triage-meeting-prep

작성자: microsoft

WinAppSDK Needs-Triage 문제에 대한 주간 트라이지 미팅 요약을 준비합니다. 트라이지 미팅 준비, Needs-Triage 문제 검토, 차이 생성 시 사용합니다.

npx skills add https://github.com/microsoft/windowsappsdk --skill triage-meeting-prep

Triage Meeting Preparation

This skill helps prepare comprehensive summaries for the twice-weekly WinAppSDK triage meetings. It focuses on issues that actually need triage attention:

  1. Needs-Triage WITHOUT area label — These need area assignment (primary focus)
  2. Closed issues still labeled Needs-Triage — These need follow-up replies

Note: Open issues with both Needs-Triage AND an area-* label are excluded — they're already triaged and waiting for area team action.

Research-Backed Analysis

Every suggestion and reply is backed by research:

Research TypeWhat We SearchWhy
🔍 Similar IssuesGitHub issue searchFind duplicates, related bugs, past fixes
💻 Codebasegrep_search, semantic_searchUnderstand technical context, find workarounds
📚 Documentationfetch_webpage on MS docsVerify known limitations, expected behavior
📜 Git Historygit log, git blameIdentify area owners, recent changes

This ensures:

  • Suggested replies are technically accurate
  • Workarounds are validated against the codebase
  • We reference related issues customers may have missed
  • Area assignments are informed by code structure

Key Outputs: What's Changed Since Last Triage

The skill tracks four critical categories for each meeting:

CategoryDescriptionAction Required
🌟 Popular Issues≥5 reactions (community interest)May need priority attention
🆕 Created This WeekIssues created since last weekly triageReview + assign area
⏳ Older PendingOlder issues still without area labelsFollow up — why no action?
✅ Closed (need reply)Closed issues with customer follow-upDraft reply with [confidence:XX]

All suggestions include confidence scoring in [confidence:XX] format for easy filtering.

When to Use This Skill

Primary triggers — Use this skill when:

  1. Preparing for triage meetings — Generate a summary of issues needing area assignment
  2. Reviewing what's changed — See the diff of issues since the last triage run
  3. Drafting customer replies — Get research-backed suggested replies for closed issues
  4. Tracking pending items — Identify issues that still haven't been actioned from previous meetings

Anti-patterns — Do NOT use this skill when:

  • Reviewing a single specific issue (use Get-IssueDetails.ps1 for individual issues)
  • General issue searching without triage context
  • Non-WinAppSDK repositories

Prerequisites

  • GitHub CLI (gh) installed and authenticated (gh auth login)
  • Access to microsoft/WindowsAppSDK repository
  • Previous triage state file for diff comparison: Generated-Files/triageMeeting/previous-state.json

Migration note: If you have an existing Generated Files/triageMeeting/... directory from earlier runs, rename Generated Files to Generated-Files before using this skill, or pass explicit input/output paths to the scripts so you keep prior diff history.

Installing GitHub CLI

# Windows
winget install GitHub.cli

# Then authenticate
gh auth login

Step-by-Step Workflow

Workflow: Generate Triage Meeting Summary

  1. Load previous triage state from Generated-Files/triageMeeting/previous-state.json
  2. Fetch current Needs-Triage issues using the scripts:
    # Get all issues needing triage (no area label)
    ./.github/skills/triage-meeting-prep/scripts/Get-TriageIssues.ps1 -NoAreaOnly -OutputFormat summary
    
    # Or get JSON for processing
    $issues = ./.github/skills/triage-meeting-prep/scripts/Get-TriageIssues.ps1 -NoAreaOnly | ConvertFrom-Json
    
  3. Categorize issues by creation date:
    • 🆕 Created This Week — createdAt ≥ last weekly triage date
    • ⏳ Older Pending — createdAt < last weekly triage date
  4. Fetch area label definitions for classification:
    ./.github/skills/triage-meeting-prep/scripts/Get-RepositoryLabels.ps1 -Filter "area-*" -OutputFormat json
    
  5. For each no-area issue, analyze using Get-IssueDetails.ps1:
    • Run: ./Get-IssueDetails.ps1 -IssueNumber <number> -OutputFormat summary
    • Review the issue body, comments, and labels
    • Classify the area label by reasoning about the issue content against the area label definitions (see workflow for confidence rubric)
  6. Generate summary report with links to each issue's overview.md
  7. Save current state for next diff comparison

Important: Every issue without an area label gets a review. The summary links to each review file.

