[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M69AECG84DC1D9CW263ZP6JC":3,"skill-same:01M69AECG84DC1D9CW263ZP6JC":77},{"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},"01M69AECG84DC1D9CW263ZP6JC","capacity",null,"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.","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\u002Fcapacity\u002FSKILL.md",[],[5,9,19,20,21],"deploy","customize","preset","2026-11-10 10:12:30",false,"---\nname: capacity\ndescription: \"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.\"\nlicense: MIT\nmetadata:\n  author: Microsoft\n  version: \"1.0.0\"\n---\n\n# Capacity Discovery\n\nFinds available Azure OpenAI model capacity across all accessible regions and projects. Recommends the best deployment location based on capacity requirements.\n\n## Quick Reference\n\n| Property | Description |\n|----------|-------------|\n| **Purpose** | Find where you can deploy a model with sufficient capacity |\n| **Scope** | All regions and projects the user has access to |\n| **Output** | Ranked table of regions\u002Fprojects with available capacity |\n| **Action** | Read-only analysis — does NOT deploy. Hands off to preset or customize |\n| **Authentication** | Azure CLI (`az login`) |\n\n## When to Use This Skill\n\n- ✅ User asks \"where can I deploy gpt-4o?\"\n- ✅ User specifies a capacity target: \"find a region with 10K TPM for gpt-4o\"\n- ✅ User wants to compare availability: \"which regions have gpt-4o available?\"\n- ✅ User got a quota error and needs to find an alternative location\n- ✅ User asks \"best region and project for deploying model X\"\n\n**After discovery → hand off to [preset](..\u002Fpreset\u002FSKILL.md) or [customize](..\u002Fcustomize\u002FSKILL.md) for actual deployment.**\n\n## Scripts\n\nPre-built scripts handle the complex REST API calls and data processing. Use these instead of constructing commands manually.\n\n| Script | Purpose | Usage |\n|--------|---------|-------|\n| `scripts\u002Fdiscover_and_rank.ps1` | Full discovery: capacity + projects + ranking | Primary script for capacity discovery |\n| `scripts\u002Fdiscover_and_rank.sh` | Same as above (bash) | Primary script for capacity discovery |\n| `scripts\u002Fquery_capacity.ps1` | Raw capacity query (no project matching) | Quick capacity check or version listing |\n| `scripts\u002Fquery_capacity.sh` | Same as above (bash) | Quick capacity check or version listing |\n\n## Workflow\n\n### Phase 1: Validate Prerequisites\n\n```bash\naz account show --query \"{Subscription:name, SubscriptionId:id}\" --output table\n```\n\n### Phase 2: Identify Model and Version\n\nExtract model name from user prompt. If version is unknown, query available versions:\n\n```powershell\n.\\scripts\\query_capacity.ps1 -ModelName \u003Cmodel-name>\n```\n```bash\n.\u002Fscripts\u002Fquery_capacity.sh \u003Cmodel-name>\n```\n\nThis lists available versions. Use the latest version unless user specifies otherwise.\n\n### Phase 3: Run Discovery\n\nRun the full discovery script with model name, version, and minimum capacity target:\n\n```powershell\n.\\scripts\\discover_and_rank.ps1 -ModelName \u003Cmodel-name> -ModelVersion \u003Cversion> -MinCapacity \u003Ctarget>\n```\n```bash\n.\u002Fscripts\u002Fdiscover_and_rank.sh \u003Cmodel-name> \u003Cversion> \u003Cmin-capacity>\n```\n\n> ? The script automatically queries capacity across ALL regions, cross-references with the user's existing projects, and outputs a ranked table sorted by: meets target → project count → available capacity.