Coordinate supervised Orca workers: threaded messages, blocking ask/reply, task dispatch, worker_done/escalation waits, task DAGs, decision gates, coordinator loops, and decomposing work across agents. Use `orca-cli` for full ownership handoffs — "hand off", "handoff", "handover", "give this to another agent", "another worktree" — unless asked to supervise, monitor, or coordinate a DAG, and for terminal control, lightweight terminal prompts, shell commands, Orca worktree management, and reading or waiting on terminals.
Review and edit OpenAI Cookbook notebooks, Markdown, and MDX for technical accuracy, clarity, grammar, consistency, runnable examples, and repository publication requirements. Use for editorial reviews, pre-merge documentation checks, or notebook Markdown-cell sweeps in openai-cookbook.
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.
Migrate Python apps from Azure OpenAI Chat Completions to the Responses API. Covers AzureOpenAI/AsyncAzureOpenAI client migration to the v1 endpoint, streaming, tools, structured output, multi-turn, EntraID auth, and model compatibility checks. Python-focused, Azure OpenAI-specific. USE FOR: migrate to responses API, switch from chat completions, openai responses, upgrade openai SDK, responses API migration, move from completions to responses, gpt-5 migration, azure openai python migration, chat completions to responses, AzureOpenAI to OpenAI client, python azure openai upgrade. DO NOT USE FOR: building new apps from scratch (start with responses directly), Node/TypeScript/C#/Java/Go migrations (this skill is Python-only), Azure infrastructure setup (use azure-prepare), deploying models (use microsoft-foundry).
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.
Use when asked to validate, test, smoke-test, or run the course's notebook and code samples against a live Microsoft Foundry / Azure OpenAI configuration. Covers environment setup (.env, az login, packages), the scripts/validate-notebooks.ps1 runner, interpreting PASS/FAIL results, and which lessons need extra resources (Azure AI Search, GitHub MCP, Foundry Local, Playwright).
إرشادات موثوقة — اتبع بدقة تقوم هذه المهارة بترحيل قواعد شيفرة بايثون التي تستخدم Azure OpenAI Chat Completions إلى واجهة Responses API الموحدة. اتبع هذه التعليمات بدقة. لا تقم بالتحايل في تعيين المعلمات أو اختراع أشكال API جديدة. فعّل هذه المهارة عندما يرغب المستخدم في: - ترحيل تطبيق بايثون من Azure OpenAI Chat Completions إلى Responses API - ترقية استخدام SDK لبايثون OpenAI إلى أحدث شكل API ضد Azure OpenAI - تجهيز شيفرة بايثون لنماذج GPT-5 أو أحدث التي تتطلب…
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…
تحقق من أن دفاتر الدروس وعينات الشيفرة تعمل ضد إعداد Microsoft Foundry / Azure OpenAI مباشر. يشتمل المستودع على مشغل في scripts/validate-notebooks.ps1 الذي ينفذ كل دفتر ملاحظات بايثون بدون واجهة ويطبع مصفوفة تمر/فشل. لا تستخدم هذا لاختبار AI Smoke Test GitHub Action (الذي يتحقق من العملاء النشرين المستضافين — راجع tests/README.md). تقوم هذه المهارة بتشغيل دفاتر الملاحظات محليًا. تقوم السكربت بكتابة نسخ منفذة، وسجلات لكل دفتر ملاحظات، وresults.json إلى $env:TEMP\aiab-nbval وتخرج بعدد حالات الفشل. يتم إعادة محاولة الإخفاقات المؤقتة (حدود…
АВТОРИТЕТНО РЪКОВОДСТВО — СПАЗВАЙТЕ ТОЧНО Тази функция мигрира Python кодови бази, използващи Azure OpenAI Chat Completions към унифицирания Responses API. Следвайте тези инструкции прецизно. Не импровизирайте с параметрични съпоставяния или измисляйте форми на API. Активирайте тази функция, когато потребителят иска да: - Мигрира Python приложение от Azure OpenAI Chat Completions към Responses API - Обнови употребата на Python OpenAI SDK до последната форма на API спрямо Azure OpenAI - Подготви Python код за модели GPT-5 или по-нови, които изискват Responses…
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…
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.
stablyaiSkill
