generated) code. DO NOT USE FOR: full TypeSpec migrations, spec edits, API design review, manual fixing. INVOKES: azure-sdk-mcp:azsdk_customized_code_update.
基于 SOC 职业分类
| name | generate-code-cs |
| description | Generate the code from typespec for C#. Parameter: C# SDK repository root location <cs_root>. |
The C# repository root location is provided by <cs_root>. C# source codes of interest are located in <cs_root>/sdk/ai/Azure.AI.Projects, <cs_root>/sdk/ai/Azure.AI.Projects.Agents and <cs_root>/sdk/ai/Azure.AI.Extensions.OpenAI. Each folder contains subfolder src, which contains all the source codes. The src/Generated folder contains generated code; the folder Custom contains the code customizations. Please review the references/customization.md for more information on code customization. The typespec repository, used for code generation is located at https://github.com/Azure/azure-rest-api-specs.git. Please use the branch provided by user, if it is not provided use feature/foundry-release.
commit field in three files: <cs_root>/sdk/ai/Azure.AI.Projects.Agents/tsp-location.yaml, <cs_root>/sdk/ai/Azure.AI.Projects/tsp-location.yaml and <cs_root>/sdk/ai/Azure.AI.Extensions.OpenAI/tsp-location.yaml.cd <cs_root>/sdk/ai/Azure.AI.Projects.Agents
dotnet build /t:GenerateCode
cd <cs_root>/sdk/ai/Azure.AI.Projects.Agents
dotnet build /t:GenerateCode
If the EPERM error has happened, run the next code and make sure it passes:
cd ../Azure.AI.Extensions.OpenAI
npm exec --prefix <cs_root>\eng\common/tsp-client --no -- tsp-client update --no-prompt --output-dir<cs_root>\sdk\ai\Azure.AI.Projects.Agents\src/../
cd ../Azure.AI.Extensions.OpenAI
npm exec --prefix <cs_root>\eng\common/tsp-client --no -- tsp-client update --no-prompt --output-dir<cs_root>\sdk\ai\Azure.AI.Projects.Agents\src/../
cd ../Azure.AI.Extensions.OpenAI
npm exec --prefix <cs_root>\eng\common/tsp-client --no -- tsp-client update --no-prompt --output-dir<cs_root>\sdk\ai\Azure.AI.Extensions.OpenAI\src/../
cd ../Azure.AI.Projects
npm exec --prefix <cs_root>\eng\common/tsp-client --no -- tsp-client update --no-prompt --output-dir<cs_root>\sdk\ai\Azure.AI.Projects\src/../
cd <cs_root>/sdk/ai/Azure.AI.Projects.Agents
dotnet build /t:GenerateCode
cd ../Azure.AI.Extensions.OpenAI
npm exec --prefix <cs_root>\eng\common/tsp-client --no -- tsp-client update --no-prompt --output-dir<cs_root>\sdk\ai\Azure.AI.Extensions.OpenAI\src/../
cd ../Azure.AI.Projects
npm exec --prefix <cs_root>\eng\common/tsp-client --no -- tsp-client update --no-prompt --output-dir<cs_root>\sdk\ai\Azure.AI.Projects\src/../
Azure.AI.Projects, Azure.AI.Extensions.OpenAI or Azure.AI.Projects.Agents):cd <cs_root>/sdk/ai/<package>
dotnet build /t:GenerateCode
cd <cs_root>/sdk/ai/<package>
dotnet build /t:GenerateCode
Azure.AI.Projects.Agents package after code generation may get new tool classes, inherited from Tool. The same classes will be generated in Azure.AI.Extensions.OpenAI projects. If that is the case, add into the file <cs_root>/sdk/ai/Azure.AI.Extensions.OpenAI/src/Custom.CodeGenStubs.Tools.cs entries to rename the generated tool classes and their parameters so that they have Responses prefix. For example, if the class FabricIQPreviewTool was added, add the next entries:[CodeGenType("FabricIQPreviewTool")] public partial class ResponsesFabricIQPreviewTool { }
[CodeGenType("FabricIQPreviewToolParameters")] public partial class ResponsesFabricIQPreviewToolParameters { }
Order the entries in the file alphabetically; do not remove the entries already present.
4. Make sure that all projects build without errors by running dotnet build inside the project folder.
5. Update the API-view by running the script (replace by Azure.AI.Projects, Azure.AI.Extensions.OpenAI or Azure.AI.Projects.Agents):
cd <cs_root>
eng\scripts\Export-API.ps1 ai\<package>
cd <cs_root>
eng\scripts\Export-API.ps1 ai\<package>
A C# sample consists of two parts: the source code in the folder <cs_root>/sdk/ai/<package_name>/tests/Samples and corresponding .md files go to <cs_root>/sdk/ai/<package_name>/Samples. The C# file should demonstrate both sync and async API when appropriate. See the example below:
#if SNIPPET
var projectEndpoint = System.Environment.GetEnvironmentVariable("FOUNDRY_PROJECT_ENDPOINT");
var modelDeploymentName = System.Environment.GetEnvironmentVariable("FOUNDRY_MODEL_NAME");
#else
var projectEndpoint = TestEnvironment.FOUNDRY_PROJECT_ENDPOINT;
var modelDeploymentName = TestEnvironment.FOUNDRY_MODEL_NAME;
#endif
AIProjectClient projectClient = new(endpoint: new Uri(projectEndpoint), tokenProvider: new DefaultAzureCredential());
DeclarativeAgentDefinition agentDefinition = new(model: modelDeploymentName)
{
Instructions = "You are a prompt agent."
