Communitygithub.com

ComeOnOliver/skillshub

该技能为 Azure AI Video Indexer 提供专家级指导,涵盖故障排除、最佳实践、决策制定、架构与设计模式、限制与配额、安全性、配置、集成与编码模式以及部署。它结合了本地快速参考内容和远程文档获取功能。

skillshub 是什么?

此技能旨在帮助开发者与AI代理高效使用 Azure AI Video Indexer。它通过一个清晰的分类索引(涵盖故障排除、最佳实践、决策制定、架构设计、安全配置等核心领域)来组织本地快速参考内容。当用户需要更深入的官方文档时,该技能能够自动利用 `mcp_microsoftdocs` 工具或回退到 `fetch_webpage` 来从Microsoft Learn远程获取最新的Markdown格式文档。该技能设计为适用于Claude Code、Coder、Cursor等AI助手平台,通过明确的指令告诉AI代理如何使用该技能(如通过行号读取特定部分),并提供了详尽的URL列表供代理在需要时调用。其核心价值在于提供了一个集成的、智能化的“知识库”,让AI代理能够一步到位地检索到关于Azure Video Indexer的精确信息,从而显著提升故障诊断、方案设计和开发效率。

兼容平台~Claude Code✓Codex CLI~Cursor
npx skills add https://github.com/ComeOnOliver/skillshub/tree/HEAD/skills/MicrosoftDocs/Agent-Skills/azure-video-indexer

在你喜欢的 AI 中提问

打开一个已预加载此 Agent Skill 的新对话。

文档

Azure AI Video Indexer 技能

此技能为 Azure AI Video Indexer 提供专家级指导,涵盖故障排除、最佳实践、决策制定、架构与设计模式、限制与配额、安全性、配置、集成与编码模式以及部署。它结合了本地快速参考内容和远程文档获取功能。

如何使用此技能

代理注意:请使用下方的分类索引来定位相关章节。对于带有行范围的分类(例如 L35-L120),请使用 read_file 并指定相应的行数。对于带有文件链接的分类(例如 [security.md](security.md)),请对链接的参考文件使用 read_file。

代理注意:如果 metadata.generated_at 超过 3 个月,建议用户从仓库拉取最新版本。如果 mcp_microsoftdocs 工具不可用,建议用户安装它:安装指南

此技能需要网络访问来获取文档内容:

  • 首选方法:使用 mcp_microsoftdocs:microsoft_docs_fetch 并附带查询字符串 from=learn-agent-skill。返回 Markdown 格式。
  • 备选方法:使用 fetch_webpage 并附带查询字符串 from=learn-agent-skill&accept=text/markdown。返回 Markdown 格式。

分类索引

分类行号描述
故障排除L37-L41排查并解决在 Arc 上运行 Azure Video Indexer 时遇到的问题,包括连接、部署、配置和运行时故障排除步骤。
最佳实践L42-L49关于使用 AI 代理进行实时分析、扩展 Video Indexer、训练自定义语音模型以及解释基于文本的情绪检测洞察的指导。
决策制定L50-L55关于选择合适的 Azure Video Indexer 帐户类型以及设计多租户设置的指导,包括针对多个客户或应用的隔离、扩展和管理策略。
架构与设计模式L56-L60关于为 Azure Video Indexer 设计灾难恢复和故障转移的指导,包括冗余、区域故障转移、备份和高可用性设计考量。
限制与配额L61-L68服务限制、支持的语言/功能,以及如何使用实时摄像索引功能(如事件摘要和查看实时录制内容)。
安全性L69-L81保护 Video Indexer:角色和访问控制、受限/有限功能、自定义人物模型、NSG/服务标签、私有端点和防火墙保护存储的最佳实践。
配置L82-L99配置 Video Indexer:自定义模型(品牌、语言、语音)、转录本和发言者、索引/实时预设、区域、监控以及高级上传/搜索设置。
集成与编码模式L100-L123使用 Video Indexer API、小部件和 Logic Apps/Power Automate 来提取、使用或遮罩洞察(人脸、对象、文本、音频、主题)并与 Azure OpenAI 集成。
部署L124-L129使用 Arc 扩展、ARM 和 Bicep 模板部署 Azure Video Indexer 的指南,包括预配帐户和配置基础设施即代码。

故障排除

主题URL
对由 Arc 启用的 Azure Video Indexer 进行故障排除https://learn.microsoft.com/en-us/azure/azure-video-indexer/arc/azure-video-indexer-enabled-by-arc-troubleshooting

