[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M69AEF2CB2J9N0F09H5PKDTP":3,"skill-same:01M69AEF2CB2J9N0F09H5PKDTP":67},{"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":22,"linkOnly":23,"markdownContent":24,"markdownBody":25,"frontMatter":26,"refName":29,"commitSha":30,"skillDirectory":31,"forksCount":32,"repositoryHtmlUrl":33,"repositoryHomepageUrl":34,"ownerHtmlUrl":35,"ownerBlogUrl":36,"ownerDescription":37,"updatedAt":38,"install":39,"resources":52},"01M69AEF2CB2J9N0F09H5PKDTP","customize",null,"Interactive guided deployment flow for Azure OpenAI models with full customization control. Step-by-step selection of model version, SKU (GlobalStandard\u002FStandard\u002FProvisionedManaged), capacity, RAI policy (content filter), and advanced options (dynamic quota, priority processing, spillover). USE FOR: custom deployment, customize model deployment, choose version, select SKU, set capacity, configure content filter, RAI policy, deployment options, detailed deployment, advanced deployment, PTU deployment, provisioned throughput. DO NOT USE FOR: quick deployment to optimal region (use preset).","microsoft\u002Ffrontier-ai-governance-rvas","microsoft","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F6154722?v=4","01M698VYDXZ6JW5WH3CRV650R8","Microsoft","01M69AAY34KYZNT0DYKTD5AX5X",1,"MIT","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Ffrontier-ai-governance-rvas\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fmicrosoft-foundry\u002Fmodels\u002Fdeploy-model\u002Fcustomize\u002FSKILL.md",[],[5,19,9,20,21],"policy","capacity","preset","2026-11-10 10:12:30",false,"---\nname: customize\ndescription: \"Interactive guided deployment flow for Azure OpenAI models with full customization control. Step-by-step selection of model version, SKU (GlobalStandard\u002FStandard\u002FProvisionedManaged), capacity, RAI policy (content filter), and advanced options (dynamic quota, priority processing, spillover). USE FOR: custom deployment, customize model deployment, choose version, select SKU, set capacity, configure content filter, RAI policy, deployment options, detailed deployment, advanced deployment, PTU deployment, provisioned throughput. DO NOT USE FOR: quick deployment to optimal region (use preset).\"\nlicense: MIT\nmetadata:\n  author: Microsoft\n  version: \"1.0.1\"\n---\n\n# Customize Model Deployment\n\nInteractive guided workflow for deploying Azure OpenAI models with full customization control over version, SKU, capacity, content filtering, and advanced options.\n\n## Quick Reference\n\n| Property | Description |\n|----------|-------------|\n| **Flow** | Interactive step-by-step guided deployment |\n| **Customization** | Version, SKU, Capacity, RAI Policy, Advanced Options |\n| **SKU Support** | GlobalStandard, Standard, ProvisionedManaged, DataZoneStandard |\n| **Best For** | Precise control over deployment configuration |\n| **Authentication** | Azure CLI (`az login`) |\n| **Tools** | Azure CLI, MCP tools (optional) |\n\n## When to Use This Skill\n\nUse this skill when you need **precise control** over deployment configuration:\n\n- ✅ **Choose specific model version** (not just latest)\n- ✅ **Select deployment SKU** (GlobalStandard vs Standard vs PTU)\n- ✅ **Set exact capacity** within available range\n- ✅ **Configure content filtering** (RAI policy selection)\n- ✅ **Enable advanced features** (dynamic quota, priority processing, spillover)\n- ✅ **PTU deployments** (Provisioned Throughput Units)\n\n**Alternative:** Use `preset` for quick deployment to the best available region with automatic configuration.