Skip to main content

为GitHub Copilot添加存储库自定义说明

创建存储库自定义说明文件,这些文件为 Copilot 提供有关如何理解项目以及如何生成、测试和验证其更改的其他上下文。

本文的此版本适用于在 GitHub 上使用存储库自定义说明。 单击上面的选项卡,获取有关在其他环境中使用自定义说明的信息。

介绍

通过存储库自定义说明,可以为 Copilot 提供特定于存储库的指导和首选项。 有关详细信息,请参阅“关于自定义GitHub Copilot 响应”。

仓库自定义指令的先决条件

  • 必须有自定义指令文件(请参阅以下指令)。

  • 对于 Copilot代码审查,你是否使用自定义指令的个人选择必须设置为启用。 此项已默认启用。 请参阅本文后面的启用或禁用存储库自定义说明

创建自定义指令

GitHub 上的 Copilot 支持三种类型的存储库自定义指令。 有关哪些 GitHub Copilot 功能支持这些类型的指令的详细信息,请参阅 关于自定义GitHub Copilot 响应

  •         **存储库级自定义指令**适用于在存储库上下文中发出的所有请求。
    

    这些是在仓库的 copilot-instructions.md 目录中的 .github 文件中指定的。 请参阅创建全仓库内的自定义指令

  •         **路径特定自定义指令**适用于在与指定路径匹配的文件上下文中发出的请求。
    

    在存储库中NAME.instructions.md目录中或其下的一个或多个.github/instructions文件中指定这些内容。 请参阅创建路径特定的自定义指令

    如果指定的路径与 Copilot 正在处理的文件匹配,并且全仓库内的自定义指令文件也存在,则使用这两个文件中的指令。

  •         **智能体指令**供 AI 智能体使用。
    

    你可以创建一个或多个 AGENTS.md 文件,存储在仓库内的任意位置。 当 Copilot 工作时,目录树中最近的 AGENTS.md 文件将优先于其他智能体指令文件。 有关详细信息,请参阅 openai/agents.md 仓库

    或者,可以使用仓库根目录中存储的单个 CLAUDE.mdGEMINI.md 文件。

创建全仓库内的自定义指令

你可以从头开始创建自己的自定义指令文件。 请参阅编写自己的 copilot-instructions.md 文件。 或者,你可以让 Copilot编程助理 帮你生成一个。

要求 Copilot编程助理 生成 copilot-instructions.md 文件

  1. 导航到 github.com/copilot/agents 的“代理”选项卡。

    您还可以通过单击 GitHub 页面上搜索栏旁的 按钮来访问此页面,然后从侧边栏中选择 Agents

  2. 使用提示字段中的下拉菜单,选择你希望 Copilot 为其生成自定义指令的存储库。

  3. 复制以下提示并将其粘贴到提示字段中,根据需要对其进行自定义:

    Markdown
    Your task is to "onboard" this repository to Copilot coding agent by adding a .github/copilot-instructions.md file in the repository that contains information describing how a coding agent seeing it for the first time can work most efficiently.
    
    You will do this task only one time per repository and doing a good job can SIGNIFICANTLY improve the quality of the agent's work, so take your time, think carefully, and search thoroughly before writing the instructions.
    
    <Goals>
    - Reduce the likelihood of a coding agent pull request getting rejected by the user due to
    generating code that fails the continuous integration build, fails a validation pipeline, or
    having misbehavior.
    - Minimize bash command and build failures.
    - Allow the agent to complete its task more quickly by minimizing the need for exploration using grep, find, str_replace_editor, and code search tools.
    </Goals>
    
    <Limitations>
    - Instructions must be no longer than 2 pages.
    - Instructions must not be task specific.
    </Limitations>
    
    <WhatToAdd>
    
    Add the following high level details about the codebase to reduce the amount of searching the agent has to do to understand the codebase each time:
    <HighLevelDetails>
    
    - A summary of what the repository does.
    - High level repository information, such as the size of the repo, the type of the project, the languages, frameworks, or target runtimes in use.
    </HighLevelDetails>
    
    Add information about how to build and validate changes so the agent does not need to search and find it each time.
    <BuildInstructions>
    
    - For each of bootstrap, build, test, run, lint, and any other scripted step, document the sequence of steps to take to run it successfully as well as the versions of any runtime or build tools used.
    - Each command should be validated by running it to ensure that it works correctly as well as any preconditions and postconditions.
    - Try cleaning the repo and environment and running commands in different orders and document errors and misbehavior observed as well as any steps used to mitigate the problem.
    - Run the tests and document the order of steps required to run the tests.
    - Make a change to the codebase. Document any unexpected build issues as well as the workarounds.
    - Document environment setup steps that seem optional but that you have validated are actually required.
    - Document the time required for commands that failed due to timing out.
    - When you find a sequence of commands that work for a particular purpose, document them in detail.
    - Use language to indicate when something should always be done. For example: "always run npm install before building".
    - Record any validation steps from documentation.
    </BuildInstructions>
    
