prompt-refactor

作者: microsoft

根據明確需求,透過完整的提示建構循環來重構現有的提示產出物。

npx skills add https://github.com/microsoft/hve-core --skill prompt-refactor

Prompt Refactor Compatibility Skill

Goal

Preserve legacy prompt-refactor activation while simplifying approved prompt-engineering artifacts through the hve-builder refactor route and its independent quality gates.

Flow

  1. Translate promptFiles to existing targets and resolve the behavior that must remain unchanged.
  2. When requirements are omitted, use the HVE Builder baseline review to derive evidence-backed cleanup objectives.
  3. Activate hve-builder with mode=refactor, the approved write boundary, requirements, and any caller-owned evidence root.
  4. Return the HVE Builder review verdict, validation result, and overall outcome.

Inputs

  • promptFiles: existing prompt-engineering artifacts to refactor
  • requirements: optional cleanup objectives, constraints, and preserved behavior
  • evidenceRoot: optional caller-owned HVE Builder evidence path

Success Criteria

  • The approved targets are simpler without unintended behavior change.
  • The review pass and host validation pass.
  • Source changes stay inside the approved write boundary.
  • The returned overall outcome is unchanged from hve-builder.

Constraints

  • Do not dispatch retired named lifecycle workers.
  • Do not create a second orchestration loop or review contract.
  • Route a requested type change, artifact split, or new support artifact back through HVE Builder scope approval.

Stop Rules

  • Stop Pass only when the HVE Builder refactor route passes every required gate.
  • Preserve Revise, Deferred, or Blocked and its rerun condition.
  • Ask when preserved behavior or write scope cannot be inferred safely.

Handoff

Use prompt-analyze for read-only follow-up review and prompt-builder when the requested work intentionally changes behavior or creates artifacts.

Final Response Contract

Return targets, changed files, refactor rationale, review verdict, validation result, overall outcome, evidence links, and next action.

來自 microsoft 的更多技能

oss-growth
microsoft
開源增長駭客角色
agent-framework-azure-ai-py
microsoft
使用Microsoft Agent Framework Python SDK(agent-framework-azure-ai)构建Azure AI Foundry代理。适用于使用AzureAIAgentsProvider创建持久化代理、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。涵盖函数工具、结构化输出和多工具代理。
development
airunway-aks-setup
microsoft
在AKS上設定AI Runway——從裸叢集到執行模型。涵蓋叢集驗證、控制器安裝、GPU評估、供應商設定及首次部署。時機:「設定AI Runway」、「上線AKS叢集」、「安裝AI Runway」、「airunway設定」、「部署模型至AKS」、「在AKS上進行GPU推論」、「在AKS上設定KAITO」、「在AKS上執行LLM」、「在AKS上使用vLLM」、「在AKS上設定模型服務」、「AI Runway控制器」。
devops
appinsights-instrumentation
microsoft
使用Azure Application Insights檢測Web應用程式的指南。提供遙測模式、SDK設定與組態參考。適用時機:如何檢測應用程式、App Insights SDK、遙測模式、什麼是App Insights、Application Insights指南、檢測範例、APM最佳實踐。
devops
applicationinsights-web-ts
microsoft
使用Application Insights JavaScript SDK(@microsoft/applicationinsights-web)為瀏覽器/Web應用程式進行檢測。適用於真實使用者監控(RUM)——頁面檢視、點擊、AJAX/fetch依賴、例外、自訂事件,以及與後端OpenTelemetry追蹤關聯的瀏覽器端GenAI代理追蹤。涵蓋SDK載入器指令碼與npm設定、框架擴充(React、React Native、Angular)、點擊分析、遙測初始化器,以及從瀏覽器發出的代理/工具/模型span的OTel GenAI語意慣例。
devops
azure-ai-anomalydetector-java
microsoft
使用適用於 Java 的 Azure AI 異常偵測器 SDK 建置異常偵測應用程式。在實作單變量/多變量異常偵測、時間序列分析或 AI 驅動監控時使用。
development
azure-ai-language-conversations-py
microsoft
使用 azure-ai-language-conversations Python SDK 實作對話語言理解(CLU)。當使用 ConversationAnalysisClient 分析對話意圖與實體、建置 NLP 功能,或將語言理解整合至應用程式時使用。
development
azure-ai-ml-py
microsoft
Azure Machine Learning SDK v2 for Python。用於機器學習工作區、作業、模型、資料集、計算資源與管線。 觸發詞:「azure-ai-ml」、「MLClient」、「workspace」、「model registry」、「training jobs」、「datasets」。
development