fix-customization-evaluation-diagnostics

作者: microsoft

修复聊天自定义评估扩展在活动提示文件中报告的诊断问题。从编辑器中读取当前诊断并…

npx skills add https://github.com/microsoft/vscode-chat-customizations-evaluation --skill fix-customization-evaluation-diagnostics

Implement suggestions

Purpose

Fix issues found by the Chat Customizations Evaluations analyzer in prompt, agent, skill, and instruction files. The diagnostics include contradictions, ambiguities, persona conflicts, cognitive load issues, and coverage gaps.

Usage

This skill is invoked automatically when the user clicks the "Implement suggestions" button in the editor title bar. It receives the diagnostics as context and rewrites the affected sections of the file to resolve them.

This skill can also be called directly by the user. In that case search for the diagnostics from the Chat Customizations Evaluations extension and apply the fixes.

Instructions

  • You will either receive a list of diagnostics from the Chat Customizations Evaluations extension or be called without diagnostics.
  • If you receive a list of diagnostics from the Chat Customizations Evaluations extension, then each diagnostic will includes a line number, code, message, and optionally a suggestion.
  • If you are called without diagnostics, you should search and find diagnostics from the Chat Customizations Evaluations extension yourself.
  • For each diagnostic, apply the fix directly to the file content. Use the suggestion if one is provided; otherwise, use your judgment to resolve the issue.
  • Preserve the overall structure, tone, and intent of the prompt file. Only change what is necessary to resolve the diagnostics.
  • If two diagnostics conflict with each other, prefer the fix that keeps the prompt clearer and more consistent.
  • Directly edit the file content to apply the fixes.
  • Do NOT add new instructions or sections that were not in the original file.
  • Do NOT remove instructions unless a diagnostic specifically calls for it (e.g., contradictions).

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