\n\n### Comparison: customize vs preset\n\n| Feature | customize | preset |\n|---------|---------------------|----------------------------|\n| **Focus** | Full customization control | Optimal region selection |\n| **Version Selection** | User chooses from available | Uses latest automatically |\n| **SKU Selection** | User chooses (GlobalStandard\u002FStandard\u002FPTU) | GlobalStandard only |\n| **Capacity** | User specifies exact value | Auto-calculated (50% of available) |\n| **RAI Policy** | User selects from options | Default policy only |\n| **Region** | Current region first, falls back to all regions if no capacity | Checks capacity across all regions upfront |\n| **Use Case** | Precise deployment requirements | Quick deployment to best region |\n\n## Prerequisites\n\n- Azure subscription with Cognitive Services Contributor or Owner role\n- Microsoft Foundry project resource ID (format: `\u002Fsubscriptions\u002F{sub}\u002FresourceGroups\u002F{rg}\u002Fproviders\u002FMicrosoft.CognitiveServices\u002Faccounts\u002F{account}\u002Fprojects\u002F{project}`)\n- Azure CLI installed and authenticated (`az login`)\n- Optional: Set `PROJECT_RESOURCE_ID` environment variable\n\n## Workflow Overview\n\n### Complete Flow (14 Phases)\n\n```\n1. Verify Authentication\n2. Get Project Resource ID\n3. Verify Project Exists\n4. Get Model Name (if not provided)\n5. List Model Versions → User Selects\n6. List SKUs for Version → User Selects\n7. Get Capacity Range → User Configures\n   7b. If no capacity: Cross-Region Fallback → Query all regions → User selects region\u002Fproject\n8. List RAI Policies → User Selects\n9. Configure Advanced Options (if applicable)\n10. Configure Version Upgrade Policy\n11. Generate Deployment Name\n12. Review Configuration\n13. Execute Deployment & Monitor\n```\n\n### Fast Path (Defaults)\n\nIf user accepts all defaults (latest version, GlobalStandard SKU, recommended capacity, default RAI policy, standard upgrade policy), deployment completes in ~5 interactions.\n\n---\n\n## Phase Summaries\n\n> ⚠️ **MUST READ:** Before executing any phase, load [references\u002Fcustomize-workflow.md](references\u002Fcustomize-workflow.md) for the full scripts and implementation details. The summaries below describe *what* each phase does — the reference file contains the *how* (CLI commands, quota patterns, capacity formulas, cross-region fallback logic).\n\n| Phase | Action | Key Details |\n|-------|--------|-------------|\n| **1. Verify Auth** | Check `az account show`; prompt `az login` if needed | Verify correct subscription is active |\n| **2. Get Project ID** | Read `PROJECT_RESOURCE_ID` env var or prompt user | ARM resource ID format required |\n| **3. Verify Project** | Parse resource ID, call `az cognitiveservices account show` | Extracts subscription, RG, account, project, region |\n| **4. Get Model** | List models via `az cognitiveservices account list-models` | User selects from available or enters custom name |\n| **5. Select Version** | Query versions for chosen model | Recommend latest; user picks from list |\n| **6. Select SKU** | Query model catalog + subscription quota, show only deployable SKUs | ⚠️ Never hardcode SKU lists — always query live data |\n| **7. Configure Capacity** | Query capacity API, validate min\u002Fmax\u002Fstep, user enters value | Cross-region fallback if no capacity in current region |\n| **8. Select RAI Policy** | Present content filter options | Default: `Microsoft.DefaultV2` |\n| **9. Advanced Options** | Dynamic quota (GlobalStandard), priority processing (PTU), spillover | SKU-dependent availability |\n| **10. Upgrade Policy** | Choose: OnceNewDefaultVersionAvailable \u002F OnceCurrentVersionExpired \u002F NoAutoUpgrade | Default: auto-upgrade on new default |\n| **11. Deployment Name** | Auto-generate unique name, allow custom override | Validates format: `^[\\w.