[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M699PTE7J62VCASZ6GB0WTF1":3,"skill-same:01M699PTE7J62VCASZ6GB0WTF1":211},{"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":23,"publishedAt":46,"linkOnly":47,"markdownContent":48,"markdownBody":49,"frontMatter":50,"refName":53,"commitSha":54,"skillDirectory":55,"forksCount":56,"repositoryHtmlUrl":57,"repositoryHomepageUrl":6,"ownerHtmlUrl":58,"ownerBlogUrl":59,"ownerDescription":60,"updatedAt":61,"install":62,"resources":75},"01M699PTE7J62VCASZ6GB0WTF1","finetuning",null,"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).","microsoft\u002Fazure-skills","microsoft","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F6154722?v=4","01M698VYDXZ6JW5WH3CRV650R8","Microsoft","01M699HXPKQFT1BH5KD1PG0CB4",1640,"MIT","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fazure-skills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fazure-skills\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[5,24,25,26,27,28,29,30,31,32,33,34,35,9,36,37,38,39,40,41,42,43,44,45],"tuning","supervised","submission","for","Prompt Optimization","distillation","dataset","creation","optimizer","do","grader","model","data","Evaluation","Optimization","calibrate","deployment","training","deploy","placeholder","microsoft foundry","foundry","2026-11-10 10:12:30",false,"---\nname: finetuning\ndescription: \"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).\"\nlicense: MIT\nmetadata:\n  author: Microsoft\n  version: \"0.0.0-placeholder\"\n---\n\n# Fine-Tuning on Microsoft Foundry\n\nFine-tune models using SFT (supervised), DPO (preference), or RFT (reinforcement with graders). Covers dataset prep, training, deployment, and evaluation.\n\n## When to Use\n\nUse this sub-skill when the user asks about:\n- Fine-tuning a model (SFT, DPO, or RFT)\n- Preparing, validating, or formatting training data\n- Submitting, monitoring, or diagnosing training jobs\n- Calibrating graders or pass thresholds for RFT\n- Deploying or evaluating a fine-tuned model\n- Choosing between training types (SFT vs DPO vs RFT)\n- Distillation, synthetic data generation, or dataset quality scoring\n- Large file uploads for training data\n- Cleaning up fine-tuning resources (files, deployments)\n\n**Do NOT use for:** General model deployment without fine-tuning (use deploy-model), agent creation (use agents), prompt optimization without training (use prompt-optimizer).\n\n## Workflows\n\n| Stage | Guide |\n|-------|-------|\n| **Quick start** | [workflows\u002Fquickstart.md](workflows\u002Fquickstart.md) |\n| **Full pipeline** | [workflows\u002Ffull-pipeline.md](workflows\u002Ffull-pipeline.md) |\n| **Create data** | [workflows\u002Fdataset-creation.md](workflows\u002Fdataset-creation.md) |\n| **Iterate** | [workflows\u002Fiterative-training.md](workflows\u002Fiterative-training.md) |\n| **Diagnose** | [workflows\u002Fdiagnose-poor-results.md](workflows\u002Fdiagnose-poor-results.md) |\n\n## References\n\n| Topic | File |\n|-------|------|\n| SFT vs DPO vs RFT | [references\u002Ftraining-types.md](references\u002Ftraining-types.md) |\n| Hyperparameters | [references\u002Fhyperparameters.md](references\u002Fhyperparameters.md) |\n| Data formats | [references\u002Fdataset-formats.md](references\u002Fdataset-formats.md) |\n| Grader design (RFT) | [references\u002Fgrader-design.md](references\u002Fgrader-design.md) |\n| Reward hacking | [references\u002Freward-hacking.md](references\u002Freward-hacking.md) |\n| Agentic RFT (tools) | [references\u002Fagentic-rft.md](references\u002Fagentic-rft.md) |\n| Deployment | [references\u002Fdeployment.md](references\u002Fdeployment.md) |\n| Training curves | [references\u002Ftraining-curves.md](references\u002Ftraining-curves.md) |\n| Evaluation | [references\u002Fevaluation.md](references\u002Fevaluation.md) |\n| Vision fine-tuning | [references\u002Fvision-fine-tuning.md](references\u002Fvision-fine-tuning.md) |\n| Large file uploads | [references\u002Flarge-file-uploads.md](references\u002Flarge-file-uploads.md) |\n| Platform gotchas | [references\u002Fplatform-gotchas.md](references\u002Fplatform-gotchas.md) |\n\n## Scripts\n\n| Script | Purpose |\n|--------|---------|\n| `scripts\u002Fsubmit_training.py` | Submit SFT\u002FDPO\u002FRFT jobs |\n| `scripts\u002Fmonitor_training.py` | Poll job until completion |\n| `scripts\u002Fcalibrate_grader.py` | Find optimal RFT pass_threshold |\n| `scripts\u002Fcheck_training.py` | Analyze curves, list checkpoints |\n| `scripts\u002Fdeploy_model.py` | Deploy via ARM REST API |\n| `scripts\u002Fevaluate_model.py` | LLM judge evaluation |\n| `scripts\u002Fconvert_dataset.py` | Convert between SFT\u002FDPO\u002FRFT formats |\n| `scripts\u002Fgenerate_distillation_data.py` | Generate synthetic training data |\n| `scripts\u002Fscore_dataset.py` | Quality scoring on training data |\n| `scripts\u002Fcleanup.py` | Delete old files and deployments |\n| `scripts\u002Fvalidate\u002F` | Data validators (SFT, DPO, RFT) + stats |\n\n## Rules\n\n1. **Always baseline first** — evaluate the base