When given an issue instead of a run, find the related issue-triage run first. Resolve the issue title and number, then match the run display title: Use the newest matching run. An issue-triage run can contain both the triage and bug-reproduction threads. Also check for directly dispatched bug-reproduction runs; their display title does not include the issue title. If the issue title changed or a run was manually dispatched, list recent candidates and confirm them from their logs: When given…
Bootstrap a new realtime eval folder inside this cookbook repo by choosing the right harness from examples/evals/realtime_evals, scaffolding prompt/tools/data files, generating a useful README, and validating it with smoke, full eval, and test runs. Use when a user wants to start a new crawl, walk, or run realtime eval in this repository.
Take a working agent prototype to a scalable, observable production deployment on Microsoft Foundry. Covers deployment patterns (client-hosted, hosted agents, agent workflows), the agent lifecycle, model routing, response caching, evaluation gates, human-in-the-loop approval, observability with OpenTelemetry, cost optimisation, and smoke-testing deployed agents with the AI Smoke Test action. Based on Lesson 16 of AI Agents for Beginners. USE FOR: deploy an agent to production, scale an agent, Microsoft Foundry hosted agent, Foundry Agent Service, model routing, response caching, evaluation gate, release gate, human approval workflow, agent observability, agent tracing, agent cost optimisation, smoke test a hosted agent, production customer support agent. DO NOT USE FOR: building your first agent (start with Lesson 01), running agents locally on-device (use local-ai-agents / Lesson 17), Azure infrastructure provisioning unrelated to agents, non-Foundry deployment targets.
Use when the user asks to create, scaffold, or edit Jupyter notebooks (`.ipynb`) for experiments, explorations, or tutorials; prefer the bundled templates and run the helper script `new_notebook.py` to generate a clean starting notebook.
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the privacy/cost/offline trade-offs. Based on Lesson 17 of AI Agents for Beginners. USE FOR: run an agent locally, offline agent, on-device agent, Foundry Local, Qwen function calling, local tool calling, local RAG, Chroma vector database, local MCP server, privacy-preserving agent, hybrid local and cloud agent, small language model agent, engineering assistant on my machine. DO NOT USE FOR: deploying agents to the cloud at scale (use deploying-scalable-agents / Lesson 16), building your first agent concept (Lesson 01), Foundry (cloud) hosted agents, GPU cluster / server-side inference provisioning.
Query official Microsoft documentation to find concepts, tutorials, and code examples across Azure, .NET, Agent Framework, Aspire, VS Code, GitHub, and more. Uses Microsoft Learn MCP as the default, with Context7 and Aspire MCP for content that lives outside learn.microsoft.com.
مهارة مرافق لدروس الدرس 16 – نشر عوامل قابلة للتوسع. استخدمها لمساعدة المتعلم على نقل وكيل من النموذج الأولي إلى نشر إنتاجي قابل للتوسع وقابل للملاحظة. استند إلى كل توصية على محتوى الدرس ودفتر الملاحظات القابل للتشغيل؛ لا تخترع واجهات برمجة تطبيقات Foundry. فعّل هذه المهارة عندما يرغب المتعلم في: - نشر وكيل على Microsoft Foundry كـ وكيل مستضاف وجعله قابلًا للإصدار والملاحظة. - الاختيار بين أنماط النشر المستضافة على العميل، الوكيل المستضاف، وتدفق عمل الوكيل. - إضافة توجيه النموذج،…
مهارة مرافقة لـ الدرس 17 – إنشاء وكلاء ذكاء اصطناعي محليين. استخدمها لمساعدة المتعلم في بناء وكيل يستدعي أدوات، ويبحث في التوثيق بالكامل على جهازه الخاص — بدون استدلال سحابي. استند على كل توصية في محتوى الدرس والدفتر التفاعلي القابل للتشغيل. قم بتنشيط هذه المهارة عندما يريد المتعلم: - تشغيل وكيل كاملًا على الجهاز لأسباب تتعلق بالخصوصية، أو التكلفة، أو عدم الاتصال بالإنترنت. - تقديم نموذج محلي باستخدام Foundry Local والاتصال عبر نقطة نهاية متوافقة مع OpenAI. - استخدام نموذج…