-]{2,64}$` |\n| **12. Review** | Display full config summary, confirm before proceeding | User approves or cancels |\n| **13. Deploy & Monitor** | `az cognitiveservices account deployment create`, poll status | Timeout after 5 min; show endpoint + portal link |\n\n\n---\n\n## Error Handling\n\n### Common Issues and Resolutions\n\n| Error | Cause | Resolution |\n|-------|-------|------------|\n| **Model not found** | Invalid model name | List available models with `az cognitiveservices account list-models` |\n| **Version not available** | Version not supported for SKU | Select different version or SKU |\n| **Insufficient quota** | Capacity > available quota | Skill auto-searches all regions; fails only if no region has quota |\n| **SKU not supported** | SKU not available in region | Cross-region fallback searches other regions automatically |\n| **Capacity out of range** | Invalid capacity value | **PREVENTED**: Skill validates min\u002Fmax\u002Fstep at input (Phase 7) |\n| **Deployment name exists** | Name conflict | Auto-incremented name generation |\n| **Authentication failed** | Not logged in | Run `az login` |\n| **Permission denied** | Insufficient permissions | Assign Cognitive Services Contributor role |\n| **Capacity query fails** | API\u002Fpermissions\u002Fnetwork error | **DEPLOYMENT BLOCKED**: Will not proceed without valid quota data |\n\n### Troubleshooting Commands\n\n```bash\n# Check deployment status\naz cognitiveservices account deployment show --name \u003Caccount> --resource-group \u003Crg> --deployment-name \u003Cname>\n\n# List all deployments\naz cognitiveservices account deployment list --name \u003Caccount> --resource-group \u003Crg> -o table\n\n# Check quota usage\naz cognitiveservices usage list --name \u003Caccount> --resource-group \u003Crg>\n\n# Delete failed deployment\naz cognitiveservices account deployment delete --name \u003Caccount> --resource-group \u003Crg> --deployment-name \u003Cname>\n```\n\n---\n\n## Selection Guides & Advanced Topics\n\n> For SKU comparison tables, PTU sizing formulas, and advanced option details, load [references\u002Fcustomize-guides.md](references\u002Fcustomize-guides.md).\n\n**SKU selection:** GlobalStandard (production\u002FHA) → Standard (dev\u002Ftest) → ProvisionedManaged (high-volume\u002Fguaranteed throughput) → DataZoneStandard (data residency).\n\n**Capacity:** TPM-based SKUs range from 1K (dev) to 100K+ (large production). PTU-based use formula: `(Input TPM × 0.001) + (Output TPM × 0.002) + (Requests\u002Fmin × 0.1)`.\n\n**Advanced options:** Dynamic quota (GlobalStandard only), priority processing (PTU only, extra cost), spillover (overflow to backup deployment).\n\n---\n\n## Related Skills\n\n- **preset** - Quick deployment to best region with automatic configuration\n- **microsoft-foundry** - Parent skill for all Microsoft Foundry operations\n- **[quota](..\u002F..\u002F..\u002Fquota\u002Fquota.md)** — For quota viewing, increase requests, and troubleshooting quota errors, defer to this skill instead of duplicating guidance\n- **rbac** - Manage permissions and access control\n\n---\n\n## Notes\n\n- Set `PROJECT_RESOURCE_ID` environment variable to skip prompt\n- Not all SKUs available in all regions; capacity varies by subscription\u002Fregion\u002Fmodel\n- Custom RAI policies can be configured in Azure Portal\n- Automatic version upgrades occur during maintenance windows\n- Use Azure Monitor and Application Insights for production deployments","# Customize Model Deployment\n\nInteractive guided workflow for deploying Azure OpenAI models with full customization control over version, SKU, capacity, content filtering, and advanced options.\n\n## Quick Reference\n\n| Property | Description |\n|----------|-------------|\n| **Flow** | Interactive step-by-step guided deployment |\n| **Customization** | Version, SKU, Capacity, RAI Policy, Advanced Options |\n| **SKU Support** | GlobalStandard, Standard, ProvisionedManaged, DataZoneStandard |\n| **Best For** | Precise control over deployment configuration |\n| **Authentication** | Azure CLI (`az login`) |\n| **Tools** | Azure CLI, MCP tools (optional) |\n\n## When to Use This Skill\n\nUse this skill when you need **precise control** over deployment configuration:\n\n- ✅ **Choose specific model version** (not just latest)\n- ✅ **Select deployment SKU** (GlobalStandard vs Standard vs PTU)\n- ✅ **Set exact capacity** within available range\n- ✅ **Configure content filtering** (RAI policy selection)\n- ✅ **Enable advanced features** (dynamic quota, priority processing, spillover)\n- ✅ **PTU deployments** (Provisioned Throughput Units)\n\n**Alternative:** Use `preset` for quick deployment to the best available region with automatic configuration.