    List key facts about the layout and architecture of the codebase to help the agent find where to make changes with minimal searching.
    <ProjectLayout>
    
    - A description of the major architectural elements of the project, including the relative paths to the main project files, the location
    of configuration files for linting, compilation, testing, and preferences.
    - A description of the checks run prior to check in, including any GitHub workflows, continuous integration builds, or other validation pipelines.
    - Document the steps so that the agent can replicate these itself.
    - Any explicit validation steps that the agent can consider to have further confidence in its changes.
    - Dependencies that aren't obvious from the layout or file structure.
    - Finally, fill in any remaining space with detailed lists of the following, in order of priority: the list of files in the repo root, the
    contents of the README, the contents of any key source files, the list of files in the next level down of directories, giving priority to the more structurally important and snippets of code from key source files, such as the one containing the main method.
    </ProjectLayout>
    </WhatToAdd>
    
    <StepsToFollow>
    - Perform a comprehensive inventory of the codebase. Search for and view:
    - README.md, CONTRIBUTING.md, and all other documentation files.
    - Search the codebase for build steps and indications of workarounds like 'HACK', 'TODO', etc.
    - All scripts, particularly those pertaining to build and repo or environment setup.
    - All build and actions pipelines.
    - All project files.
    - All configuration and linting files.
    - For each file:
    - think: are the contents or the existence of the file information that the coding agent will need to implement, build, test, validate, or demo a code change?
    - If yes:
       - Document the command or information in detail.
       - Explicitly indicate which commands work and which do not and the order in which commands should be run.
       - Document any errors encountered as well as the steps taken to workaround them.
    - Document any other steps or information that the agent can use to reduce time spent exploring or trying and failing to run bash commands.
    - Finally, explicitly instruct the agent to trust the instructions and only perform a search if the information in the instructions is incomplete or found to be in error.
    </StepsToFollow>
       - Document any errors encountered as well as the steps taken to work-around them.
    
    
  4. Click or press Enter.

Copilot will start a new session, which will appear in the list below the prompt box. Copilot will create a draft pull request, write your custom instructions, push them to the branch, then add you as a reviewer when it has finished, triggering a notification.

Writing your own copilot-instructions.md file

  1. In the root of your repository, create a file named .github/copilot-instructions.md.

    Create the .github directory if it does not already exist.

  2. Add natural language instructions to the file, in Markdown format.

    Whitespace between instructions is ignored, so the instructions can be written as a single paragraph, each on a new line, or separated by blank lines for legibility.

提示

The first time you create a pull request in a given repository with Copilot编程助理, Copilot will leave a comment with a link to automatically generate custom instructions for the repository.

Creating path-specific custom instructions

注意

Currently, on GitHub.com, path-specific custom instructions are only supported for Copilot编程助理 and Copilot代码审查.

  1. 如果尚无 .github/instructions 目录,则创建该目录。

  2. (可选)创建用于组织指令文件的子目录 .github/instructions

  3. 创建一个或多个 NAME.instructions.md 文件,其中 NAME 指示指令的用途。 文件名必须以 .instructions.md 结尾。

  4. 在文件开头,创建包含 applyTo 关键字的前辅文块。 使用 glob 语法指定指令应用于的文件或目录。

    例如:

    ---
    applyTo: "app/models/**/*.rb"
    ---
    

    可以通过用逗号分隔多个模式来指定这些模式。 例如,若要将指令应用于仓库中的所有 TypeScript 文件,可以使用以下前辅文块:

    ---
    applyTo: "**/*.ts,**/*.tsx"
    ---
    

    Glob 示例:

    •      `*` - 会匹配当前目录中的所有文件。
      
    •      `**` 或 `**/*` - 均会匹配所有目录中的所有文件。
      
    •      `*.py` - 将匹配当前目录中的所有 `.py` 文件。
      
    •      `**/*.py` - 将以递归方式匹配所有目录中的所有 `.py` 文件。
      
    •      `src/*.py` - 将匹配 `.py` 目录中所有 `src` 文件。 例如,`src/foo.py`和`src/bar.py`但_不_`src/foo/bar.py`。
      
    •      `src/**/*.py` - 将以递归方式匹配目录中的所有 `.py` 文件 `src` 。 例如 、 `src/foo.py``src/foo/bar.py`和 `src/foo/bar/baz.py`。
      
    •      `**/subdir/**/*.py` - 将以递归方式匹配任何深度目录中所有`.py`文件。 例如,`subdir/foo.py`、`subdir/nested/bar.py`、`parent/subdir/baz.py`和`deep/parent/subdir/nested/qux.py`_,但不_`foo.py`位于不包含`subdir`目录的路径。
      