\n\n### Phase 3.5: Validate Subscription Quota\n\nAfter discovery identifies candidate regions, validate that the user's subscription actually has available quota in each region. Model capacity (from Phase 3) shows what the platform can support, but subscription quota limits what this specific user can deploy.\n\n```powershell\n# For each candidate region from discovery results:\n$usageData = az cognitiveservices usage list --location \u003Cregion> --subscription $SUBSCRIPTION_ID -o json 2>$null | ConvertFrom-Json\n\n# Check quota for each SKU the model supports\n# Quota names follow pattern: OpenAI.\u003CSKU>.\u003Cmodel-name>\n$usageEntry = $usageData | Where-Object { $_.name.value -eq \"OpenAI.\u003CSKU>.\u003Cmodel-name>\" }\n\nif ($usageEntry) {\n  $quotaAvailable = $usageEntry.limit - $usageEntry.currentValue\n} else {\n  $quotaAvailable = 0  # No quota allocated\n}\n```\n```bash\n# For each candidate region from discovery results:\nusage_json=$(az cognitiveservices usage list --location \u003Cregion> --subscription \"$SUBSCRIPTION_ID\" -o json 2>\u002Fdev\u002Fnull)\n\n# Extract quota for specific SKU+model\nquota_available=$(echo \"$usage_json\" | jq -r --arg name \"OpenAI.\u003CSKU>.\u003Cmodel-name>\" \\\n  '.[] | select(.name.value == $name) | .limit - .currentValue')\n```\n\n**Annotate discovery results:**\n\nAdd a \"Quota Available\" column to the ranked output from Phase 3:\n\n| Region | Available Capacity | Meets Target | Projects | Quota Available |\n|--------|-------------------|--------------|----------|-----------------|\n| eastus2 | 120K TPM | ✅ | 3 | ✅ 80K |\n| westus3 | 90K TPM | ✅ | 1 | ❌ 0 (at limit) |\n| swedencentral | 100K TPM | ✅ | 0 | ✅ 100K |\n\nRegions\u002FSKUs where `quotaAvailable = 0` should be marked with ❌ in the results. If no region has available quota, hand off to the [quota skill](..\u002F..\u002F..\u002Fquota\u002Fquota.md) for increase requests and troubleshooting.\n\n### Phase 4: Present Results and Hand Off\n\nAfter the script outputs the ranked table (now annotated with quota info), present it to the user and ask:\n\n1. ? **Quick deploy** to top recommendation with defaults → route to [preset](..\u002Fpreset\u002FSKILL.md)\n2. ⚙️ **Custom deploy** with version\u002FSKU\u002Fcapacity\u002FRAI selection → route to [customize](..\u002Fcustomize\u002FSKILL.md)\n3. ? **Check another model** or capacity target → re-run Phase 2\n4. ❌ Cancel\n\n### Phase 5: Confirm Project Before Deploying\n\nBefore handing off to preset or customize, **always confirm the target project** with the user. See the [Project Selection](..\u002FSKILL.md#project-selection-all-modes) rules in the parent router.\n\nIf the discovery table shows a sample project for the chosen region, suggest it as the default. Otherwise, query projects in that region and let the user pick.\n\n## Error Handling\n\n| Error | Cause | Resolution |\n|-------|-------|------------|\n| \"No capacity found\" | Model not available or all at quota | Hand off to [quota skill](..\u002F..\u002F..\u002Fquota\u002Fquota.md) for increase requests and troubleshooting |\n| Script auth error | `az login` expired | Re-run `az login` |\n| Empty version list | Model not in region catalog | Try a different region: `.\u002Fscripts\u002Fquery_capacity.sh \u003Cmodel> \"\" eastus` |\n| \"No projects found\" | No AI Services resources | Guide to `project\u002Fcreate` skill or Azure Portal |\n\n## Related Skills\n\n- **[preset](..\u002Fpreset\u002FSKILL.md)** — Quick deployment after capacity discovery\n- **[customize](..\u002Fcustomize\u002FSKILL.md)** — Custom deployment after capacity discovery\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","# Capacity Discovery\n\nFinds available Azure OpenAI model capacity across all accessible regions and projects. Recommends the best deployment location based on capacity requirements.