最佳实践

主题URL
使用 AI 代理进行实时 Video Indexer 分析https://learn.microsoft.com/en-us/azure/azure-video-indexer/agents-overview
应用 Azure Video Indexer 的规模最佳实践https://learn.microsoft.com/en-us/azure/azure-video-indexer/considerations-when-use-at-scale
应用 Video Indexer 语音模型训练的最佳实践https://learn.microsoft.com/en-us/azure/azure-video-indexer/speech-model-training-best-practices
解释 Video Indexer 中基于文本的情绪检测洞察https://learn.microsoft.com/en-us/azure/azure-video-indexer/text-based-emotions-detection-insight

决策制定

主题URL
在 Azure Video Indexer 帐户类型之间进行选择https://learn.microsoft.com/en-us/azure/azure-video-indexer/accounts-overview
选择 Video Indexer 的多租户管理策略https://learn.microsoft.com/en-us/azure/azure-video-indexer/manage-multiple-tenants

架构与设计模式

主题URL
为 Video Indexer 设计灾难恢复和故障转移https://learn.microsoft.com/en-us/azure/azure-video-indexer/video-indexer-disaster-recovery

限制与配额

主题URL
查看 Azure Video Indexer 支持矩阵和服务限制https://learn.microsoft.com/en-us/azure/azure-video-indexer/avi-support-matrix
检查 Video Indexer 中的语言支持和功能https://learn.microsoft.com/en-us/azure/azure-video-indexer/language-support
为实时摄像画面生成事件摘要https://learn.microsoft.com/en-us/azure/azure-video-indexer/live-event-summary
在 Video Indexer 中查看实时摄像录制内容https://learn.microsoft.com/en-us/azure/azure-video-indexer/live-watch-recordings

安全性

主题URL
使用受限人脸功能创建 Azure Video Indexer 帐户https://learn.microsoft.com/en-us/azure/azure-video-indexer/create-account
在 Video Indexer 中配置和使用自定义人物模型https://learn.microsoft.com/en-us/azure/azure-video-indexer/customize-person-model-how-to
请求访问受限的 Azure Video Indexer 功能https://learn.microsoft.com/en-us/azure/azure-video-indexer/limited-access-features
使用 NSG 和服务标签保护 Video Indexer 流量https://learn.microsoft.com/en-us/azure/azure-video-indexer/network-security
为 Azure Video Indexer 配置私有端点https://learn.microsoft.com/en-us/azure/azure-video-indexer/private-endpoint-how-to
使用私有端点保护 Azure Video Indexerhttps://learn.microsoft.com/en-us/azure/azure-video-indexer/private-endpoint-overview
使用内置角色管理 Video Indexer 帐户访问权限https://learn.microsoft.com/en-us/azure/azure-video-indexer/restricted-viewer-role
为 Video Indexer 实施安全基线和最佳实践https://learn.microsoft.com/en-us/azure/azure-video-indexer/security-baseline-video-indexer
使用防火墙保护的存储帐户保护 Video Indexerhttps://learn.microsoft.com/en-us/azure/azure-video-indexer/storage-behind-firewall

配置

主题URL
在 Video Indexer 中自定义品牌检测模型https://learn.microsoft.com/en-us/azure/azure-video-indexer/customize-brands-model-how-to
在 Video Indexer 中配置自定义语言模型https://learn.microsoft.com/en-us/azure/azure-video-indexer/customize-language-model-how-to
在 Video Indexer 中创建和管理自定义语音模型https://learn.microsoft.com/en-us/azure/azure-video-indexer/customize-speech-model-how-to
编辑 Azure Video Indexer 转录本中的发言者身份https://learn.microsoft.com/en-us/azure/azure-video-indexer/edit-speakers
编辑和管理 Azure Video Indexer 中的转录内容https://learn.microsoft.com/en-us/azure/azure-video-indexer/edit-transcript-lines-portal
配置 Azure Video Indexer 的索引选项https://learn.microsoft.com/en-us/azure/azure-video-indexer/indexing-configuration-guide
在 Video Indexer 中配置自定义实时 AI 洞察预设https://learn.microsoft.com/en-us/azure/azure-video-indexer/live-ai-insights-catalog
为实时摄像分析配置关注区域https://learn.microsoft.com/en-us/azure/azure-video-indexer/live-area-interest
配置 Azure Video Indexer 实时扩展https://learn.microsoft.com/en-us/azure/azure-video-indexer/live-extension
使用 Azure Monitor 配置 Azure Video Indexer 的监控https://learn.microsoft.com/en-us/azure/azure-video-indexer/monitor-video-indexer
Azure Video Indexer 监控数据参考https://learn.microsoft.com/en-us/azure/azure-video-indexer/monitor-video-indexer-data-reference
为 Video Indexer API 配置区域和位置参数https://learn.microsoft.com/en-us/azure/azure-video-indexer/regions
使用高级 Video Indexer 设置上传和索引媒体https://learn.microsoft.com/en-us/azure/azure-video-indexer/upload-index-media
在 Azure Video Indexer 中搜索和筛选视频库https://learn.microsoft.com/en-us/azure/azure-video-indexer/video-indexer-search