  5. (可选)若要防止 Copilot编程助理 或 Copilot代码审查 使用该文件,请将 excludeAgent 关键字添加到 frontmatter 块。 使用 "code-review""coding-agent"

    例如,以下文件仅由 Copilot编程助理读取。

    ---
    applyTo: "**"
    excludeAgent: "code-review"
    ---
    
           `excludeAgent`如果在前言块中未包括关键字,则 Copilot代码审查 和 Copilot编程助理 都将使用您的说明。
    
  6. 使用 Markdown 格式以自然语言添加自定义指令。 系统会忽略说明信息间的空格,因此可将信息编写为一个段落,每个段落位于一行上,或用空白行分隔,以保持其可读性。

注释 %}

你是否已成功将自定义指令文件添加到你的仓库中?

          <a href="https://docs.github.io/success-test/yes.html" target="_blank" class="btn btn-outline mt-3 mr-3 no-underline">
          <span>是</span></a><a href="https://docs.github.io/success-test/no.html" target="_blank" class="btn btn-outline mt-3 mr-3 no-underline"><span>否</span></a>

尾注 %}

正在使用的自定义说明

文件(s)中的说明可供 Copilot 在保存文件后立即使用。 指令会自动添加到提交到 Copilot的请求。

In Copilot对话 (github.com/copilot), you can start a conversation that uses repository custom instructions by adding, as an attachment, the repository that contains the instructions file.

Whenever repository custom instructions are used by Copilot对话, the instructions file is added as a reference for the response that's generated. To find out whether repository custom instructions were used, expand the list of references at the top of a chat response in the Chat panel and check whether the .github/copilot-instructions.md file is listed.

Screenshot of an expanded References list, showing the 'copilot-instructions.md' file highlighted with a dark orange outline.

You can click the reference to open the file.

注意

  • 多种类型的自定义指令可以应用于发送到 Copilot的请求。 个人指令采用最高优先级。 接下来是存储库说明,然后组织说明将优先安排在最后。 但是,向 Copilot提供了所有相关指令集。
  • 尽可能避免提供冲突的指令集。 如果担心响应质量,可以暂时禁用存储库说明。 请参阅“为GitHub Copilot添加存储库自定义说明”。

Enabling or disabling custom instructions for Copilot代码审查

Custom instructions are enabled for Copilot代码审查 by default but you can disable, or re-enable, them in the repository settings on GitHub.com. This applies to Copilot's use of custom instructions for all code reviews it performs in this repository.

  1. 在 GitHub 上,导航到存储库的主页面。

  2. 在仓库名称下,单击 “Settings”****。 如果看不到“设置”选项卡,请选择“”下拉菜单,然后单击“设置”。

    存储库标头的屏幕截图,其中显示了选项卡。 “设置”选项卡以深橙色边框突出显示。

  3. In the "Code & automation" section of the sidebar, click Copilot, then Code review.

  4. Toggle the “Use custom instructions when reviewing pull requests” option on or off.

注意

评审拉取请求时,Copilot 使用拉取请求基础分支中的自定义指令。 例如,如果你的拉取请求旨在将 my-feature-branch 合并到 main,Copilot 将使用 main 中的自定义指令。

Further reading

This version of this article is for using repository custom instructions and prompt files in VS Code. Click the tabs above for instructions on using custom instructions in other environments.

介绍

通过存储库自定义说明,可以为 Copilot 提供特定于存储库的指导和首选项。 有关详细信息,请参阅“关于自定义GitHub Copilot 响应”。

仓库自定义指令的先决条件

Creating custom instructions

VS Code supports three types of repository custom instructions. For details of which GitHub Copilot features support these types of instructions, see 关于自定义GitHub Copilot 响应.

  • Repository-wide custom instructions, which apply to all requests made in the context of a repository.

    These are specified in a copilot-instructions.md file in the .github directory of the repository. See Creating repository-wide custom instructions.

  • Path-specific custom instructions, which apply to requests made in the context of files that match a specified path.

    These are specified in one or more NAME.instructions.md files within or below the .github/instructions directory in the repository. See Creating path-specific custom instructions.

    If the path you specify matches a file that Copilot is working on, and a repository-wide custom instructions file also exists, then the instructions from both files are used.

  • Agent instructions are used by AI agents.

    你可以创建一个或多个 AGENTS.md 文件,存储在仓库内的任意位置。 当 Copilot 正常工作时,目录树中最接近的 AGENTS.md 文件将优先。 有关详细信息,请参阅 openai/agents.md 仓库

    注意

    Support of AGENTS.md files outside of the workspace root is currently turned off by default. For details of how to enable this feature, see Use custom instructions in VS Code in the VS Code documentation.

Creating repository-wide custom instructions

  1. In the root of your repository, create a file named .github/copilot-instructions.md.

    Create the .github directory if it does not already exist.

