commit

作者: microsoft

使用AI生成的提交信息提交暂存或未暂存的更改,该信息需匹配仓库现有的提交风格。当用户要求“提交”时使用…

npx skills add https://github.com/microsoft/vscode --skill commit

Commit Changes

Help the user commit code changes with a well-crafted commit message derived from the diff, following the conventions already established in the repository.

Guidelines

  • Never amend existing commits without asking.
  • Never force-push or push without explicit user approval.
  • Never skip pre-commit hooks (do not use --no-verify).
  • Never skip signing commits (do not use --no-gpg-sign).
  • Never revert, reset, or discard user changes unless the user explicitly asked for that.
  • Check for obvious secrets or generated artifacts that should not be committed. If something looks risky - ask the user.
  • When in doubt about staging, convention, or message content — ask the user.

Workflow

1. Discover the repository's commit convention

Run the following to sample recent commits and the user's own commits:

# Recent repo commits (for overall style)
git log --oneline -20

# User's recent commits (for personal style)
git log --oneline --author="$(git config user.name)" -10

Analyse the output to determine the commit message convention used in the repository (e.g. Conventional Commits, Gitmoji, ticket-prefixed, free-form). All generated messages must follow the detected convention.

2. Check repository status

git status --short
  • If there are no changes (working tree clean, nothing staged), inform the user and stop.
  • If there are staged changes, proceed with those and do not stage any unstaged changes.
  • If there are only unstaged changes, stage everything (git add -A), and proceed with those.

3. Generate the commit message

Obtain the full diff of what will be committed:

git diff --cached --stat
git diff --cached

Using the diff and the commit convention detected in step 1, draft a commit message with:

  • A subject line (≤ 72 characters) that summarises the change, following the repository's convention.
  • An optional body that explains why the change was made, only when the diff is non-trivial.
  • Reference issue/ticket numbers when they appear in branch names or related context.
  • Focus on the intent of the change, not a file-by-file inventory.

4. Commit

Construct the git commit command with the generated message.

Execute the commit:

git commit -m "<subject>" -m "<body>"

5. Confirm

After the commit:

  • Run git status --short to confirm the commit completed.
  • Run git log --oneline -1 to show the new commit.
  • If pre-commit hooks changed files or blocked the commit, summarize exactly what happened.
  • If hooks rewrote files after the commit attempt, do not amend automatically. Tell the user what changed and ask whether they want you to stage and commit those follow-up edits.

来自 microsoft 的更多技能

oss-growth
microsoft
OSS增长黑客角色
agent-framework-azure-ai-py
microsoft
使用Microsoft Agent Framework Python SDK(agent-framework-azure-ai)构建Azure AI Foundry代理。在创建使用AzureAIAgentsProvider的持久化代理、使用托管工具(代码解释器、文件搜索、网络搜索)、集成MCP服务器、管理对话线程或实现流式响应时使用。涵盖函数工具、结构化输出和多工具代理。
development
airunway-aks-setup
microsoft
在AKS上设置AI Runway——从裸集群到运行模型。涵盖集群验证、控制器安装、GPU评估、提供商设置和首次部署。适用场景:“设置AI Runway”、“接入AKS集群”、“安装AI Runway”、“airunway设置”、“将模型部署到AKS”、“在AKS上进行GPU推理”、“在AKS上配置KAITO”、“在AKS上运行LLM”、“在AKS上使用vLLM”、“在AKS上设置模型服务”、“AI Runway控制器”。
devops
appinsights-instrumentation
microsoft
使用Azure Application Insights对Web应用进行插桩的指南。提供遥测模式、SDK设置和配置参考。适用场景:如何对应用进行插桩、App Insights SDK、遥测模式、什么是App Insights、Application Insights指南、插桩示例、APM最佳实践。
devops
applicationinsights-web-ts
microsoft
使用Application Insights JavaScript SDK(@microsoft/applicationinsights-web)为浏览器/Web应用添加检测。用于真实用户监控(RUM)——页面视图、点击、AJAX/fetch依赖项、异常、自定义事件,以及与后端OpenTelemetry追踪关联的浏览器端GenAI代理追踪。涵盖SDK加载器脚本和npm设置、框架扩展(React、React Native、Angular)、点击分析、遥测初始化器,以及从浏览器发出的代理/工具/模型跨度所遵循的OTel GenAI语义约定。
devops
azure-ai-anomalydetector-java
microsoft
使用适用于 Java 的 Azure AI 异常检测器 SDK 构建异常检测应用程序。在实现单变量/多变量异常检测、时间序列分析或 AI 驱动的监控时使用。
development
azure-ai-language-conversations-py
microsoft
使用azure-ai-language-conversations Python SDK实现对话语言理解(CLU)。当使用ConversationAnalysisClient分析对话意图和实体、构建NLP功能或将语言理解集成到应用程序中时使用。
development
azure-ai-ml-py
microsoft
Azure Machine Learning SDK v2 for Python。用于机器学习工作区、作业、模型、数据集、计算资源和管道。 触发词:“azure-ai-ml”、“MLClient”、“工作区”、“模型注册表”、“训练作业”、“数据集”。
development