[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M73F1NYZ8HQAXAW9AXAK5MV8":3,"skill-same:01M73F1NYZ8HQAXAW9AXAK5MV8":65},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":27,"commitSha":28,"skillDirectory":29,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":33,"ownerDescription":6,"updatedAt":34,"install":35,"resources":48},"01M73F1NYZ8HQAXAW9AXAK5MV8","deploy-model",null,"Unified Azure OpenAI model deployment skill with intelligent intent-based routing. Handles quick preset deployments, fully customized deployments (version\u002FSKU\u002Fcapacity\u002FRAI policy), and capacity discovery across regions and projects. USE FOR: deploy model, deploy gpt, create deployment, model deployment, deploy openai model, set up model, provision model, find capacity, check model availability, where can I deploy, best region for model, capacity analysis. DO NOT USE FOR: listing existing deployments (use foundry_models_deployments_list MCP tool), deleting deployments, agent creation (use agent\u002Fcreate), project creation (use project\u002Fcreate).","qhjqhj00\u002Fresearch-skills-pool","qhjqhj00","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F29684092?v=4","01M72AE0ZGXVM5C57N512DGQG8","Tommy Chien","01M72AE107ESJMHT7QC5SXX144",3,"MIT","https:\u002F\u002Fgithub.com\u002Fqhjqhj00\u002Fresearch-skills-pool\u002Fblob\u002Fmaster\u002Fskills_collected\u002Fmicrosoft--skills--.github__plugins__azure-skills__skills__microsoft-foundry\u002Fmodels\u002Fdeploy-model\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: deploy-model\ndescription: \"Unified Azure OpenAI model deployment skill with intelligent intent-based routing. Handles quick preset deployments, fully customized deployments (version\u002FSKU\u002Fcapacity\u002FRAI policy), and capacity discovery across regions and projects. USE FOR: deploy model, deploy gpt, create deployment, model deployment, deploy openai model, set up model, provision model, find capacity, check model availability, where can I deploy, best region for model, capacity analysis. DO NOT USE FOR: listing existing deployments (use foundry_models_deployments_list MCP tool), deleting deployments, agent creation (use agent\u002Fcreate), project creation (use project\u002Fcreate).\"\nlicense: MIT\nmetadata:\n  author: Microsoft\n  version: \"1.0.0\"\n---\n\n# Deploy Model\n\nUnified entry point for all Azure OpenAI model deployment workflows. Analyzes user intent and routes to the appropriate deployment mode.\n\n## Quick Reference\n\n| Mode | When to Use | Sub-Skill |\n|------|-------------|-----------|\n| **Preset** | Quick deployment, no customization needed | [preset\u002FSKILL.md](preset\u002FSKILL.md) |\n| **Customize** | Full control: version, SKU, capacity, RAI policy | [customize\u002FSKILL.md](customize\u002FSKILL.md) |\n| **Capacity Discovery** | Find where you can deploy with specific capacity | [capacity\u002FSKILL.md](capacity\u002FSKILL.md) |\n\n## Intent Detection\n\nAnalyze the user's prompt and route to the correct mode:\n\n```\nUser Prompt\n    │\n    ├─ Simple deployment (no modifiers)\n    │  \"deploy gpt-4o\", \"set up a model\"\n    │  └─> PRESET mode\n    │\n    ├─ Customization keywords present\n    │  \"custom settings\", \"choose version\", \"select SKU\",\n    │  \"set capacity to X\", \"configure content filter\",\n    │  \"PTU deployment\", \"with specific quota\"\n    │  └─> CUSTOMIZE mode\n    │\n    ├─ Capacity\u002Favailability query\n    │  \"find where I can deploy\", \"check capacity\",\n    │  \"which region has X capacity\", \"best region for 10K TPM\",\n    │  \"where is this model available\"\n    │  └─> CAPACITY DISCOVERY mode\n    │\n    └─ Ambiguous (has capacity target + deploy intent)\n       \"deploy gpt-4o with 10K capacity to best region\"\n       └─> CAPACITY DISCOVERY first → then PRESET or CUSTOMIZE\n```\n\n### Routing Rules\n\n| Signal in Prompt | Route To | Reason |\n|------------------|----------|--------|\n| Just model name, no options | **Preset** | User