  2. Add natural language instructions to the file, in Markdown format.

    Whitespace between instructions is ignored, so the instructions can be written as a single paragraph, each on a new line, or separated by blank lines for legibility.

Creating path-specific custom instructions

  1. 如果尚无 .github/instructions 目录,则创建该目录。

  2. (可选)创建用于组织指令文件的子目录 .github/instructions

  3. 创建一个或多个 NAME.instructions.md 文件,其中 NAME 指示指令的用途。 文件名必须以 .instructions.md 结尾。

  4. 在文件开头,创建包含 applyTo 关键字的前辅文块。 使用 glob 语法指定指令应用于的文件或目录。

    例如:

    ---
    applyTo: "app/models/**/*.rb"
    ---
    

    可以通过用逗号分隔多个模式来指定这些模式。 例如,若要将指令应用于仓库中的所有 TypeScript 文件,可以使用以下前辅文块:

    ---
    applyTo: "**/*.ts,**/*.tsx"
    ---
    

    Glob 示例:

    •      `*` - 会匹配当前目录中的所有文件。
      
    •      `**` 或 `**/*` - 均会匹配所有目录中的所有文件。
      
    •      `*.py` - 将匹配当前目录中的所有 `.py` 文件。
      
    •      `**/*.py` - 将以递归方式匹配所有目录中的所有 `.py` 文件。
      
    •      `src/*.py` - 将匹配 `.py` 目录中所有 `src` 文件。 例如,`src/foo.py`和`src/bar.py`但_不_`src/foo/bar.py`。
      
    •      `src/**/*.py` - 将以递归方式匹配目录中的所有 `.py` 文件 `src` 。 例如 、 `src/foo.py``src/foo/bar.py`和 `src/foo/bar/baz.py`。
      
    •      `**/subdir/**/*.py` - 将以递归方式匹配任何深度目录中所有`.py`文件。 例如,`subdir/foo.py`、`subdir/nested/bar.py`、`parent/subdir/baz.py`和`deep/parent/subdir/nested/qux.py`_,但不_`foo.py`位于不包含`subdir`目录的路径。
      
  5. (可选)若要防止 Copilot编程助理 或 Copilot代码审查 使用该文件,请将 excludeAgent 关键字添加到 frontmatter 块。 使用 "code-review""coding-agent"

    例如,以下文件仅由 Copilot编程助理读取。

    ---
    applyTo: "**"
    excludeAgent: "code-review"
    ---
    
           `excludeAgent`如果在前言块中未包括关键字,则 Copilot代码审查 和 Copilot编程助理 都将使用您的说明。
    
  6. 使用 Markdown 格式以自然语言添加自定义指令。 系统会忽略说明信息间的空格,因此可将信息编写为一个段落,每个段落位于一行上,或用空白行分隔,以保持其可读性。

注释 %}

你是否已成功将自定义指令文件添加到你的仓库中?

          <a href="https://docs.github.io/success-test/yes.html" target="_blank" class="btn btn-outline mt-3 mr-3 no-underline">
          <span>是</span></a><a href="https://docs.github.io/success-test/no.html" target="_blank" class="btn btn-outline mt-3 mr-3 no-underline"><span>否</span></a>

尾注 %}

正在使用的自定义说明

文件(s)中的说明可供 Copilot 在保存文件后立即使用。 指令会自动添加到提交到 Copilot的请求。

自定义说明在“聊天”视图或内联聊天中不可见,但可以通过查看“聊天”视图中的回复引用列表来验证 Copilot 是否正在使用这些说明。 如果将自定义说明添加到发送到模型的提示中,引用信息中会列出文件 .github/copilot-instructions.md。 可以单击引用信息来打开该文件。

Screenshot of an expanded References list, showing the 'copilot-instructions.md' file highlighted with a dark orange outline.

启用或禁用存储库自定义说明

可以选择是否要让 Copilot 使用基于仓库的自定义指令。

为 Copilot对话 启用或禁用自定义指令

默认情况下,Copilot对话 已启用自定义指令,但你可以随时禁用或重新启用它们。 这适用于你自己的 Copilot对话 使用,不会影响其他用户。

  1. Open the Setting editor by using the keyboard shortcut Command+, (Mac) / Ctrl+, (Linux/Windows).
  2. Type instruction file in the search box.
  3. Select or clear the checkbox under Code Generation: Use Instruction Files.