集成与编码模式

主题URL
通过 Video Indexer 检索音频效果检测洞察https://learn.microsoft.com/en-us/azure/azure-video-indexer/audio-effects-detection-insight
通过 Video Indexer 检索拍板检测洞察https://learn.microsoft.com/en-us/azure/azure-video-indexer/clapper-board-insight
将 Azure Video Indexer 帐户连接到 Azure OpenAIhttps://learn.microsoft.com/en-us/azure/azure-video-indexer/connect-azure-open-ai-task
在 Video Indexer 中使用数字模式和色条洞察https://learn.microsoft.com/en-us/azure/azure-video-indexer/digital-patterns-color-bars-insight
从 Azure Video Indexer 检索人脸检测洞察https://learn.microsoft.com/en-us/azure/azure-video-indexer/face-detection-insight
使用 Video Indexer API 在视频中遮罩人脸https://learn.microsoft.com/en-us/azure/azure-video-indexer/face-redaction-with-api
从 Azure Video Indexer 获取关键词提取洞察https://learn.microsoft.com/en-us/azure/azure-video-indexer/keywords-insight
从 Video Indexer 获取标签识别洞察https://learn.microsoft.com/en-us/azure/azure-video-indexer/labels-identification-insight
将 Video Indexer 与 Logic Apps 和 Power Automate 集成https://learn.microsoft.com/en-us/azure/azure-video-indexer/logic-apps-connector-arm-accounts
在 Video Indexer 中使用命名实体提取洞察https://learn.microsoft.com/en-us/azure/azure-video-indexer/named-entities-insight
从 Azure Video Indexer 获取对象检测洞察https://learn.microsoft.com/en-us/azure/azure-video-indexer/object-detection-insight
在 Video Indexer 中使用观察到的人物和匹配人脸洞察https://learn.microsoft.com/en-us/azure/azure-video-indexer/observed-matched-people-insight
为观察到的人物启用特色服装洞察https://learn.microsoft.com/en-us/azure/azure-video-indexer/observed-people-featured-clothing
从 Azure Video Indexer 获取 OCR 洞察https://learn.microsoft.com/en-us/azure/azure-video-indexer/ocr-insight
获取场景、镜头和关键帧检测洞察https://learn.microsoft.com/en-us/azure/azure-video-indexer/scene-shot-keyframe-detection-insight
使用 Azure OpenAI 文本摘要与 Video Indexerhttps://learn.microsoft.com/en-us/azure/azure-video-indexer/text-summarization-task
从 Azure Video Indexer 获取主题推理洞察https://learn.microsoft.com/en-us/azure/azure-video-indexer/topics-inference-insight
使用 Video Indexer 的转录和翻译洞察https://learn.microsoft.com/en-us/azure/azure-video-indexer/transcription-translation-lid-insight
在应用程序中嵌入 Azure Video Indexer 小部件https://learn.microsoft.com/en-us/azure/azure-video-indexer/video-indexer-embed-widgets
使用付费帐户的 Azure Video Indexer REST APIhttps://learn.microsoft.com/en-us/azure/azure-video-indexer/video-indexer-use-apis

部署

主题URL
将 Azure Video Indexer 作为 Arc 扩展启用https://learn.microsoft.com/en-us/azure/azure-video-indexer/arc/azure-video-indexer-enabled-by-arc-quickstart
使用 ARM 模板预配 Azure Video Indexerhttps://learn.microsoft.com/en-us/azure/azure-video-indexer/deploy-with-arm-template
使用 Bicep 模板部署 Azure Video Indexer 帐户https://learn.microsoft.com/en-us/azure/azure-video-indexer/deploy-with-bicep

Individual skills in this repo

This repo contains 20 individual skills — each has its own dedicated page.

ComeOnOliver/skillshub

Create stunning, animation-rich HTML presentations from scratch or by converting PowerPoint files. Use when the user wants to build a presentation, convert a PPT/PPTX to web, or create slides for a talk/pitch. Helps non-designers discover their aesthetic through visual exploration rather than abstract choices.