Available Scripts

The skill provides several PowerShell scripts for data fetching and analysis:

Get-TriageIssues.ps1

Fetches all issues with the Needs-Triage label from the repository.

# Get all Needs-Triage issues without area labels
./Get-TriageIssues.ps1 -NoAreaOnly -OutputFormat summary

# Get JSON output for programmatic processing
$issues = ./Get-TriageIssues.ps1 -NoAreaOnly | ConvertFrom-Json

Parameters:

  • -Repository — Repository in 'owner/repo' format (default: microsoft/WindowsAppSDK)
  • -State — Filter by state: 'open', 'closed', or 'all' (default: all)
  • -NoAreaOnly — Only include issues without area-* labels
  • -Limit — Maximum issues to fetch (default: 200)
  • -OutputFormat — Output format: 'json', 'summary', or 'table' (default: json)

Get-IssueDetails.ps1

Performs deep analysis of a single issue including scoring and recommendations.

# Analyze a specific issue
./Get-IssueDetails.ps1 -IssueNumber 1234 -OutputFormat summary

Get-RepositoryLabels.ps1

Fetches all label definitions from the repository including names, descriptions, and colors.

# Get all labels
./Get-RepositoryLabels.ps1 -OutputFormat summary

# Get only area labels
./Get-RepositoryLabels.ps1 -Filter "area-*" -OutputFormat table

# Get labels from a different repository
./Get-RepositoryLabels.ps1 -Repository "microsoft/terminal" -OutputFormat json

Parameters:

  • -Repository — Repository in 'owner/repo' format (default: microsoft/WindowsAppSDK)
  • -Filter — Filter pattern for label names (supports wildcards like 'area-*')
  • -Limit — Maximum labels to fetch (default: 500)
  • -OutputFormat — Output format: 'json', 'summary', or 'table' (default: json)

Use cases:

  • Understanding available area labels for issue categorization
  • Verifying label descriptions for triage decisions
  • Comparing label definitions across repositories
  • Finding labels that lack descriptions

Compare-TriageState.ps1

Compares current triage state with previous state to identify changes.

Save-TriageState.ps1

Saves the current triage state for future comparisons.

Output Structure

All outputs are saved to Generated-Files/triageMeeting/<date>/:

FilePurpose
summary.mdMain meeting document with tables linking to individual reviews
previous-state.jsonState snapshot for next diff (auto-generated)

Individual issue reviews are saved to Generated-Files/issueReview/<issue-number>/:

FilePurpose
overview.mdFull issue analysis with scores and suggested actions (linked from summary)
implementation-plan.mdTechnical implementation details (if applicable)

Key Output: The summary.md includes the Suggested Actions section extracted from each issue's overview.md, with [confidence:XX] scores.

Detailed Workflow

See workflow-triage-prep.md for the complete step-by-step process.

Issue Categories

CategoryDefinitionAction Needed
🌟 Popular Issues≥5 reactions (community interest)May need priority attention
🆕 Created This WeekcreatedAt is after last weekly triage dateUse Get-IssueDetails.ps1 + assign area
⏳ Older PendingCreated before this week, still no area labelFollow up — why not actioned?
✅ ResolvedIn previous state, NOT in currentAcknowledge (got area label or closed)
🏷️ Closed (cleanup)Closed + still has Needs-Triage labelRemove Needs-Triage label

Key distinction: "Created This Week" is based on when the issue was created (createdAt), not when it was first seen in triage runs. This ensures new issues are highlighted even if triage runs multiple times per week.

Summary.md Format

See template-summary.md for the full template structure.

Area Classification (LLM-Based)

Issues without an area-* label are classified by the agent using LLM reasoning — not keyword matching. The agent:

  1. Fetches area label definitions via Get-RepositoryLabels.ps1 -Filter "area-*"
  2. Reads the issue title, body, and comments from Get-IssueDetails.ps1
  3. Reasons about the best area match and assigns a confidence score

Confidence scale:

ScoreLevelMeaning
80–100HighIssue explicitly names the component; maps to exactly one area
60–79Medium-HighStrong signals (stack traces, API names) point to one area
40–59MediumReasonable match, but 2+ areas are plausible
20–39LowWeak signal; best guess
0–19Very LowNo clear signal; vague or multi-area

See workflow-triage-prep.md for the full confidence rubric and adjusters.