wants quick deployment |\n| \"custom\", \"configure\", \"choose\", \"select\" | **Customize** | User wants control |\n| \"find\", \"check\", \"where\", \"which region\", \"available\" | **Capacity** | User wants discovery |\n| Specific capacity number + \"best region\" | **Capacity → Preset** | Discover then deploy quickly |\n| Specific capacity number + \"custom\" keywords | **Capacity → Customize** | Discover then deploy with options |\n| \"PTU\", \"provisioned throughput\" | **Customize** | PTU requires SKU selection |\n| \"optimal region\", \"best region\" (no capacity target) | **Preset** | Region optimization is preset's specialty |\n\n### Multi-Mode Chaining\n\nSome prompts require two modes in sequence:\n\n**Pattern: Capacity → Deploy**\nWhen a user specifies a capacity requirement AND wants deployment:\n1. Run **Capacity Discovery** to find regions\u002Fprojects with sufficient quota\n2. Present findings to user\n3. Ask: \"Would you like to deploy with **quick defaults** or **customize settings**?\"\n4. Route to **Preset** or **Customize** based on answer\n\n> 💡 **Tip:** If unsure which mode the user wants, default to **Preset** (quick deployment). Users who want customization will typically use explicit keywords like \"custom\", \"configure\", or \"with specific settings\".\n\n## Project Selection (All Modes)\n\nBefore any deployment, resolve which project to deploy to. This applies to **all** modes (preset, customize, and after capacity discovery).\n\n### Resolution Order\n\n1. **Check `PROJECT_RESOURCE_ID` env var** — if set, use it as the default\n2. **Check user prompt** — if user named a specific project or region, use that\n3. **If neither** — query the user's projects and suggest the current one\n\n### Confirmation Step (Required)\n\n**Always confirm the target before deploying.** Show the user what will be used and give them a chance to change it:\n\n```\nDeploying to:\n  Project:  \u003Cproject-name>\n  Region:   \u003Cregion>\n  Resource: \u003Cresource-group>\n\nIs this correct? Or choose a different project:\n  1. ✅ Yes, deploy here (default)\n  2. 📋 Show me other projects in this region\n  3. 🌍 Choose a different region\n```\n\nIf user picks option 2, show top 5 projects in that region:\n\n```\nProjects in \u003Cregion>:\n  1. project-alpha (rg-alpha)\n  2. project-beta (rg-beta)\n  3. project-gamma (rg-gamma)\n  ...\n```\n\n> ⚠️ **Never deploy without showing the user which project will be used.** This prevents accidental deployments to the wrong resource.\n\n## Pre-Deployment Validation (All Modes)\n\nBefore presenting any deployment options (SKU, capacity), always validate both of these:\n\n1. **Model supports the SKU** — query the model catalog to confirm the selected model+version supports the target SKU:\n   ```bash\n   az cognitiveservices model list --location \u003Cregion> --subscription \u003Csub-id> -o json\n   ```\n   Filter for the model, extract `.model.skus[].name` to get supported SKUs.\n\n2. **Subscription has available quota** — check that the user's subscription has unallocated quota for the SKU+model combination:\n   ```bash\n   az cognitiveservices usage list --location \u003Cregion> --subscription \u003Csub-id> -o json\n   ```\n   Match by usage name pattern `OpenAI.\u003CSKU>.\u003Cmodel-name>` (e.g., `OpenAI.GlobalStandard.gpt-4o`). Compute `available = limit - currentValue`.\n\n> ⚠️ **Warning:** Only present options that pass both checks. Do NOT show hardcoded SKU lists — always query dynamically. SKUs with 0 available quota should be shown as ❌ informational items, not selectable options.\n\n> 💡 **Quota management:** For quota increase requests, usage monitoring, and troubleshooting quota errors, defer to the [quota skill](..\u002F..\u002Fquota\u002Fquota.md) instead of duplicating that guidance inline.