为 Copilot代码审查 启用或禁用自定义指令

默认情况下,Copilot代码审查 已启用自定义指令,但你可以在 GitHub.com 上的仓库设置中禁用或重新启用它们。 这适用于 Copilot 对此仓库中执行的所有代码评审使用自定义指令。

  1. 在 GitHub 上,导航到存储库的主页面。

  2. 在仓库名称下,单击 “Settings”****。 如果看不到“设置”选项卡,请选择“”下拉菜单,然后单击“设置”。

    存储库标头的屏幕截图,其中显示了选项卡。 “设置”选项卡以深橙色边框突出显示。

  3. 在边栏的“Code & automation”部分,单击 Copilot,然后单击“Code review”********。

  4. 打开或关闭“Use custom instructions when reviewing pull requests”选项。

Enabling and using prompt files

注意

Prompt files let you build and share reusable prompt instructions with additional context. A prompt file is a Markdown file, stored in your workspace, that mimics the existing format of writing prompts in Copilot对话 (for example, Rewrite #file:x.ts). You can have multiple prompt files in your workspace, each of which defines a prompt for a different purpose.

Enabling prompt files

To enable prompt files, configure the workspace settings.

  1. Open the command palette by pressing Ctrl+Shift+P (Windows/Linux) / Command+Shift+P (Mac).
  2. Type "Open Workspace Settings (JSON)" and select the option that's displayed.
  3. In the settings.json file, add "chat.promptFiles": true to enable the .github/prompts folder as the location for prompt files. This folder will be created if it does not already exist.

Creating prompt files

  1. Open the command palette by pressing Ctrl+Shift+P (Windows/Linux) / Command+Shift+P (Mac).

  2. Type "prompt" and select Chat: Create Prompt.

  3. Enter a name for the prompt file, excluding the .prompt.md file name extension. The name can contain alphanumeric characters and spaces and should describe the purpose of the prompt information the file will contain.

  4. Write the prompt instructions, using Markdown formatting.

    You can reference other files in the workspace by using Markdown links—for example, [index](../../web/index.ts)—or by using the #file:../../web/index.ts syntax. Paths are relative to the prompt file. Referencing other files allows you to provide additional context, such as API specifications or product documentation.

Using prompt files

  1. At the bottom of the Copilot对话 view, click the Attach context icon ().

  2. In the dropdown menu, click Prompt... and choose the prompt file you want to use.

  3. Optionally, attach additional files, including prompt files, to provide more context.

  4. Optionally, type additional information in the chat prompt box.

    Whether you need to do this or not depends on the contents of the prompt you are using.

  5. Submit the chat prompt.

For more information about prompt files, see Use prompt files in Visual Studio Code in the Visual Studio Code documentation.

Further reading

This version of this article is for using repository custom instructions and prompt files in Visual Studio. Click the tabs above for instructions on using custom instructions in other environments.

介绍

通过存储库自定义说明,可以为 Copilot 提供特定于存储库的指导和首选项。 有关详细信息,请参阅“关于自定义GitHub Copilot 响应”。

仓库自定义指令的先决条件

Creating custom instructions

Visual Studio supports two types of custom instructions. For details of which GitHub Copilot features support these types of instructions, see 关于自定义GitHub Copilot 响应.

  • Repository-wide custom instructions, which apply to all requests made in the context of a repository.

    These are specified in a copilot-instructions.md file in the .github directory of the repository. See Creating repository-wide custom instructions.

  • Path-specific custom instructions, which apply to requests made in the context of files that match a specified path.

    These are specified in one or more NAME.instructions.md files within or below the .github/instructions directory in the repository. See Creating path-specific custom instructions.

    If the path you specify matches a file that Copilot is working on, and a repository-wide custom instructions file also exists, then the instructions from both files are used.

Creating repository-wide custom instructions

  1. In the root of your repository, create a file named .github/copilot-instructions.md.

    Create the .github directory if it does not already exist.

  2. Add natural language instructions to the file, in Markdown format.

    Whitespace between instructions is ignored, so the instructions can be written as a single paragraph, each on a new line, or separated by blank lines for legibility.

Creating path-specific custom instructions

  1. 如果尚无 .github/instructions 目录,则创建该目录。

  2. (可选)创建用于组织指令文件的子目录 .github/instructions

  3. 创建一个或多个 NAME.instructions.md 文件,其中 NAME 指示指令的用途。 文件名必须以 .instructions.md 结尾。

  4. 在文件开头,创建包含 applyTo 关键字的前辅文块。 使用 glob 语法指定指令应用于的文件或目录。

    例如:

    ---
    applyTo: "app/models/**/*.rb"
    ---
    

    可以通过用逗号分隔多个模式来指定这些模式。 例如,若要将指令应用于仓库中的所有 TypeScript 文件,可以使用以下前辅文块:

    ---
    applyTo: "**/*.ts,**/*.tsx"
    ---
    

    Glob 示例:

    •      `*` - 会匹配当前目录中的所有文件。
      
    •      `**` 或 `**/*` - 均会匹配所有目录中的所有文件。
      
    •      `*.py` - 将匹配当前目录中的所有 `.py` 文件。
      
    •      `**/*.py` - 将以递归方式匹配所有目录中的所有 `.py` 文件。
      
    •      `src/*.py` - 将匹配 `.py` 目录中所有 `src` 文件。 例如,`src/foo.py`和`src/bar.py`但_不_`src/foo/bar.py`。
      