\n\n## Quick Reference\n\n| Property | Description |\n|----------|-------------|\n| **Purpose** | Find where you can deploy a model with sufficient capacity |\n| **Scope** | All regions and projects the user has access to |\n| **Output** | Ranked table of regions\u002Fprojects with available capacity |\n| **Action** | Read-only analysis — does NOT deploy. Hands off to preset or customize |\n| **Authentication** | Azure CLI (`az login`) |\n\n## When to Use This Skill\n\n- ✅ User asks \"where can I deploy gpt-4o?\"\n- ✅ User specifies a capacity target: \"find a region with 10K TPM for gpt-4o\"\n- ✅ User wants to compare availability: \"which regions have gpt-4o available?\"\n- ✅ User got a quota error and needs to find an alternative location\n- ✅ User asks \"best region and project for deploying model X\"\n\n**After discovery → hand off to [preset](..\u002Fpreset\u002FSKILL.md) or [customize](..\u002Fcustomize\u002FSKILL.md) for actual deployment.**\n\n## Scripts\n\nPre-built scripts handle the complex REST API calls and data processing. Use these instead of constructing commands manually.\n\n| Script | Purpose | Usage |\n|--------|---------|-------|\n| `scripts\u002Fdiscover_and_rank.ps1` | Full discovery: capacity + projects + ranking | Primary script for capacity discovery |\n| `scripts\u002Fdiscover_and_rank.sh` | Same as above (bash) | Primary script for capacity discovery |\n| `scripts\u002Fquery_capacity.ps1` | Raw capacity query (no project matching) | Quick capacity check or version listing |\n| `scripts\u002Fquery_capacity.sh` | Same as above (bash) | Quick capacity check or version listing |\n\n## Workflow\n\n### Phase 1: Validate Prerequisites\n\n```bash\naz account show --query \"{Subscription:name, SubscriptionId:id}\" --output table\n```\n\n### Phase 2: Identify Model and Version\n\nExtract model name from user prompt. If version is unknown, query available versions:\n\n```powershell\n.\\scripts\\query_capacity.ps1 -ModelName \u003Cmodel-name>\n```\n```bash\n.\u002Fscripts\u002Fquery_capacity.sh \u003Cmodel-name>\n```\n\nThis lists available versions. Use the latest version unless user specifies otherwise.\n\n### Phase 3: Run Discovery\n\nRun the full discovery script with model name, version, and minimum capacity target:\n\n```powershell\n.\\scripts\\discover_and_rank.ps1 -ModelName \u003Cmodel-name> -ModelVersion \u003Cversion> -MinCapacity \u003Ctarget>\n```\n```bash\n.\u002Fscripts\u002Fdiscover_and_rank.sh \u003Cmodel-name> \u003Cversion> \u003Cmin-capacity>\n```\n\n> ? The script automatically queries capacity across ALL regions, cross-references with the user's existing projects, and outputs a ranked table sorted by: meets target → project count → available capacity.\n\n### Phase 3.5: Validate Subscription Quota\n\nAfter discovery identifies candidate regions, validate that the user's subscription actually has available quota in each region. Model capacity (from Phase 3) shows what the platform can support, but subscription quota limits what this specific user can deploy.\n\n```powershell\n# For each candidate region from discovery results:\n$usageData = az cognitiveservices usage list --location \u003Cregion> --subscription $SUBSCRIPTION_ID -o json 2>$null | ConvertFrom-Json\n\n# Check quota for each SKU the model supports\n# Quota names follow pattern: OpenAI.\u003CSKU>.\u003Cmodel-name>\n$usageEntry = $usageData | Where-Object { $_.name.value -eq \"OpenAI.\u003CSKU>.