\n\n## Prerequisites\n\nAll deployment modes require:\n- Azure CLI installed and authenticated (`az login`)\n- Active Azure subscription with deployment permissions\n- Azure AI Foundry project resource ID (or agent will help discover it via `PROJECT_RESOURCE_ID` env var)\n\n## Sub-Skills\n\n- **[preset\u002FSKILL.md](preset\u002FSKILL.md)** — Quick deployment to optimal region with sensible defaults\n- **[customize\u002FSKILL.md](customize\u002FSKILL.md)** — Interactive guided flow with full configuration control\n- **[capacity\u002FSKILL.md](capacity\u002FSKILL.md)** — Discover available capacity across regions and projects\n","# Deploy Model\n\nUnified entry point for all Azure OpenAI model deployment workflows. Analyzes user intent and routes to the appropriate deployment mode.\n\n## Quick Reference\n\n| Mode | When to Use | Sub-Skill |\n|------|-------------|-----------|\n| **Preset** | Quick deployment, no customization needed | [preset\u002FSKILL.md](preset\u002FSKILL.md) |\n| **Customize** | Full control: version, SKU, capacity, RAI policy | [customize\u002FSKILL.md](customize\u002FSKILL.md) |\n| **Capacity Discovery** | Find where you can deploy with specific capacity | [capacity\u002FSKILL.md](capacity\u002FSKILL.md) |\n\n## Intent Detection\n\nAnalyze the user's prompt and route to the correct mode:\n\n```\nUser Prompt\n    │\n    ├─ Simple deployment (no modifiers)\n    │  \"deploy gpt-4o\", \"set up a model\"\n    │  └─> PRESET mode\n    │\n    ├─ Customization keywords present\n    │  \"custom settings\", \"choose version\", \"select SKU\",\n    │  \"set capacity to X\", \"configure content filter\",\n    │  \"PTU deployment\", \"with specific quota\"\n    │  └─> CUSTOMIZE mode\n    │\n    ├─ Capacity\u002Favailability query\n    │  \"find where I can deploy\", \"check capacity\",\n    │  \"which region has X capacity\", \"best region for 10K TPM\",\n    │  \"where is this model available\"\n    │  └─> CAPACITY DISCOVERY mode\n    │\n    └─ Ambiguous (has capacity target + deploy intent)\n       \"deploy gpt-4o with 10K capacity to best region\"\n       └─> CAPACITY DISCOVERY first → then PRESET or CUSTOMIZE\n```\n\n### Routing Rules\n\n| Signal in Prompt | Route To | Reason |\n|------------------|----------|--------|\n| Just model name, no options | **Preset** | User wants quick deployment |\n| \"custom\", \"configure\", \"choose\", \"select\" | **Customize** | User wants control |\n| \"find\", \"check\", \"where\", \"which region\", \"available\" | **Capacity** | User wants discovery |\n| Specific capacity number + \"best region\" | **Capacity → Preset** | Discover then deploy quickly |\n| Specific capacity number + \"custom\" keywords | **Capacity → Customize** | Discover then deploy with options |\n| \"PTU\", \"provisioned throughput\" | **Customize** | PTU requires SKU selection |\n| \"optimal region\", \"best region\" (no capacity target) | **Preset** | Region optimization is preset's specialty |\n\n### Multi-Mode Chaining\n\nSome prompts require two modes in sequence:\n\n**Pattern: Capacity → Deploy**\nWhen a user specifies a capacity requirement AND wants deployment:\n1. Run **Capacity Discovery** to find regions\u002Fprojects with sufficient quota\n2. Present findings to user\n3. Ask: \"Would you like to deploy with **quick defaults** or **customize settings**?\"\n4. Route to **Preset** or **Customize** based on answer\n\n> 💡 **Tip:** If unsure which mode the user wants, default to **Preset** (quick deployment). Users who want customization will typically use explicit keywords like \"custom\", \"configure\", or \"with specific settings\".\n\n## Project Selection (All Modes)\n\nBefore any deployment, resolve which project to deploy to. This applies to **all** modes (preset, customize, and after capacity discovery).\n\n### Resolution Order\n\n1. **Check `PROJECT_RESOURCE_ID` env var** — if set, use it as the default\n2. **Check user prompt** — if user named a specific project or region, use that\n3. **If neither** — query the user's projects and suggest the current one\n\n### Confirmation Step (Required)\n\n**Always confirm the target before deploying.