microsoft-foundry-tools — скилл для Claude Code: Azure AI сервисы
Скилл microsoft-foundry-tools с экспертными знаниями об Azure AI services (Content Moderator, Content Safety, Content Understanding). Даёт советы по архитектуре, безопасности, лимитам и интеграции через REST/.NET API.
CC-BY-4.0 200 установок ★ 818 обновлён 2026-10-25
npx skills add MicrosoftDocs/Agent-Skills --skill microsoft-foundry-tools -a claude-codeЧто делает microsoft-foundry-tools
Это справочник по разработке с инструментами Microsoft Foundry Tools — сервисами обработки контента и документов в Azure. Скилл покрывает архитектуру решений, выбор между инструментами, настройку анализаторов документов, работу с Content Moderator и Content Understanding через REST и .NET API.
Внутри — рекомендации по лучшим практикам, устранению неполадок, расчёту квот и лимитов (поддерживаемые языки, ограничения на запросы), безопасности и шифрованию данных. Скилл помогает перейти с preview API на GA версию, выбрать между развёртыванием на serverless, managed или custom инфраструктуре.
Требует сетевой доступ. Скилл использует mcp_microsoftdocs:microsoft_docs_fetch или fetch_webpage для получения документации из Microsoft Learn. Если данные устаревают больше чем на 3 месяца, скилл подскажет обновить версию из репозитория.
Какие задачи решает
- выбрать между Content Moderator, Content Safety и Content Understanding для своей задачи
- настроить анализаторы документов и калибровать точность извлечения
- спроектировать масштабируемую архитектуру с правильным развёртыванием модели
- оставаться в рамках квот и лимитов по запросам и языкам
- защитить данные в Content Understanding: аутентификация, шифрование, изоляция сети
Примеры запросов агенту
- Помоги выбрать инструмент: мне нужна модерация видео и текста с поддержкой русского языка
- Как настроить Content Understanding для извлечения данных из PDF с высокой точностью
- Покажи пример на .NET, как работать с image lists в Content Moderator без превышения лимитов
Как установить microsoft-foundry-tools
1Через Skills CLI (Vercel)
npx skills add MicrosoftDocs/Agent-Skills --skill microsoft-foundry-tools -a claude-code2Вручную: положить файлы
~/.claude/skills/microsoft-foundry-tools/SKILL.mdПапка скилла целиком; для одного проекта — .claude/skills/microsoft-foundry-tools/
1Через Skills CLI (Vercel)
npx skills add MicrosoftDocs/Agent-Skills --skill microsoft-foundry-tools -a codex2Вручную: положить файлы
.agents/skills/microsoft-foundry-tools/SKILL.mdДля всех проектов — ~/.agents/skills/
1Через Skills CLI (Vercel)
npx skills add MicrosoftDocs/Agent-Skills --skill microsoft-foundry-tools -a cursor2Вручную: положить файлы
.cursor/skills/microsoft-foundry-tools/SKILL.mdCursor читает и .agents/skills/, и .claude/skills/
1GitHub CLI
gh skill install MicrosoftDocs/Agent-Skills skills/microsoft-foundry-tools2Вручную: положить файлы
.github/skills/microsoft-foundry-tools/SKILL.md1Через Skills CLI (Vercel)
npx skills add MicrosoftDocs/Agent-Skills --skill microsoft-foundry-tools -a gemini-cli2Командой платформы
gemini skills install https://github.com/MicrosoftDocs/Agent-Skills --path skills/microsoft-foundry-toolsВручную: положить файлы
.devin/skills/microsoft-foundry-tools/SKILL.mdСтарый путь .windsurf/skills/ тоже читается
Через Skills CLI (Vercel)
npx skills add MicrosoftDocs/Agent-Skills --skill microsoft-foundry-tools -a opencodeClaude.ai
Упакуйте папку в zip и загрузите в Settings → Capabilities → Skills
По шагам, с командами для каждой платформы: Как установить скилл в Claude Code: пять способов
Вопросы о microsoft-foundry-tools
Как установить microsoft-foundry-tools в Claude Code?