ComeOnOliver/skillshub

Next.js 16+ 和 Turbopack — 增量打包、文件系统缓存、开发速度,以及何时使用 Turbopack 与 webpack。

ComeOnOliver/skillshub

SwiftUI architecture patterns, state management with @Observable, view composition, navigation, performance optimization, and modern iOS/macOS UI best practices.

ComeOnOliver/skillshub

See, Understand, Act on video and audio. See- ingest from local files, URLs, RTSP/live feeds, or live record desktop; return realtime context and playable stream links. Understand- extract frames, build visual/semantic/temporal indexes, and search moments with timestamps and auto-clips. Act- transcode and normalize (codec, fps, resolution, aspect ratio), perform timeline edits (subtitles, text/image overlays, branding, audio overlays, dubbing, translation), generate media assets (image, audio, video), and create real time alerts for events from live streams or desktop capture.

ComeOnOliver/skillshub

AI-assisted video editing workflows for cutting, structuring, and augmenting real footage. Covers the full pipeline from raw capture through FFmpeg, Remotion, ElevenLabs, fal.ai, and final polish in Descript or CapCut. Use when the user wants to edit video, cut footage, create vlogs, or build video content.

ComeOnOliver/skillshub

Next.js 15 애플리케이션을 위한 프론트엔드 개발 가이드라인. React 19, TypeScript, Shadcn/ui, Tailwind CSS를 사용한 모던 패턴. Server Components, Client Components, App Router, 파일 구조, Shadcn/ui 컴포넌트, 성능 최적화, TypeScript 모범 사례 포함. 컴포넌트, 페이지, 기능 생성, 데이터 페칭, 스타일링, 라우팅, 프론트엔드 코드 작업 시 사용.

ComeOnOliver/skillshub

Provides Tamagui patterns for config v4, compiler optimization, styled context, and cross-platform styling. Must use when working with Tamagui projects (tamagui.config.ts, @tamagui imports).

ComeOnOliver/skillshub

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.

ComeOnOliver/skillshub

Create high-converting, visually distinctive landing pages. Use when building marketing pages, product launches, SaaS homepages, or any single-page conversion-focused website. Guides section-by-section composition with anti-AI-slop principles.

ComeOnOliver/skillshub

Auto-loaded context for Portfolio Buddy 2 development. Use for ANY task involving: React 19 development, TypeScript, portfolio analysis features, metrics calculations, trading strategy comparison, or working with the Portfolio Buddy 2 codebase. Contains tech stack, known issues, and architectural constraints.

ComeOnOliver/skillshub

Next.js development tooling via MCP. Inspect routes, components, build info, and debug Next.js apps. Use when working on Next.js applications, debugging routing, or inspecting app structure. NOT for general React or non-Next.js projects.

ComeOnOliver/skillshub

Implement UI using Shadcn MCP (atoms/theme) and 21st.dev MCP (complex sections). Use when adding buttons, layouts, or generating landing pages.

ComeOnOliver/skillshub

A conceptual skill for building an API client in Next.js that handles JWT tokens

ComeOnOliver/skillshub

Best practices and patterns for Next.js App Router, Server Actions, and Routing in this project.

ComeOnOliver/skillshub

The Design System, Theme, and UX rules for the Physical AI Hub.

ComeOnOliver/skillshub

Comprehensive frontend development skill for building modern, performant web applications using ReactJS, NextJS, TypeScript, Tailwind CSS. Includes component scaffolding, performance optimization, bundle analysis, and UI best practices. Use when developing frontend features, optimizing performance, implementing UI/UX designs, managing state, or reviewing frontend code.

ComeOnOliver/skillshub

This document captures learnings from fixing keyboard navigation issues when floating components (Select, DropdownMenu, Popover) have CSS open/close animations.

ComeOnOliver/skillshub

Build Next.js 16 applications with correct patterns and distinctive design. Use when creating pages, layouts, dynamic routes, upgrading from Next.js 15, or implementing proxy.ts. Covers breaking changes (async params/searchParams, Turbopack, cacheComponents) and frontend aesthetics. NOT when building non-React or backend-only applications.

ComeOnOliver/skillshub

Comprehensive Framer Motion animation library for React. Covers motion components, variants, gestures, page transitions, and scroll animations. Use when adding animations to React/Next.js applications.

ComeOnOliver/skillshub

Build interfaces that resonate, not just render. This skill enforces bold, intentional

相关技能