** Show the user what will be used and give them a chance to change it:\n\n```\nDeploying to:\n  Project:  \u003Cproject-name>\n  Region:   \u003Cregion>\n  Resource: \u003Cresource-group>\n\nIs this correct? Or choose a different project:\n  1. ✅ Yes, deploy here (default)\n  2. 📋 Show me other projects in this region\n  3. 🌍 Choose a different region\n```\n\nIf user picks option 2, show top 5 projects in that region:\n\n```\nProjects in \u003Cregion>:\n  1. project-alpha (rg-alpha)\n  2. project-beta (rg-beta)\n  3. project-gamma (rg-gamma)\n  ...\n```\n\n> ⚠️ **Never deploy without showing the user which project will be used.** This prevents accidental deployments to the wrong resource.\n\n## Pre-Deployment Validation (All Modes)\n\nBefore presenting any deployment options (SKU, capacity), always validate both of these:\n\n1. **Model supports the SKU** — query the model catalog to confirm the selected model+version supports the target SKU:\n   ```bash\n   az cognitiveservices model list --location \u003Cregion> --subscription \u003Csub-id> -o json\n   ```\n   Filter for the model, extract `.model.skus[].name` to get supported SKUs.\n\n2. **Subscription has available quota** — check that the user's subscription has unallocated quota for the SKU+model combination:\n   ```bash\n   az cognitiveservices usage list --location \u003Cregion> --subscription \u003Csub-id> -o json\n   ```\n   Match by usage name pattern `OpenAI.\u003CSKU>.\u003Cmodel-name>` (e.g., `OpenAI.GlobalStandard.gpt-4o`). Compute `available = limit - currentValue`.\n\n> ⚠️ **Warning:** Only present options that pass both checks. Do NOT show hardcoded SKU lists — always query dynamically. SKUs with 0 available quota should be shown as ❌ informational items, not selectable options.\n\n> 💡 **Quota management:** For quota increase requests, usage monitoring, and troubleshooting quota errors, defer to the [quota skill](..\u002F..\u002Fquota\u002Fquota.md) instead of duplicating that guidance inline.\n\n## Prerequisites\n\nAll deployment modes require:\n- Azure CLI installed and authenticated (`az login`)\n- Active Azure subscription with deployment permissions\n- Azure AI Foundry project resource ID (or agent will help discover it via `PROJECT_RESOURCE_ID` env var)\n\n## Sub-Skills\n\n- **[preset\u002FSKILL.md](preset\u002FSKILL.md)** — Quick deployment to optimal region with sensible defaults\n- **[customize\u002FSKILL.md](customize\u002FSKILL.md)** — Interactive guided flow with full configuration control\n- **[capacity\u002FSKILL.md](capacity\u002FSKILL.md)** — Discover available capacity across regions and projects\n",{"name":5,"license":15,"metadata":24,"description":7},{"author":25,"version":26},"Microsoft","1.0.0","master","c247302c836de6438d746b45670990eb71691166","skills_collected\u002Fmicrosoft--skills--.github__plugins__azure-skills__skills__microsoft-foundry\u002Fmodels\u002Fdeploy-model",1,"https:\u002F\u002Fgithub.com\u002Fqhjqhj00\u002Fresearch-skills-pool","https:\u002F\u002Fgithub.com\u002Fqhjqhj00","chien.io","2026-05-11 15:07:59",{"source":8,"skillName":5,"commands":36,"prompt":46,"zipAvailable":47},[37,40,43],{"tool":38,"command":39},"npx","npx skills add qhjqhj00\u002Fresearch-skills-pool --skill deploy-model",{"tool":41,"command":42},"bunx","bunx skills add qhjqhj00\u002Fresearch-skills-pool --skill deploy-model",{"tool":44,"command":45},"pnpm","pnpm dlx skills add qhjqhj00\u002Fresearch-skills-pool --skill