\u003Cmodel-name>\" }\n\nif ($usageEntry) {\n  $quotaAvailable = $usageEntry.limit - $usageEntry.currentValue\n} else {\n  $quotaAvailable = 0  # No quota allocated\n}\n```\n```bash\n# For each candidate region from discovery results:\nusage_json=$(az cognitiveservices usage list --location \u003Cregion> --subscription \"$SUBSCRIPTION_ID\" -o json 2>\u002Fdev\u002Fnull)\n\n# Extract quota for specific SKU+model\nquota_available=$(echo \"$usage_json\" | jq -r --arg name \"OpenAI.\u003CSKU>.\u003Cmodel-name>\" \\\n  '.[] | select(.name.value == $name) | .limit - .currentValue')\n```\n\n**Annotate discovery results:**\n\nAdd a \"Quota Available\" column to the ranked output from Phase 3:\n\n| Region | Available Capacity | Meets Target | Projects | Quota Available |\n|--------|-------------------|--------------|----------|-----------------|\n| eastus2 | 120K TPM | ✅ | 3 | ✅ 80K |\n| westus3 | 90K TPM | ✅ | 1 | ❌ 0 (at limit) |\n| swedencentral | 100K TPM | ✅ | 0 | ✅ 100K |\n\nRegions\u002FSKUs where `quotaAvailable = 0` should be marked with ❌ in the results. If no region has available quota, hand off to the [quota skill](..\u002F..\u002F..\u002Fquota\u002Fquota.md) for increase requests and troubleshooting.\n\n### Phase 4: Present Results and Hand Off\n\nAfter the script outputs the ranked table (now annotated with quota info), present it to the user and ask:\n\n1. ? **Quick deploy** to top recommendation with defaults → route to [preset](..\u002Fpreset\u002FSKILL.md)\n2. ⚙️ **Custom deploy** with version\u002FSKU\u002Fcapacity\u002FRAI selection → route to [customize](..\u002Fcustomize\u002FSKILL.md)\n3. ? **Check another model** or capacity target → re-run Phase 2\n4. ❌ Cancel\n\n### Phase 5: Confirm Project Before Deploying\n\nBefore handing off to preset or customize, **always confirm the target project** with the user. See the [Project Selection](..\u002FSKILL.md#project-selection-all-modes) rules in the parent router.\n\nIf the discovery table shows a sample project for the chosen region, suggest it as the default. Otherwise, query projects in that region and let the user pick.\n\n## Error Handling\n\n| Error | Cause | Resolution |\n|-------|-------|------------|\n| \"No capacity found\" | Model not available or all at quota | Hand off to [quota skill](..\u002F..\u002F..\u002Fquota\u002Fquota.md) for increase requests and troubleshooting |\n| Script auth error | `az login` expired | Re-run `az login` |\n| Empty version list | Model not in region catalog | Try a different region: `.\u002Fscripts\u002Fquery_capacity.sh \u003Cmodel> \"\" eastus` |\n| \"No projects found\" | No AI Services resources | Guide to `project\u002Fcreate` skill or Azure Portal |\n\n## Related Skills\n\n- **[preset](..\u002Fpreset\u002FSKILL.md)** — Quick deployment after capacity discovery\n- **[customize](..\u002Fcustomize\u002FSKILL.md)** — Custom deployment after capacity discovery\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",{"name":5,"license":15,"metadata":27,"description":7},{"author":12,"version":28},"1.0.0","main","653b12ebe42d8d4fb0ce41896196cb51189927a9",".agents\u002Fskills\u002Fmicrosoft-foundry\u002Fmodels\u002Fdeploy-model\u002Fcapacity",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 capacity",{"tool":45,"command":46},"bunx","bunx skills add microsoft\u002Ffrontier-ai-governance-rvas --skill capacity",{"tool":48,"command":49},"pnpm","pnpm dlx skills add microsoft\u002Ffrontier-ai-governance-rvas --skill