Выполни команду npx skills add MicrosoftDocs/Agent-Skills --skill microsoft-foundry-tools -a claude-code. После установки скилл будет доступен в ~/.claude/skills/microsoft-foundry-tools/SKILL.md.
Что делает microsoft-foundry-tools?
Даёт экспертные советы по разработке с Azure AI services: выбор инструмента, архитектура, настройка анализаторов, работа с API, безопасность, лимиты. Помогает с Content Moderator, Content Safety и Content Understanding.
Когда использовать Content Moderator вместо Content Understanding?
Content Moderator — для модерации текста, изображений и видео. Content Understanding — для извлечения структурированных данных из документов. Скилл поможет выбрать на основе твоей задачи и провести миграцию, если нужно.
Исходный текст
SKILL.md · CC-BY-4.0
--- name: microsoft-foundry-tools description: Expert knowledge for Microsoft Foundry Tools (aka Azure AI services, Azure Cognitive Services) development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, and integrations & coding patterns. Use when using Content Moderator, Content Safety, Content Understanding analyzers, REST/.NET APIs, or document extraction workloads, and other Microsoft Foundry Tools related development tasks. Not for Microsoft Foundry (use microsoft-foundry), Microsoft Foundry Classic (use microsoft-foundry-classic), Microsoft Foundry Local (use microsoft-foundry-local). compatibility: Requires network access. Uses mcp_microsoftdocs:microsoft_docs_fetch or fetch_webpage to retrieve documentation. metadata: generated_at: "2026-06-28" generator: "docs2skills/1.0.0" --- # Microsoft Foundry Tools Skill This skill provides expert guidance for Microsoft Foundry Tools. Covers troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, and integrations & coding patterns. It combines local quick-reference content with remote documentation fetching capabilities. ## How to Use This Skill > **IMPORTANT for Agent**: Use the **Category Index** below to locate relevant sections. For categories with line ranges (e.g., `L35-L120`), use `read_file` with the specified lines. For categories with file links (e.g., `[security.md](security.md)`), use `read_file` on the linked reference file > **IMPORTANT for Agent**: If `metadata.generated_at` is more than 3 months old, suggest the user pull the latest version from the repository. If `mcp_microsoftdocs` tools are not available, suggest the user install it: [Installation Guide](https://github.com/MicrosoftDocs/mcp/blob/main/README.md) This skill requires **network access** to fetch documentation content: - **Preferred**: Use `mcp_microsoftdocs:microsoft_docs_fetch` with query string `from=learn-agent-skill`. Returns Markdown. - **Fallback**: Use `fetch_webpage` with query string `from=learn-agent-skill&accept=text/markdown`. Returns Markdown. ## Category Index | Category | Lines | Description | |----------|-------|-------------| | Troubleshooting | L36-L40 | Troubleshooting steps and FAQs for Content Understanding features, including diagnosing model issues, configuration problems, and resolving common errors in content analysis workflows. | | Best Practices | L41-L46 | Guidance on improving Content Understanding accuracy, grounding and confidence in document extraction, and migrating from preview to GA Content Understanding APIs. | | Decision Making | L47-L55 | Guidance for choosing and migrating between Azure AI/Foundry content tools (Content Moderator, Content Safety, Content Understanding), including feature comparisons and pricing/usage planning. | | Architecture & Design Patterns | L56-L60 | Guidance on choosing and configuring deployment options (serverless, managed, custom) for Content Understanding models, including trade-offs, scalability, and integration patterns. | | Limits & Quotas | L61-L68 | Quotas, limits, and supported languages for Content Moderator image/list APIs and Content Understanding, plus .NET samples showing how to stay within list and usage limits. | | Security | L69-L73 | Securing Azure Content Understanding analyzers and data: auth options, network isolation, encryption, access control, and best practices for protecting analyzer inputs/outputs. | | Configuration | L74-L83 | Configuring and customizing Content Understanding analyzers (prebuilt and custom), document layout, face detection, and cross-resource capacity settings. | | Integrations & Coding Patterns | L84-L98 | Using Content Moderator and Content Understanding via REST/.NET: text/image/video moderation, term lists, multimodal analysis, and consuming Markdown/structured outputs | ### Troubleshooting | Topic | URL | |-------|-----| | Troubleshoot and answer FAQs for Content Understanding | https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/faq | ### Best Practices | Topic | URL | |-------|-----| | Apply best practices for Content Understanding accuracy | https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/concepts/best-practices | | Improve document extraction with confidence and grounding | https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/document/analyzer-improvement | ### Decision Making | Topic | URL | |-------|-----| | Migrate Azure Content Moderator workloads to Content Safety | https://learn.microsoft.com/en-us/azure/ai-services/content-moderator/content-moderator | | Choose Azure AI tools for document processing | https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/choosing-right-ai-tool | | Choose between Foundry and Content Understanding Studio features | https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/foundry-vs-content-understanding-studio | | Migrate Content Understanding from preview to GA APIs | https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/how-to/migration-preview-to-ga | | Estimate and plan Content Understanding pricing | https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/pricing-explainer | ### Architecture & Design Patterns | Topic | URL | |-------|-----| | Select model deployment options for Content Understanding | https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/concepts/models-deployments | ### Limits & Quotas | Topic | URL | |-------|-----| | Use Content Moderator image lists within quota limits | https://learn.microsoft.com/en-us/azure/ai-services/content-moderator/image-lists-quickstart-dotnet | | Use supported languages in Content Moderator API | https://learn.microsoft.com/en-us/azure/ai-services/content-moderator/language-support | | Apply Content Moderator .NET samples with list limits | https://learn.microsoft.com/en-us/azure/ai-services/content-moderator/samples-dotnet | | Content Understanding service quotas and limits reference | https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/service-limits | ### Security | Topic | URL | |-------|-----| | Secure Azure Content Understanding analyzers and data | https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/concepts/secure-communications | ### Configuration | Topic | URL | |-------|-----| | Configure and reference analyzers in Azure Content Understanding | https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/concepts/analyzer-reference | | Use and customize Content Understanding prebuilt analyzers | https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/concepts/prebuilt-analyzers | | Configure document layout analysis with Content Understanding | https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/document/elements | | Configure face detection and recognition in Content Understanding | https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/face/overview | | Configure cross-resource capacity for Content Understanding | https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/how-to/bring-your-own-cross-resource-capacity | | Build and refine custom analyzers in Content Understanding Studio | https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/how-to/customize-analyzer-content-understanding-studio | ### Integrations & Coding Patterns | Topic | URL | |-------|-----| | Content Moderator REST API operations reference | https://learn.microsoft.com/en-us/azure/ai-services/content-moderator/api-reference | | Integrate Content Moderator via .NET client library | https://learn.microsoft.com/en-us/azure/ai-services/content-moderator/client-libraries | | Call Content Moderator image moderation APIs | https://learn.microsoft.com/en-us/azure/ai-services/content-moderator/image-moderation-api | | Call Content Moderator REST APIs from C# samples | https://learn.microsoft.com/en-us/azure/ai-services/content-moderator/samples-rest | | Use .NET SDK term lists with Content Moderator | https://learn.microsoft.com/en-us/azure/ai-services/content-moderator/term-lists-quickstart-dotnet | | Use Content Moderator text moderation APIs | https://learn.microsoft.com/en-us/azure/ai-services/content-moderator/text-moderation-api | | Moderate video content using Content Moderator .NET SDK | https://learn.microsoft.com/en-us/azure/ai-services/content-moderator/video-moderation-api | | Consume Content Understanding document Markdown output | https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/document/markdown | | Call Content Understanding REST API for multimodal data | https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/quickstart/use-rest-api | | Create custom Content Understanding analyzers via REST API | https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/tutorial/create-custom-analyzer | | Extract structured audiovisual content with Content Understanding | https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/video/elements | | Use audiovisual Markdown output from Content Understanding | https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/video/markdown |
© MicrosoftDocs · CC-BY-4.0 · MicrosoftDocs/Agent-Skills