deploy-model","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fqhjqhj00\u002Fresearch-skills-pool\u002Fblob\u002Fmaster\u002Fskills_collected\u002Fmicrosoft--skills--.github__plugins__azure-skills__skills__microsoft-foundry\u002Fmodels\u002Fdeploy-model\u002FSKILL.md",true,[49,55,59],{"path":50,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":53,"sourceHtmlUrl":54},"scripts\u002Fgenerate_deployment_url.ps1","SCRIPT","脚本",2368,"https:\u002F\u002Fgithub.com\u002Fqhjqhj00\u002Fresearch-skills-pool\u002Fblob\u002Fmaster\u002Fskills_collected\u002Fmicrosoft--skills--.github__plugins__azure-skills__skills__microsoft-foundry\u002Fmodels\u002Fdeploy-model\u002Fscripts\u002Fgenerate_deployment_url.ps1",{"path":56,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":57,"sourceHtmlUrl":58},"scripts\u002Fgenerate_deployment_url.sh",2684,"https:\u002F\u002Fgithub.com\u002Fqhjqhj00\u002Fresearch-skills-pool\u002Fblob\u002Fmaster\u002Fskills_collected\u002Fmicrosoft--skills--.github__plugins__azure-skills__skills__microsoft-foundry\u002Fmodels\u002Fdeploy-model\u002Fscripts\u002Fgenerate_deployment_url.sh",{"path":60,"resourceType":61,"resourceTypeDesc":62,"sizeBytes":63,"sourceHtmlUrl":64},"TEST_PROMPTS.md","REFERENCE","参考文档",3367,"https:\u002F\u002Fgithub.com\u002Fqhjqhj00\u002Fresearch-skills-pool\u002Fblob\u002Fmaster\u002Fskills_collected\u002Fmicrosoft--skills--.github__plugins__azure-skills__skills__microsoft-foundry\u002Fmodels\u002Fdeploy-model\u002FTEST_PROMPTS.md",[66,73,80,87,94,101],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":19},"01M73JJB6EQPFPPVQK2Y9N67Q0","transformer-lens-interpretability","Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation caching. Use when reverse-engineering model algorithms, studying attention patterns, or performing activation patching experiments.","https:\u002F\u002Fgithub.com\u002Fqhjqhj00\u002Fresearch-skills-pool\u002Fblob\u002Fmaster\u002Ftop100-runs\u002F130-transformer-lens\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":19},"01M73JHTANRRWEE9HP98TPEHAY","wiki-vitepress","Packages generated wiki Markdown into a VitePress static site with dark theme, dark-mode Mermaid diagrams with click-to-zoom, and production build output. Use when the user wants to create a browsable website from generated wiki pages.","https:\u002F\u002Fgithub.com\u002Fqhjqhj00\u002Fresearch-skills-pool\u002Fblob\u002Fmaster\u002Ftop100-runs\u002F126-wiki-vitepress\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":19},"01M73JHJBMVFW46F1Y8K3SBF43","phoenix-observability","Open-source AI observability platform for LLM tracing, evaluation, and monitoring. Use when debugging LLM applications with detailed traces, running evaluations on datasets, or monitoring production AI systems with real-time insights.","https:\u002F\u002Fgithub.com\u002Fqhjqhj00\u002Fresearch-skills-pool\u002Fblob\u002Fmaster\u002Ftop100-runs\u002F124-phoenix\u002FSKILL.md",[],[],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":19},"01M73JHFPA3A2806PMP42ZN86Q","frontend-ui-dark-ts","Build dark-themed React applications using Tailwind CSS with custom theming, glassmorphism effects, and Framer Motion animations. Use when creating dashboards, admin panels, or data-rich interfaces with a refined dark aesthetic.","https:\u002F\u002Fgithub.com\u002Fqhjqhj00\u002Fresearch-skills-pool\u002Fblob\u002Fmaster\u002Ftop100-runs\u002F123-frontend-ui-dark-ts\u002FSKILL.md",[],[],{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":19},"01M73JFVBVK57NRJS49TT2VDCT","tensorboard","Visualize training metrics, debug models with histograms, compare experiments, visualize model graphs, and profile performance with TensorBoard - Google's ML visualization toolkit","https:\u002F\u002Fgithub.com\u002Fqhjqhj00\u002Fresearch-skills-pool\u002Fblob\u002Fmaster\u002Ftop100-runs\u002F113-tensorboard\u002FSKILL.md",[],[],{"skillNo":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":105,"licenseFileUrl":6,"sourceHtmlUrl":106,"categories":107,"keywords":108,"publishedAt":19},"01M73JFF6PK6ZCN41C89J7HS2B","markdown-mermaid-writing","Comprehensive markdown and Mermaid diagram writing skill. Use when creating any scientific document, report, analysis, or visualization. Establishes text-based diagrams as the default documentation standard with full style guides (markdown + mermaid), 24 diagram type references, and 9 document templates.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fqhjqhj00\u002Fresearch-skills-pool\u002Fblob\u002Fmaster\u002Ftop100-runs\u002F110-markdown-mermaid-writing\u002FSKILL.md",[],[]]