\n\n### Comparison: customize vs preset\n\n| Feature | customize | preset |\n|---------|---------------------|----------------------------|\n| **Focus** | Full customization control | Optimal region selection |\n| **Version Selection** | User chooses from available | Uses latest automatically |\n| **SKU Selection** | User chooses (GlobalStandard\u002FStandard\u002FPTU) | GlobalStandard only |\n| **Capacity** | User specifies exact value | Auto-calculated (50% of available) |\n| **RAI Policy** | User selects from options | Default policy only |\n| **Region** | Current region first, falls back to all regions if no capacity | Checks capacity across all regions upfront |\n| **Use Case** | Precise deployment requirements | Quick deployment to best region |\n\n## Prerequisites\n\n- Azure subscription with Cognitive Services Contributor or Owner role\n- Microsoft Foundry project resource ID (format: `\u002Fsubscriptions\u002F{sub}\u002FresourceGroups\u002F{rg}\u002Fproviders\u002FMicrosoft.CognitiveServices\u002Faccounts\u002F{account}\u002Fprojects\u002F{project}`)\n- Azure CLI installed and authenticated (`az login`)\n- Optional: Set `PROJECT_RESOURCE_ID` environment variable\n\n## Workflow Overview\n\n### Complete Flow (14 Phases)\n\n```\n1. Verify Authentication\n2. Get Project Resource ID\n3. Verify Project Exists\n4. Get Model Name (if not provided)\n5. List Model Versions → User Selects\n6. List SKUs for Version → User Selects\n7. Get Capacity Range → User Configures\n   7b. If no capacity: Cross-Region Fallback → Query all regions → User selects region\u002Fproject\n8. List RAI Policies → User Selects\n9. Configure Advanced Options (if applicable)\n10. Configure Version Upgrade Policy\n11. Generate Deployment Name\n12. Review Configuration\n13. Execute Deployment & Monitor\n```\n\n### Fast Path (Defaults)\n\nIf user accepts all defaults (latest version, GlobalStandard SKU, recommended capacity, default RAI policy, standard upgrade policy), deployment completes in ~5 interactions.\n\n---\n\n## Phase Summaries\n\n> ⚠️ **MUST READ:** Before executing any phase, load [references\u002Fcustomize-workflow.md](references\u002Fcustomize-workflow.md) for the full scripts and implementation details. The summaries below describe *what* each phase does — the reference file contains the *how* (CLI commands, quota patterns, capacity formulas, cross-region fallback logic).\n\n| Phase | Action | Key Details |\n|-------|--------|-------------|\n| **1. Verify Auth** | Check `az account show`; prompt `az login` if needed | Verify correct subscription is active |\n| **2. Get Project ID** | Read `PROJECT_RESOURCE_ID` env var or prompt user | ARM resource ID format required |\n| **3. Verify Project** | Parse resource ID, call `az cognitiveservices account show` | Extracts subscription, RG, account, project, region |\n| **4. Get Model** | List models via `az cognitiveservices account list-models` | User selects from available or enters custom name |\n| **5. Select Version** | Query versions for chosen model | Recommend latest; user picks from list |\n| **6. Select SKU** | Query model catalog + subscription quota, show only deployable SKUs | ⚠️ Never hardcode SKU lists — always query live data |\n| **7. Configure Capacity** | Query capacity API, validate min\u002Fmax\u002Fstep, user enters value | Cross-region fallback if no capacity in current region |\n| **8. Select RAI Policy** | Present content filter options | Default: `Microsoft.DefaultV2` |\n| **9. Advanced Options** | Dynamic quota (GlobalStandard), priority processing (PTU), spillover | SKU-dependent availability |\n| **10. Upgrade Policy** | Choose: OnceNewDefaultVersionAvailable \u002F OnceCurrentVersionExpired \u002F NoAutoUpgrade | Default: auto-upgrade on new default |\n| **11. Deployment Name** | Auto-generate unique name, allow custom override | Validates format: `^[\\w.