Придружаващо умение за Урок 16 – Разгръщане на мащабируеми агенти. Използвайте го, за да помогнете на учащия да премести агент от прототип към мащабируема, наблюдаема производствена среда. Всяка препоръка трябва да се основава на съдържанието на урока и изпълнимия тетрадка; не измисляйте API-та на Foundry. Активирайте това умение, когато учащ иска да: - Разгърне агент в Microsoft Foundry като хостиран агент и да го направи версиониран/наблюдаем. - Избере между модели за разгръщане клиент-хостиран, хостиран агент и агент-работен поток. - Добави…
Спомагателно умение за Урок 17 – Създаване на локални AI агенти. Използвайте го, за да помогнете на учащия да създаде агент, който разсъждава, извиква инструменти и търси документиране изцяло на собствената му машина — без облачно осмисляне. Всяка препоръка се основава на съдържанието на урока и изпълнимия бележник. Активирайте това умение, когато учащ иска да: - Стартира агент изцяло на устройството по причини за поверителност, разходи или офлайн работа. - Служи на модел локално с Foundry Local и да се…
Lesson 16 – Deploying Scalable Agents এর সঙ্গী দক্ষতা। এটি ব্যবহার করে একজন শেখার্থীকে সাহায্য করুন একটি এজেন্টকে প্রোটোটাইপ থেকে এক স্কেলযোগ্য, পর্যবেক্ষণযোগ্য প্রোডাকশন ডেপ্লয়মেন্টে স্থানান্তর করতে। প্রতিটি সুপারিশ পাঠের বিষয়বস্তু এবং চালানোর যোগ্য নোটবুকের উপর ভিত্তি করে রাখুন; ফাউন্ড্রি API উদ্ভাবন করবেন না। যখন একজন শেখার্থী করতে চান তখন এই দক্ষতা সক্রিয় করুন: - মাইক্রোসফট ফাউন্ড্রিতে একটি এজেন্টকে হোস্টেড এজেন্ট হিসেবে মোতায়েন করা এবং সেটিকে ভার্সান/পর্যবেক্ষণযোগ্য করা। - ক্লায়েন্ট-হোস্টেড, হোস্টেড-এজেন্ট, এবং এজেন্ট-ওয়ার্কফ্লো মোতায়েন প্যাটার্নগুলোর মধ্যে নির্বাচন করা। - মডেল…
Microsoft প্রযুক্তি ইকোসিস্টেমের জন্য গবেষণা দক্ষতা। Covers learn.microsoft.com and documentation that lives outside it (VS Code, GitHub, Aspire, Agent Framework repos). Use these tools for everything on learn.microsoft.com — Azure, .NET, M365, Power Platform, Agent Framework, Semantic Kernel, Windows, and more. এটি Microsoft ডকুমেন্টেশন সম্পর্কিত অধিকাংশ অনুসন্ধানের জন্য প্রধান টুল। Search করার পরে যখন আপনাকে সম্পূর্ণ টিউটোরিয়াল, সমস্ত কনফিগ অপশন, বা যখন সার্চ এক্সসার্প্ট কাটা হয় তখন microsoftdocsfetch ব্যবহার করুন। নিচের ক্যাটাগরিগুলো learn.microsoft.com-এর বাইরে অবস্থিত। পরিবর্তে নির্দিষ্ট টুলটি ব্যবহার করুন।
Doplňková dovednost k Lekci 16 – Nasazení škálovatelných agentů. Použijte ji k pomoci studentovi přesunout agenta z prototypu do škálovatelného, pozorovatelného produkčního nasazení. Každé doporučení zakládejte na obsahu lekce a spustitelném notebooku; nevymýšlejte API Foundry. Aktivujte tuto dovednost, když chce student: - Nasadit agenta do Microsoft Foundry jako hostovaného agenta a zajistit jeho verzování/pozorovatelnost. - Vybrat mezi nasazovacími vzory client-hosted, hosted-agent a agent-workflow. - Přidat směrování modelů, cache odpovědí nebo omezenou paralelnost pro kontrolu latence a nákladů. - Přidat evaluační…
A folder with a SKILL.md file: a name, a description of when to use it, and instructions. Claude loads a skill only when the task matches its description.
How do I use one I find here?
Copy the folder into your project's .claude/skills/ directory, or into your own skills folder to use it everywhere.
What do the warnings mean?
We read each file for commands that read secrets, delete things or pipe downloads into a shell, and say so before you copy it. No warning is not a promise that a file is safe.
Which skills worked for people?
Open a skill to see its discussion. Reports from people and their agents are coming.
AstralSkill