model before fine-tuning\n2. **Validate data** before submitting — run `scripts\u002Fvalidate\u002Fvalidate_sft.py`\n3. **Calibrate RFT graders** — target 25-50% failure rate on the base model\n4. **Evaluate checkpoints** — don't blindly deploy the final one\n5. **Measure token cost** alongside accuracy when comparing models\n\n## Quick Reference\n\n| Task | Command |\n|------|---------|\n| Validate SFT data | `python scripts\u002Fvalidate\u002Fvalidate_sft.py data.jsonl` |\n| Submit SFT job | `python scripts\u002Fsubmit_training.py --model gpt-4.1-mini --training-file train.jsonl --validation-file val.jsonl --type sft` |\n| Monitor job | `python scripts\u002Fmonitor_training.py --job-id ftjob-xxx` |\n| Analyze curves | `python scripts\u002Fcheck_training.py --job-id ftjob-xxx` |\n| Deploy model | `python scripts\u002Fdeploy_model.py --model-id ft:gpt-4.1-mini:... --name my-eval` |\n| Evaluate model | `python scripts\u002Fevaluate_model.py --deployment-name my-eval --test-file test.jsonl` |\n\n## Error Handling\n\n| Error | Cause | Fix |\n|-------|-------|-----|\n| \"API version not supported\" | Older `openai` SDK on `\u002Fv1\u002F` endpoint | Upgrade to `openai>=1.0` |\n| \"does not support fine-tuning with Standard TrainingType\" | OSS model needs `globalStandard` | Use `--use-rest` flag or script auto-falls back |\n| Job stuck in post-training eval | Under-provisioned tool endpoint (RFT) | Scale to S2+, enable Always On |\n| \"DeploymentNotReady\" after ARM succeeds | ARM\u002Fdata-plane race condition | Delete and recreate deployment, wait 5 min |\n| Content safety block at deployment | PII-dense training data | Remove problematic document types |\n","# Fine-Tuning on Microsoft Foundry\n\nFine-tune models using SFT (supervised), DPO (preference), or RFT (reinforcement with graders). Covers dataset prep, training, deployment, and evaluation.\n\n## When to Use\n\nUse this sub-skill when the user asks about:\n- Fine-tuning a model (SFT, DPO, or RFT)\n- Preparing, validating, or formatting training data\n- Submitting, monitoring, or diagnosing training jobs\n- Calibrating graders or pass thresholds for RFT\n- Deploying or evaluating a fine-tuned model\n- Choosing between training types (SFT vs DPO vs RFT)\n- Distillation, synthetic data generation, or dataset quality scoring\n- Large file uploads for training data\n- Cleaning up fine-tuning resources (files, deployments)\n\n**Do NOT use for:** General model deployment without fine-tuning (use deploy-model), agent creation (use agents), prompt optimization without training (use prompt-optimizer).\n\n## Workflows\n\n| Stage | Guide |\n|-------|-------|\n| **Quick start** | [workflows\u002Fquickstart.md](workflows\u002Fquickstart.md) |\n| **Full pipeline** | [workflows\u002Ffull-pipeline.md](workflows\u002Ffull-pipeline.md) |\n| **Create data** | [workflows\u002Fdataset-creation.md](workflows\u002Fdataset-creation.md) |\n| **Iterate** | [workflows\u002Fiterative-training.md](workflows\u002Fiterative-training.md) |\n| **Diagnose** | [workflows\u002Fdiagnose-poor-results.md](workflows\u002Fdiagnose-poor-results.md) |\n\n## References\n\n| Topic | File |\n|-------|------|\n| SFT vs DPO vs RFT | [references\u002Ftraining-types.md](references\u002Ftraining-types.md) |\n| Hyperparameters | [references\u002Fhyperparameters.md](references\u002Fhyperparameters.md) |\n| Data formats | [references\u002Fdataset-formats.md](references\u002Fdataset-formats.md) |\n| Grader design (RFT) | [references\u002Fgrader-design.md](references\u002Fgrader-design.md) |\n| Reward hacking | [references\u002Freward-hacking.md](references\u002Freward-hacking.md) |\n| Agentic RFT (tools) | [references\u002Fagentic-rft.md](references\u002Fagentic-rft.md) |\n| Deployment | [references\u002Fdeployment.md](references\u002Fdeployment.md) |\n| Training curves | [references\u002Ftraining-curves.md](references\u002Ftraining-curves.md) |\n| Evaluation | [references\u002Fevaluation.md](references\u002Fevaluation.md) |\n| Vision fine-tuning | [references\u002Fvision-fine-tuning.md](references\u002Fvision-fine-tuning.md) |\n| Large file uploads | [references\u002Flarge-file-uploads.md](references\u002Flarge-file-uploads.md) |\n| Platform gotchas | [references\u002Fplatform-gotchas.md](references\u002Fplatform-gotchas.md) |\n\n## Scripts\n\n| Script | Purpose |\n|--------|---------|\n| `scripts\u002Fsubmit_training.py` | Submit SFT\u002FDPO\u002FRFT jobs |\n| `scripts\u002Fmonitor_training.py` | Poll job until completion |\n| `scripts\u002Fcalibrate_grader.py` | Find optimal RFT pass_threshold |\n| `scripts\u002Fcheck_training.py` | Analyze curves, list checkpoints |\n| `scripts\u002Fdeploy_model.py` | Deploy via ARM REST API |\n| `scripts\u002Fevaluate_model.py` | LLM judge evaluation |\n| `scripts\u002Fconvert_dataset.py` | Convert between SFT\u002FDPO\u002FRFT formats |\n| `scripts\u002Fgenerate_distillation_data.py` | Generate synthetic training data |\n| `scripts\u002Fscore_dataset.py` | Quality scoring on training data |\n| `scripts\u002Fcleanup.py` | Delete