    •      `src/**/*.py` - 将以递归方式匹配目录中的所有 `.py` 文件 `src` 。 例如 、 `src/foo.py``src/foo/bar.py`和 `src/foo/bar/baz.py`。
      
    •      `**/subdir/**/*.py` - 将以递归方式匹配任何深度目录中所有`.py`文件。 例如,`subdir/foo.py`、`subdir/nested/bar.py`、`parent/subdir/baz.py`和`deep/parent/subdir/nested/qux.py`_,但不_`foo.py`位于不包含`subdir`目录的路径。
      
  5. (可选)若要防止 Copilot编程助理 或 Copilot代码审查 使用该文件,请将 excludeAgent 关键字添加到 frontmatter 块。 使用 "code-review""coding-agent"

    例如,以下文件仅由 Copilot编程助理读取。

    ---
    applyTo: "**"
    excludeAgent: "code-review"
    ---
    
           `excludeAgent`如果在前言块中未包括关键字,则 Copilot代码审查 和 Copilot编程助理 都将使用您的说明。
    
  6. 使用 Markdown 格式以自然语言添加自定义指令。 系统会忽略说明信息间的空格,因此可将信息编写为一个段落,每个段落位于一行上,或用空白行分隔,以保持其可读性。

注释 %}

你是否已成功将自定义指令文件添加到你的仓库中?

          <a href="https://docs.github.io/success-test/yes.html" target="_blank" class="btn btn-outline mt-3 mr-3 no-underline">
          <span>是</span></a><a href="https://docs.github.io/success-test/no.html" target="_blank" class="btn btn-outline mt-3 mr-3 no-underline"><span>否</span></a>

尾注 %}

正在使用的自定义说明

文件(s)中的说明可供 Copilot 在保存文件后立即使用。 指令会自动添加到提交到 Copilot的请求。

自定义说明在“聊天”视图或内联聊天中不可见,但可以通过查看“聊天”视图中的回复引用列表来验证 Copilot 是否正在使用这些说明。 如果将自定义说明添加到发送到模型的提示中,引用信息中会列出文件 .github/copilot-instructions.md。 可以单击引用信息来打开该文件。

Screenshot of the References popup, showing the 'copilot-instructions.md' file highlighted with a dark orange outline.

启用或禁用存储库自定义说明

可以选择是否要让 Copilot 使用基于仓库的自定义指令。

为 Copilot对话 启用或禁用自定义指令

默认情况下,Copilot对话 已启用自定义指令,但你可以随时禁用或重新启用它们。 这适用于你自己的 Copilot对话 使用,不会影响其他用户。

  1. In the Visual Studio menu bar, under Tools, click Options.

    Screenshot of the Visual Studio menu bar. The "Tools" menu is expanded, and the "Options" item is highlighted with an orange outline.

  2. In the "Options" dialog, type custom instructions in the search box, then click Copilot.

  3. Select or clear the checkbox for Enable custom instructions to be loaded from .github/copilot-instructions.md files and added to requests.

    Screenshot of the Visual Studio Options dialog showing the "Enable custom instructions" option checkbox selected.

为 Copilot代码审查 启用或禁用自定义指令

默认情况下,Copilot代码审查 已启用自定义指令,但你可以在 GitHub.com 上的仓库设置中禁用或重新启用它们。 这适用于 Copilot 对此仓库中执行的所有代码评审使用自定义指令。

  1. 在 GitHub 上,导航到存储库的主页面。

  2. 在仓库名称下,单击 “Settings”****。 如果看不到“设置”选项卡,请选择“”下拉菜单,然后单击“设置”。

    存储库标头的屏幕截图,其中显示了选项卡。 “设置”选项卡以深橙色边框突出显示。

  3. 在边栏的“Code & automation”部分,单击 Copilot,然后单击“Code review”********。

  4. 打开或关闭“Use custom instructions when reviewing pull requests”选项。

Using prompt files

注意

Prompt files let you build and share reusable prompt instructions with additional context. A prompt file is a Markdown file, stored in your workspace, that mimics the existing format of writing prompts in Copilot对话 (for example, Rewrite #file:x.ts). You can have multiple prompt files in your workspace, each of which defines a prompt for a different purpose.

Creating prompt files

  1. Add a prompt file, including the .prompt.md file name extension inside the .github/prompts folder in the root of the repository. The name can contain alphanumeric characters and spaces and should describe the purpose of the prompt information the file will contain.