};
ProjectsAgentVersion agentVersion1 = await projectClient.AgentAdministrationClient.CreateAgentVersionAsync(
agentName: "myAgent1",
options: new(agentDefinition));
#if SNIPPET
var projectEndpoint = System.Environment.GetEnvironmentVariable("FOUNDRY_PROJECT_ENDPOINT");
var modelDeploymentName = System.Environment.GetEnvironmentVariable("FOUNDRY_MODEL_NAME");
#else
var projectEndpoint = TestEnvironment.FOUNDRY_PROJECT_ENDPOINT;
var modelDeploymentName = TestEnvironment.FOUNDRY_MODEL_NAME;
#endif
AIProjectClient projectClient = new(endpoint: new Uri(projectEndpoint), tokenProvider: new DefaultAzureCredential());
DeclarativeAgentDefinition agentDefinition = new(model: modelDeploymentName)
{
Instructions = "You are a prompt agent."
};
ProjectsAgentVersion agentVersion1 = projectClient.AgentAdministrationClient.CreateAgentVersion(
agentName: "myAgent1",
options: new(agentDefinition));
The code needs to be logically split into blocks, whose usage should be explained in .md file. Each block is marked in the source code as follows:
#region Snippet:Sample_FunctionFoo_MySampl_Async
public async Task Foo()
{
await Task.Delay(1000);
Console.WriteLine("Hello world!")
}
#endregion
These blocks will be rendered in the .md file code block based on the region name (it will be done by automation):
public async Task Foo()
{
await Task.Delay(1000);
Console.WriteLine("Hello world!")
}
If the code block has sync and async counterpart, please create code block for each of them. Provide the short explanation for each code block. Please make sure that there is one-to-one consistency between C# regions and .md file code blocks.
To make sure that it is so, call the script (replace by Azure.AI.Projects, Azure.AI.Extensions.OpenAI or Azure.AI.Projects.Agents):
cd <cs_root>
eng\scripts\Update-Snippets.ps1 ai\<package>
cd <cs_root>
eng\scripts\Update-Snippets.ps1 ai\<package>
Get the differences by running
cd <cs_root>
git diff
cd <cs_root>
git diff
Figure out, which classes are public facing and based on that populate the latest section of Release History. Append the found changes to the ### Features Added, ### Breaking Changes, ### Bugs Fixed or ### Other Changes section. It is also possible to add ### Sample Updates section or append data to it. Do not modify the header, denoting version and release date, for example ## 2.1.0-beta.2 (Unreleased).
Prompt user if the PR is required. If it is not, go to the section "Package generation".
Get the user's github alias by running gh api user --jq .login.
Stash the changes and make sure to use the latest main branch.
git stash
git checkout main
git pull origin main
git stash
git checkout main
git pull origin main
Create a branch and apply stashed changes; replace <user_alias> by user github alias from step 2. Replace <commit> by the commit hash from the typespec.
git checkout -b <user_alias>/code_generation_<commit>
git stash apply
git checkout -b <user_alias>/code_generation_<commit>
git stash apply
Add all new files by running git add and modified files by git add -u.
Commit changes with the short summary of added features as a comment git commit -m "new features"
Create a pull request by calling gh pr create --title "<title>" --body "<changelog> --assignee @me"; replace <title> and <changelog> by short PR title and the changes from the changelog, we have generated in "Updating changelog" section.
az az pipelines show --id 7296 --organization https://dev.azure.com/azure-sdk/ --project internal).curl https://dev.azure.com/azure-sdk/internal/_artifacts/feed/azure-sdk-for-net-pr)az pipelines run --id 7296 --organization https://dev.azure.com/azure-sdk/ --project internal --branch nirovins/fix_pipelines --variables "SetDevVersion=true" --open; replace the <branch> by the branch from "Create a pull request" section.After everything is ready, please generate the packages for all <package> i.e. (replace <package> by Azure.AI.Projects, Azure.AI.Extensions.OpenAI or Azure.AI.Projects.Agents).
cd <cs_root>/sdk/ai/<package>
dotnet pack
cd <cs_root>/sdk/ai/<package>
dotnet pack
Provide the location of each package in the summary and provide the simple instruction on installation.
If the alpha package was released to Azure (in section "Create an alpha package release"), please add to the instructions command to add a new NuGet repository to the project. dotnet nuget add source https://pkgs.dev.azure.com/azure-sdk/public/_packaging/azure-sdk-for-net/nuget/v3/index.json