-]{2,64}$` |\n| **12. Review** | Display full config summary, confirm before proceeding | User approves or cancels |\n| **13. Deploy & Monitor** | `az cognitiveservices account deployment create`, poll status | Timeout after 5 min; show endpoint + portal link |\n\n\n---\n\n## Error Handling\n\n### Common Issues and Resolutions\n\n| Error | Cause | Resolution |\n|-------|-------|------------|\n| **Model not found** | Invalid model name | List available models with `az cognitiveservices account list-models` |\n| **Version not available** | Version not supported for SKU | Select different version or SKU |\n| **Insufficient quota** | Capacity > available quota | Skill auto-searches all regions; fails only if no region has quota |\n| **SKU not supported** | SKU not available in region | Cross-region fallback searches other regions automatically |\n| **Capacity out of range** | Invalid capacity value | **PREVENTED**: Skill validates min\u002Fmax\u002Fstep at input (Phase 7) |\n| **Deployment name exists** | Name conflict | Auto-incremented name generation |\n| **Authentication failed** | Not logged in | Run `az login` |\n| **Permission denied** | Insufficient permissions | Assign Cognitive Services Contributor role |\n| **Capacity query fails** | API\u002Fpermissions\u002Fnetwork error | **DEPLOYMENT BLOCKED**: Will not proceed without valid quota data |\n\n### Troubleshooting Commands\n\n```bash\n# Check deployment status\naz cognitiveservices account deployment show --name \u003Caccount> --resource-group \u003Crg> --deployment-name \u003Cname>\n\n# List all deployments\naz cognitiveservices account deployment list --name \u003Caccount> --resource-group \u003Crg> -o table\n\n# Check quota usage\naz cognitiveservices usage list --name \u003Caccount> --resource-group \u003Crg>\n\n# Delete failed deployment\naz cognitiveservices account deployment delete --name \u003Caccount> --resource-group \u003Crg> --deployment-name \u003Cname>\n```\n\n---\n\n## Selection Guides & Advanced Topics\n\n> For SKU comparison tables, PTU sizing formulas, and advanced option details, load [references\u002Fcustomize-guides.md](references\u002Fcustomize-guides.md).\n\n**SKU selection:** GlobalStandard (production\u002FHA) → Standard (dev\u002Ftest) → ProvisionedManaged (high-volume\u002Fguaranteed throughput) → DataZoneStandard (data residency).\n\n**Capacity:** TPM-based SKUs range from 1K (dev) to 100K+ (large production). PTU-based use formula: `(Input TPM × 0.001) + (Output TPM × 0.002) + (Requests\u002Fmin × 0.1)`.\n\n**Advanced options:** Dynamic quota (GlobalStandard only), priority processing (PTU only, extra cost), spillover (overflow to backup deployment).\n\n---\n\n## Related Skills\n\n- **preset** - Quick deployment to best region with automatic configuration\n- **microsoft-foundry** - Parent skill for all Microsoft Foundry operations\n- **[quota](..\u002F..\u002F..\u002Fquota\u002Fquota.md)** — For quota viewing, increase requests, and troubleshooting quota errors, defer to this skill instead of duplicating guidance\n- **rbac** - Manage permissions and access control\n\n---\n\n## Notes\n\n- Set `PROJECT_RESOURCE_ID` environment variable to skip prompt\n- Not all SKUs available in all regions; capacity varies by subscription\u002Fregion\u002Fmodel\n- Custom RAI policies can be configured in Azure Portal\n- Automatic version upgrades occur during maintenance windows\n- Use Azure Monitor and Application Insights for production deployments",{"name":5,"license":15,"metadata":27,"description":7},{"author":12,"version":28},"1.0.1","main","653b12ebe42d8d4fb0ce41896196cb51189927a9",".agents\u002Fskills\u002Fmicrosoft-foundry\u002Fmodels\u002Fdeploy-model\u002Fcustomize",0,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Ffrontier-ai-governance-rvas","https:\u002F\u002Fmicrosoft.github.io\u002Ffrontier-ai-governance-rvas","https:\u002F\u002Fgithub.com\u002Fmicrosoft","https:\u002F\u002Fopensource.microsoft.com","Open