  2. Write the prompt instructions, using Markdown formatting.

    You can reference other files in the workspace by using Markdown links—for example, [index](../../web/index.ts)—or by using the #file:'../../web/index.ts' syntax. Paths are relative to the prompt file. Referencing other files allows you to provide additional context, such as API specifications or product documentation.

For more information about prompt files, see Use prompt files in Visual Studio in the Visual Studio documentation.

Further reading

This version of this article is for using repository custom instructions in JetBrains IDEs. Click the tabs above for instructions on using custom instructions in other environments.

介绍

通过存储库自定义说明,可以为 Copilot 提供特定于存储库的指导和首选项。 有关详细信息,请参阅“关于自定义GitHub Copilot 响应”。

仓库自定义指令的先决条件

  • 必须有自定义指令文件(请参阅以下指令)。

  • The latest version of the Copilot extension must be installed in your JetBrains IDE.

Creating custom instructions

JetBrains IDEs support a single .github/copilot-instructions.md custom instructions file stored in the repository, and a locally stored global-copilot-instructions.md file.

You can create the .github/copilot-instructions.md file in your repository using the Copilot settings page, or you can create the file manually.

Whitespace between instructions is ignored, so the instructions can be written as a single paragraph, each on a new line, or separated by blank lines for legibility.

Using the settings page

  1. 在 JetBrains IDE 中,单击“文件”**** 菜单 (Windows) 或菜单栏中的应用程序名称 (macOS),然后单击“设置”****。
  2. 工具下,单击 GitHub Copilot,然后单击自定义
  3. Under "Copilot Instructions", click Workspace or Global to choose whether the custom instructions apply to the current workspace or all workspaces.

Manually creating a workspace custom instructions file

  1. In the root of your repository, create a file named .github/copilot-instructions.md.

    Create the .github directory if it does not already exist.

  2. Add natural language instructions to the file, in Markdown format.

Once saved, these instructions will apply to the current workspace in JetBrains IDEs that you open with Copilot enabled.

Manually creating a global custom instructions file

To apply the same instructions across all workspaces in JetBrains IDEs, you can create a global custom instructions file on your local machine.

  1. Open your file explorer or terminal.

  2. Navigate to the appropriate location for your operating system:

    • macOS: /Users/YOUR-USERNAME/.config/github-copilot/intellij/
    • Windows: C:\Users\YOUR-USERNAME\AppData\Local\github-copilot\intellij\
  3. Create a file named global-copilot-instructions.md in that directory.

  4. Add your custom instructions in natural language, using Markdown format.

Once saved, these instructions will apply globally across all workspaces in JetBrains IDEs that you open with Copilot enabled.

注释 %}

你是否已成功将自定义指令文件添加到你的仓库中?

          <a href="https://docs.github.io/success-test/yes.html" target="_blank" class="btn btn-outline mt-3 mr-3 no-underline">
          <span>是</span></a><a href="https://docs.github.io/success-test/no.html" target="_blank" class="btn btn-outline mt-3 mr-3 no-underline"><span>否</span></a>

尾注 %}

正在使用的自定义说明

文件(s)中的说明可供 Copilot 在保存文件后立即使用。 指令会自动添加到提交到 Copilot的请求。

自定义说明在“聊天”视图或内联聊天中不可见,但可以通过查看“聊天”视图中的回复引用列表来验证 Copilot 是否正在使用这些说明。 如果将自定义说明添加到发送到模型的提示中,引用信息中会列出文件 .github/copilot-instructions.md。 可以单击引用信息来打开该文件。

Using prompt files

注意

Prompt files let you build and share reusable prompt instructions with additional context. A prompt file is a Markdown file, stored in your workspace, that mimics the existing format of writing prompts in Copilot对话 (for example, Rewrite #file:x.ts). You can have multiple prompt files in your workspace, each of which defines a prompt for a different purpose.

When writing prompt instructions, you can reference other files in the workspace by using Markdown links—for example, [index](../../web/index.ts)—or by using the #file:../../web/index.ts syntax. Paths are relative to the prompt file. Referencing other files allows you to provide additional context, such as API specifications or product documentation.

Once prompt files are saved, their instructions will apply to the current workspace in JetBrains IDEs that you open with Copilot enabled.

Creating prompt files using the command line

  1. Create the .github/prompts directory if it doesn't already exist in your workspace. This directory will be the location for your prompt files.
  2. Create a prompt file in the .github/prompts directory. The prompt file name can contain alphanumeric characters and spaces and should describe the purpose of the prompt information the file will contain. The file name must end with the .prompt.md file name extension, for example TESTPROMPT.prompt.md.
  3. Write the prompt instructions using Markdown formatting, and save the file.