Action Item Types

ActionWhen to Suggest
Assign to milestoneHigh business importance, clear scope
Add area labelMissing component/area identification
Request clarificationRequirement clarity < 50
Close as duplicateSimilar closed issue found with fix
Close as by-designExpected behavior, not a bug
Needs investigationRepro unclear, needs debugging
Ready for workClear requirements, assignable

Troubleshooting

SymptomSolution
No previous state fileFirst run — all issues shown as "New"
gh CLI not installedRun winget install GitHub.cli then gh auth login
gh not authenticatedRun gh auth login and follow the prompts
Rate limitedWait and retry, or reduce --limit parameter
Missing issue detailsUse Get-IssueDetails.ps1 -IssueNumber <number>

Related Resources

microsoft의 다른 스킬

oss-growth
microsoft
OSS 성장 해커 페르소나
agent-framework-azure-ai-py
microsoft
Microsoft Agent Framework Python SDK(agent-framework-azure-ai)를 사용하여 Azure AI Foundry 에이전트를 구축합니다. AzureAIAgentsProvider로 지속적 에이전트를 만들 때, 호스팅 도구(코드 인터프리터, 파일 검색, 웹 검색)를 사용할 때, MCP 서버를 통합할 때, 대화 스레드를 관리할 때, 또는 스트리밍 응답을 구현할 때 사용합니다. 함수 도구, 구조화된 출력, 다중 도구 에이전트를 다룹니다.
development
airunway-aks-setup
microsoft
AKS에서 AI Runway 설정 — 빈 클러스터에서 실행 중인 모델까지. 클러스터 검증, 컨트롤러 설치, GPU 평가, 공급자 설정, 첫 배포를 다룹니다. 시기: "AI Runway 설정", "AKS 클러스터 온보딩", "AI Runway 설치", "airunway 설정", "AKS에 모델 배포", "AKS에서 GPU 추론", "AKS에서 KAITO 설정", "AKS에서 LLM 실행", "AKS에서 vLLM", "AKS에서 모델 서빙 설정", "AI Runway 컨트롤러".
devops
appinsights-instrumentation
microsoft
Azure Application Insights로 웹앱을 계측하기 위한 지침입니다. 원격 분석 패턴, SDK 설정, 구성 참조를 제공합니다. WHEN: 앱 계측 방법, App Insights SDK, 원격 분석 패턴, App Insights란 무엇인가, Application Insights 지침, 계측 예시, APM 모범 사례.
devops
applicationinsights-web-ts
microsoft
브라우저/웹 앱을 Application Insights JavaScript SDK(@microsoft/applicationinsights-web)로 계측합니다. Real User Monitoring(RUM) — 페이지 뷰, 클릭, AJAX/fetch 종속성, 예외, 사용자 지정 이벤트, 백엔드 OpenTelemetry 트레이스와 상관관계가 있는 브라우저 측 GenAI 에이전트 트레이스에 사용합니다. SDK Loader Script 및 npm 설정, 프레임워크 확장(React, React Native, Angular), Click Analytics, 텔레메트리 이니셜라이저, 브라우저에서 생성된 에이전트/도구/모델 스팬에 대한 OTel GenAI 의미론적 규칙을 다룹니다.
devops
azure-ai-anomalydetector-java
microsoft
Azure AI Anomaly Detector SDK for Java로 이상 탐지 애플리케이션을 구축하세요. 단변량/다변량 이상 탐지, 시계열 분석 또는 AI 기반 모니터링을 구현할 때 사용하세요.
development
azure-ai-language-conversations-py
microsoft
azure-ai-language-conversations Python SDK를 사용하여 대화형 언어 이해(CLU)를 구현합니다. ConversationAnalysisClient로 대화 의도와 엔터티를 분석하거나, NLP 기능을 구축하거나, 애플리케이션에 언어 이해를 통합할 때 사용합니다.
development
azure-ai-ml-py
microsoft
Azure Machine Learning SDK v2 for Python. ML 작업 영역, 작업, 모델, 데이터 세트, 컴퓨팅 및 파이프라인에 사용합니다. 트리거: "azure-ai-ml", "MLClient", "workspace", "model registry", "training jobs", "datasets".
development