source projects and samples from Microsoft","2026-10-27 01:11:46",{"source":8,"skillName":5,"commands":40,"prompt":50,"zipAvailable":51},[41,44,47],{"tool":42,"command":43},"npx","npx skills add microsoft\u002Ffrontier-ai-governance-rvas --skill customize",{"tool":45,"command":46},"bunx","bunx skills add microsoft\u002Ffrontier-ai-governance-rvas --skill customize",{"tool":48,"command":49},"pnpm","pnpm dlx skills add microsoft\u002Ffrontier-ai-governance-rvas --skill customize","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Ffrontier-ai-governance-rvas\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fmicrosoft-foundry\u002Fmodels\u002Fdeploy-model\u002Fcustomize\u002FSKILL.md",true,[53,59,63],{"path":54,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":57,"sourceHtmlUrl":58},"EXAMPLES.md","REFERENCE","参考文档",4402,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Ffrontier-ai-governance-rvas\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fmicrosoft-foundry\u002Fmodels\u002Fdeploy-model\u002Fcustomize\u002FEXAMPLES.md",{"path":60,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":61,"sourceHtmlUrl":62},"references\u002Fcustomize-guides.md",3487,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Ffrontier-ai-governance-rvas\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fmicrosoft-foundry\u002Fmodels\u002Fdeploy-model\u002Fcustomize\u002Freferences\u002Fcustomize-guides.md",{"path":64,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":65,"sourceHtmlUrl":66},"references\u002Fcustomize-workflow.md",13403,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Ffrontier-ai-governance-rvas\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fmicrosoft-foundry\u002Fmodels\u002Fdeploy-model\u002Fcustomize\u002Freferences\u002Fcustomize-workflow.md",[68,84,96,102,114,124],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":79,"publishedAt":22},"01M69AEY2SZBH07YRH81HNQQ8Y","skill-creator","Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Ffrontier-ai-governance-rvas\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fskill-creator\u002FSKILL.md",[74],{"categoryNo":75,"categoryName":76,"taxonomyType":77,"taxonomyTypeDesc":78},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[80,81,82,83],"skill creator","performance","run evals","test",{"skillNo":85,"name":21,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":92,"publishedAt":22},"01M69AEHQ7SGDKMGZAJGGPYBXX","Intelligently deploys Azure OpenAI models to optimal regions by analyzing capacity across all available regions. Automatically checks current region first and shows alternatives if needed. USE FOR: quick deployment, optimal region, best region, automatic region selection, fast setup, multi-region capacity check, high availability deployment, deploy to best location. DO NOT USE FOR: custom SKU selection (use customize), specific version selection (use customize), custom capacity configuration (use customize), PTU deployments (use customize).","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Ffrontier-ai-governance-rvas\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fmicrosoft-foundry\u002Fmodels\u002Fdeploy-model\u002Fpreset\u002FSKILL.md",[89],{"categoryNo":90,"categoryName":91,"taxonomyType":77,"taxonomyTypeDesc":78},"01JBSEEDCAT000000000000011","运维与部署",[21,20,9,93,5,94,95],"deploy","setup","capacity check",{"skillNo":97,"name":20,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":101,"publishedAt":22},"01M69AECG84DC1D9CW263ZP6JC","Discovers available Azure OpenAI model capacity across regions and projects. Analyzes quota limits, compares availability, and recommends optimal deployment locations based on capacity requirements. USE FOR: find capacity, check quota, where can I deploy, capacity discovery, best region for capacity, multi-project capacity search, quota analysis, model availability, region comparison, check TPM availability. DO NOT USE FOR: actual deployment (hand off to preset or customize after discovery), quota increase requests (direct user to Azure Portal), listing existing deployments.