capacity","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\u002Fcapacity\u002FSKILL.md",true,[53,59,65,69,73],{"path":54,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":57,"sourceHtmlUrl":58},"apm.yml","REFERENCE","参考文档",255,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fapm\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fautopilot-comment\u002Fapm.yml",{"path":60,"resourceType":61,"resourceTypeDesc":62,"sizeBytes":63,"sourceHtmlUrl":64},"scripts\u002Fdiscover_and_rank.ps1","SCRIPT","脚本",4677,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Ffrontier-ai-governance-rvas\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fmicrosoft-foundry\u002Fmodels\u002Fdeploy-model\u002Fcapacity\u002Fscripts\u002Fdiscover_and_rank.ps1",{"path":66,"resourceType":61,"resourceTypeDesc":62,"sizeBytes":67,"sourceHtmlUrl":68},"scripts\u002Fdiscover_and_rank.sh",4641,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Ffrontier-ai-governance-rvas\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fmicrosoft-foundry\u002Fmodels\u002Fdeploy-model\u002Fcapacity\u002Fscripts\u002Fdiscover_and_rank.sh",{"path":70,"resourceType":61,"resourceTypeDesc":62,"sizeBytes":71,"sourceHtmlUrl":72},"scripts\u002Fquery_capacity.ps1",3030,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Ffrontier-ai-governance-rvas\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fmicrosoft-foundry\u002Fmodels\u002Fdeploy-model\u002Fcapacity\u002Fscripts\u002Fquery_capacity.ps1",{"path":74,"resourceType":61,"resourceTypeDesc":62,"sizeBytes":75,"sourceHtmlUrl":76},"scripts\u002Fquery_capacity.sh",2942,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Ffrontier-ai-governance-rvas\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fmicrosoft-foundry\u002Fmodels\u002Fdeploy-model\u002Fcapacity\u002Fscripts\u002Fquery_capacity.sh",[78,94,105,112,124,134],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":89,"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",[84],{"categoryNo":85,"categoryName":86,"taxonomyType":87,"taxonomyTypeDesc":88},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[90,91,92,93],"skill creator","performance","run evals","test",{"skillNo":95,"name":21,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":102,"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",[99],{"categoryNo":100,"categoryName":101,"taxonomyType":87,"taxonomyTypeDesc":88},"01JBSEEDCAT000000000000011","运维与部署",[21,5,9,19,20,103,104],"setup","capacity check",{"skillNo":106,"name":20,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":110,"publishedAt":22},"01M69AEF2CB2J9N0F09H5PKDTP","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).","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Ffrontier-ai-governance-rvas\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fmicrosoft-foundry\u002Fmodels\u002Fdeploy-model\u002Fcustomize\u002FSKILL.md",[],[20,111,9,5,21],"policy",{"skillNo":113,"name":114,"nameZh":6,"description":115,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":116,"categories":117,"keywords":120,"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",[118,119],{"categoryNo":100,"categoryName":101,"taxonomyType":87,"taxonomyTypeDesc":88},{"categoryNo":85,"categoryName":86,"taxonomyType":87,"taxonomyTypeDesc":88},[19,121,5,21,9,122,123,111],"deploy model","foundry","MCP",{"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":131,"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",[130],{"categoryNo":85,"categoryName":86,"taxonomyType":87,"taxonomyTypeDesc":88},[126,9,122,132,133,19],"microsoft foundry","placeholder",{"skillNo":135,"name":136,"nameZh":6,"description":137,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":138,"categories":139,"keywords":142,"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",[140,141],{"categoryNo":100,"categoryName":101,"taxonomyType":87,"taxonomyTypeDesc":88},{"categoryNo":85,"categoryName":86,"taxonomyType":87,"taxonomyTypeDesc":88},[9,122,132,143,144,145,19,146,147,148,121,5,20,149],"add tool","troubleshoot","create agent","prepare","scaffold","azure deploy","ai agent"]