list-plans

作者: microsoft

在工作區中發現有效的遷移計畫,並返回所選計畫的路徑。有效的計畫是 .github/modernize/ 下包含 plan.md 的子目錄…

npx skills add https://github.com/microsoft/github-copilot-modernization --skill list-plans

List and Select Plan

Step 1 — Discover valid plans

You MUST run this in a terminal — do NOT use file tools (list_dir, file_search, grep_search) to discover plans.

Detect the OS and run the matching script in the terminal. Replace <workspace-root> with the absolute path to the workspace root before running.

Windows (PowerShell) — run in terminal:

Set-Location "<workspace-root>"
$modernizeDir = ".github/modernize"
$plans = @()

if (Test-Path $modernizeDir) {
    Get-ChildItem -Path $modernizeDir -Directory | ForEach-Object {
        $hasPlan  = Test-Path (Join-Path $_.FullName "plan.md")
        $hasTasks = (Test-Path (Join-Path $_.FullName "tasks.json")) -or (Test-Path (Join-Path $_.FullName ".metadata/tasks.json"))
        if ($hasPlan -and $hasTasks) {
            $plans += @{ folder = $_.Name; planPath = "$modernizeDir/$($_.Name)/plan.md" }
        }
    }
}

$plans | ConvertTo-Json -Depth 2

macOS / Linux (bash) — run in terminal:

cd "<workspace-root>"
modernize_dir=".github/modernize"
entries="[]"

if [ -d "$modernize_dir" ]; then
    for folder in "$modernize_dir"/*/; do
        [ -d "$folder" ] || continue
        name=$(basename "$folder")
        if [ -f "$folder/plan.md" ] && ([ -f "$folder/tasks.json" ] || [ -f "$folder/.metadata/tasks.json" ]); then
            entry="{\"folder\":\"$name\",\"planPath\":\"$modernize_dir/$name/plan.md\"}"
            if [ "$entries" = "[]" ]; then
                entries="[$entry]"
            else
                entries="${entries%]},$entry]"
            fi
        fi
    done
fi

echo "$entries"

Parse the JSON output from the terminal as the list of valid plans for the next step.

Step 2 — Route based on count

No plans found

Return no-plans-found to the caller. Do not prompt the user.

Exactly 1 plan found

Return its path immediately — no user prompt needed:

.github/modernize/<folder>/plan.md

Multiple plans found

  1. For each plan, read .github/modernize/<folder>/plan.md, extract the first heading, strip the leading # and any prefix of the form <Word> Plan: (e.g. Modernization Plan: , Migration Plan: ), and use the remainder as the title.
  2. Do not invoke a question tool. Return exactly these two lines to planning-coordinator, with compact JSON on the second line and no surrounding prose or Markdown fence:
NEEDS_INPUT
{"schemaVersion":1,"coordinator":"planning-coordinator","requestType":"plan-selection","questions":[{"header":"plan-selection","question":"Which plan would you like to execute?","allowFreeformInput":false,"options":[{"label":"<folder>","description":"<plan title>"}]}],"resumeContext":{"plans":[{"label":"<folder>","planPath":".github/modernize/<folder>/plan.md"}]}}

Include one option and one matching resumeContext.plans entry per discovered plan, preserving discovery order. The option label is the folder name and its description is the title from step 1. Never select the first plan by default.

Step 3 — Return

After planning-coordinator receives the top-level structured answer, it resolves the selected label through resumeContext.plans and returns that path:

.github/modernize/<selected-folder>/plan.md

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