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Ffrontier-ai-governance-rvas\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fmicrosoft-foundry\u002Fmodels\u002Fdeploy-model\u002Fcapacity\u002FSKILL.md",[],[20,9,93,5,21],{"skillNo":103,"name":104,"nameZh":6,"description":105,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":106,"categories":107,"keywords":110,"publishedAt":22},"01M69AE9TETM0YV9PADJTF9YZ6","deploy-model","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).","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Ffrontier-ai-governance-rvas\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fmicrosoft-foundry\u002Fmodels\u002Fdeploy-model\u002FSKILL.md",[108,109],{"categoryNo":90,"categoryName":91,"taxonomyType":77,"taxonomyTypeDesc":78},{"categoryNo":75,"categoryName":76,"taxonomyType":77,"taxonomyTypeDesc":78},[93,111,20,21,9,112,113,19],"deploy model","foundry","MCP",{"skillNo":115,"name":116,"nameZh":6,"description":117,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":118,"categories":119,"keywords":121,"publishedAt":22},"01M69AE4M3X9ZQJ8FT0CD0MCAK","finetuning","Fine-tune models on Microsoft Foundry using SFT (supervised), DPO (preference), or RFT (reinforcement with graders). Covers dataset preparation, training job submission, deployment, and evaluation. USE FOR: fine-tune, SFT, DPO, RFT, training data, grader, distillation, fine-tuned model, training job, large file upload, calibrate grader, deploy fine-tuned model, evaluate fine-tuned model. DO NOT USE FOR: general model deployment without fine-tuning (use deploy-model), agent creation (use agents), prompt optimization without training (use prompt-optimizer).","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Ffrontier-ai-governance-rvas\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002FSKILL.md",[120],{"categoryNo":75,"categoryName":76,"taxonomyType":77,"taxonomyTypeDesc":78},[116,9,112,122,123,93],"microsoft foundry","placeholder",{"skillNo":125,"name":126,"nameZh":6,"description":127,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":128,"categories":129,"keywords":132,"publishedAt":22},"01M69ADQG4P4Q7RSM9HB3V9B4K","microsoft-foundry","Build, deploy, evaluate, optimize, fine-tune, and manage Microsoft Foundry agents, models, and resources end to end with azd. USE FOR: azd ai agent, azd provision\u002Fdeploy, hosted agent scaffold\u002Fdevelop\u002Frun\u002Fdeploy, prompt agent create, create agent, update agent, add tool to agent, invoke agent, agent.yaml, evaluate agent, batch eval, continuous eval, continuous monitoring, agent CI\u002FCD, optimize prompt, improve prompt, prompt optimizer, optimize agent instructions, Agent Optimizer scaffold, dataset curation from traces, deploy model, model fine-tuning (SFT\u002FDPO\u002FRFT), Foundry project, RBAC, role assignment, permissions, quota, capacity, region, troubleshoot agent, deployment failure, AI Services, create Foundry resource, knowledge index, customize deployment, onboard, availability, training-data, grader, distillation, fine-tuned model, large file upload. DO NOT USE FOR: Azure Functions, App Service, general Azure deploy (use azure-deploy), general Azure prep (use azure-prepare).","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Ffrontier-ai-governance-rvas\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fmicrosoft-foundry\u002FSKILL.md",[130,131],{"categoryNo":90,"categoryName":91,"taxonomyType":77,"taxonomyTypeDesc":78},{"categoryNo":75,"categoryName":76,"taxonomyType":77,"taxonomyTypeDesc":78},[9,112,122,133,134,135,93,136,137,138,111,20,5,139],"add tool","troubleshoot","create agent","prepare","scaffold","azure deploy","ai agent"]