Creating prompt files using the settings page

  1. 在 JetBrains IDE 中,单击“文件”**** 菜单 (Windows) 或菜单栏中的应用程序名称 (macOS),然后单击“设置”****。
  2. Under Tools, under GitHub Copilot, click Edit Settings.
  3. Under "Settings Categories", click Customizations.
  4. Under "Prompt Files", click Workspace, to create a prompt file in your workspace.
  5. Enter a name for the prompt file, excluding the .prompt.md file name extension. The prompt file name can contain alphanumeric characters and spaces and should describe the purpose of the prompt information the file will contain.
  6. Click Ok to save the prompt file name.
  7. Write the prompt instructions using Markdown formatting, and save the file.

Using prompt files

  1. In the chat input box, type / followed by the name of the prompt file. For example, /TESTPROMPT.

  2. Optionally, attach additional files, to provide more context.

  3. Optionally, type additional information in the chat prompt box.

    Whether you need to do this or not depends on the contents of the prompt you are using.

  4. Submit the chat prompt.

Further reading

This version of this article is for using repository custom instructions in Xcode. Click the tabs above for instructions on using custom instructions in other environments.

介绍

通过存储库自定义说明,可以为 Copilot 提供特定于存储库的指导和首选项。 有关详细信息,请参阅“关于自定义GitHub Copilot 响应”。

仓库自定义指令的先决条件

  • 必须有自定义指令文件(请参阅以下指令)。

  • The latest version of the Copilot extension must be installed in Xcode.

Creating custom instructions

Xcode supports a single .github/copilot-instructions.md custom instructions file stored in the repository.

You can create a custom instructions file in your repository via the Copilot settings page.

Whitespace between instructions is ignored, so the instructions can be written as a single paragraph, each on a new line, or separated by blank lines for legibility.

  1. Open the GitHub Copilot for Xcode application.
  2. At the top of the application window, under Settings, click Advanced.
  3. To the right of "Custom Instructions", click Current Workspace or Global to choose whether the custom instructions apply to the current workspace or all workspaces.

注释 %}

你是否已成功将自定义指令文件添加到你的仓库中?

          <a href="https://docs.github.io/success-test/yes.html" target="_blank" class="btn btn-outline mt-3 mr-3 no-underline">
          <span>是</span></a><a href="https://docs.github.io/success-test/no.html" target="_blank" class="btn btn-outline mt-3 mr-3 no-underline"><span>否</span></a>

尾注 %}

正在使用的自定义说明

文件(s)中的说明可供 Copilot 在保存文件后立即使用。 指令会自动添加到提交到 Copilot的请求。

自定义说明在“聊天”视图或内联聊天中不可见,但可以通过查看“聊天”视图中的回复引用列表来验证 Copilot 是否正在使用这些说明。 如果将自定义说明添加到发送到模型的提示中,引用信息中会列出文件 .github/copilot-instructions.md。 可以单击引用信息来打开该文件。

Further reading

注意

This feature is currently in 公共预览版 and is subject to change.

This version of this article is for using repository custom instructions in Eclipse. Click the tabs above for instructions on using custom instructions in other environments.

介绍

通过存储库自定义说明,可以为 Copilot 提供特定于存储库的指导和首选项。 有关详细信息,请参阅“关于自定义GitHub Copilot 响应”。

仓库自定义指令的先决条件

  • 必须有自定义指令文件(请参阅以下指令)。

  • The latest version of the Copilot extension must be installed in Eclipse.

Creating custom instructions

Eclipse supports two types of repository custom instructions: workspace and project custom instructions.

To create a workspace custom instructions file, you can use the Copilot settings page. To create a project custom instructions file, you can create the file manually in the project directory.

Whitespace between instructions is ignored, so the instructions can be written as a single paragraph, each on a new line, or separated by blank lines for legibility.

Creating a workspace custom instructions file

  1. To open the Copilot对话 panel, click the Copilot icon () in the status bar at the bottom of Eclipse.
  2. From the menu, select "Edit preferences".
  3. In the left pane, expand GitHub Copilot and click Custom Instructions.
  4. Select Enable workspace instructions.
  5. In the "Workspace" section, under "Set custom instructions to guide Copilot's code suggestions in this workspace", add natural language instructions to the file, in Markdown format.

Creating a project custom instructions file

  1. In the root of your project directory, create a file named .github/copilot-instructions.md.
  2. Add your custom instructions in natural language, using Markdown format.

Once saved, these instructions will apply to the current project in Eclipse that you open with Copilot enabled.

注释 %}

你是否已成功将自定义指令文件添加到你的仓库中?

          <a href="https://docs.github.io/success-test/yes.html" target="_blank" class="btn btn-outline mt-3 mr-3 no-underline">
          <span>是</span></a><a href="https://docs.github.io/success-test/no.html" target="_blank" class="btn btn-outline mt-3 mr-3 no-underline"><span>否</span></a>

尾注 %}

正在使用的自定义说明

文件(s)中的说明可供 Copilot 在保存文件后立即使用。 指令会自动添加到提交到 Copilot的请求。

Further reading