old files and deployments |\n| `scripts\u002Fvalidate\u002F` | Data validators (SFT, DPO, RFT) + stats |\n\n## Rules\n\n1. **Always baseline first** — evaluate the base model before fine-tuning\n2. **Validate data** before submitting — run `scripts\u002Fvalidate\u002Fvalidate_sft.py`\n3. **Calibrate RFT graders** — target 25-50% failure rate on the base model\n4. **Evaluate checkpoints** — don't blindly deploy the final one\n5. **Measure token cost** alongside accuracy when comparing models\n\n## Quick Reference\n\n| Task | Command |\n|------|---------|\n| Validate SFT data | `python scripts\u002Fvalidate\u002Fvalidate_sft.py data.jsonl` |\n| Submit SFT job | `python scripts\u002Fsubmit_training.py --model gpt-4.1-mini --training-file train.jsonl --validation-file val.jsonl --type sft` |\n| Monitor job | `python scripts\u002Fmonitor_training.py --job-id ftjob-xxx` |\n| Analyze curves | `python scripts\u002Fcheck_training.py --job-id ftjob-xxx` |\n| Deploy model | `python scripts\u002Fdeploy_model.py --model-id ft:gpt-4.1-mini:... --name my-eval` |\n| Evaluate model | `python scripts\u002Fevaluate_model.py --deployment-name my-eval --test-file test.jsonl` |\n\n## Error Handling\n\n| Error | Cause | Fix |\n|-------|-------|-----|\n| \"API version not supported\" | Older `openai` SDK on `\u002Fv1\u002F` endpoint | Upgrade to `openai>=1.0` |\n| \"does not support fine-tuning with Standard TrainingType\" | OSS model needs `globalStandard` | Use `--use-rest` flag or script auto-falls back |\n| Job stuck in post-training eval | Under-provisioned tool endpoint (RFT) | Scale to S2+, enable Always On |\n| \"DeploymentNotReady\" after ARM succeeds | ARM\u002Fdata-plane race condition | Delete and recreate deployment, wait 5 min |\n| Content safety block at deployment | PII-dense training data | Remove problematic document types |\n",{"name":5,"license":15,"metadata":51,"description":7},{"author":12,"version":52},"0.0.0-placeholder","main","fbda857c484a85c7ce644f56809b7f204471fb69",".github\u002Fplugins\u002Fazure-skills\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning",267,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fazure-skills","https:\u002F\u002Fgithub.com\u002Fmicrosoft","https:\u002F\u002Fopensource.microsoft.com","Open source projects and samples from Microsoft","2026-11-14 01:56:00",{"source":8,"skillName":5,"commands":63,"prompt":73,"zipAvailable":74},[64,67,70],{"tool":65,"command":66},"npx","npx skills add microsoft\u002Fazure-skills --skill finetuning",{"tool":68,"command":69},"bunx","bunx skills add microsoft\u002Fazure-skills --skill finetuning",{"tool":71,"command":72},"pnpm","pnpm dlx skills add microsoft\u002Fazure-skills --skill finetuning","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fazure-skills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fazure-skills\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002FSKILL.md",true,[76,82,86,90,94,98,102,106,110,114,118,122,126,132,136,140,144,148,152,156,160,164,168,172,176,180,184,188,192,195,199,203,207],{"path":77,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":80,"sourceHtmlUrl":81},"references\u002Fagentic-rft.md","REFERENCE","参考文档",3234,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fazure-skills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fazure-skills\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Freferences\u002Fagentic-rft.md",{"path":83,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":84,"sourceHtmlUrl":85},"references\u002Fdataset-formats.md",3740,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fazure-skills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fazure-skills\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Freferences\u002Fdataset-formats.md",{"path":87,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":88,"sourceHtmlUrl":89},"references\u002Fdeployment.md",3503,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fazure-skills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fazure-skills\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Freferences\u002Fdeployment.md",{"path":91,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":92,"sourceHtmlUrl":93},"references\u002Fevaluation.md",5924,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fazure-skills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fazure-skills\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Freferences\u002Fevaluation.md",{"path":95,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":96,"sourceHtmlUrl":97},"references\u002Fgrader-design.md",3437,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fazure-skills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fazure-skills\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Freferences\u002Fgrader-design.md",{"path":99,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":100,"sourceHtmlUrl":101},"references\u002Fhyperparameters.md",3233,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fazure-skills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fazure-skills\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Freferences\u002Fhyperparameters.md",{"path":103,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":104,"sourceHtmlUrl":105},"references\u002Flarge-file-uploads.md",927,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fazure-skills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fazure-skills\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Freferences\u002Flarge-file-uploads.md",{"path":107,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":108,"sourceHtmlUrl":109},"references\u002Fplatform-gotchas.md",2069,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fazure-skills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fazure-skills\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Freferences\u002Fplatform-gotchas.md",{"path":111,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":112,"sourceHtmlUrl":113},"references\u002Freward-hacking.md",2945,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fazure-skills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fazure-skills\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Freferences\u002Freward-hacking.md",{"path":115,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":116,"sourceHtmlUrl":117},"references\u002Ftraining-curves.md",4183,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fazure-skills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fazure-skills\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Freferences\u002Ftraining-curves.md",{"path":119,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":120,"sourceHtmlUrl":121},"references\u002Ftraining-types.md",3161,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fazure-skills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fazure-skills\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Freferences\u002Ftraining-types.md",{"path":123,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":124,"sourceHtmlUrl":125},"references\u002Fvision-fine-tuning.md",4205,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fazure-skills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fazure-skills\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Freferences\u002Fvision-fine-tuning.md",{"path":127,"resourceType":128,"resourceTypeDesc":129,"sizeBytes":130,"sourceHtmlUrl":131},"scripts\u002Fcalibrate_grader.py","SCRIPT","脚本",9493,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fazure-skills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fazure-skills\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Fscripts\u002Fcalibrate_grader.py",{"path":133,"resourceType":128,"resourceTypeDesc":129,"sizeBytes":134,"sourceHtmlUrl":135},"scripts\u002Fcheck_training.py",7987,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fazure-skills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fazure-skills\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Fscripts\u002Fcheck_training.py",{"path":137,"resourceType":128,"resourceTypeDesc":129,"sizeBytes":138,"sourceHtmlUrl":139},"scripts\u002Fcleanup.py",9687,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fazure-skills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fazure-skills\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Fscripts\u002Fcleanup.py",{"path":141,"resourceType":128,"resourceTypeDesc":129,"sizeBytes":142,"sourceHtmlUrl":143},"scripts\u002Fcommon.py",7808,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fazure-skills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fazure-skills\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Fscripts\u002Fcommon.py",{"path":145,"resourceType":128,"resourceTypeDesc":129,"sizeBytes":146,"sourceHtmlUrl":147},"scripts\u002Fconvert_dataset.py",10936,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fazure-skills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fazure-skills\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Fscripts\u002Fconvert_dataset.py",{"path":149,"resourceType":128,"resourceTypeDesc":129,"sizeBytes":150,"sourceHtmlUrl":151},"scripts\u002Fdeploy_model.py",9618,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fazure-skills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fazure-skills\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Fscripts\u002Fdeploy_model.py",{"path":153,"resourceType":128,"resourceTypeDesc":129,"sizeBytes":154,"sourceHtmlUrl":155},"scripts\u002Fevaluate_model.py",11690,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fazure-skills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fazure-skills\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Fscripts\u002Fevaluate_model.py",{"path":157,"resourceType":128,"resourceTypeDesc":129,"sizeBytes":158,"sourceHtmlUrl":159},"scripts\u002Fgenerate_distillation_data.py",10299,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fazure-skills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fazure-skills\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Fscripts\u002Fgenerate_distillation_data.py",{"path":161,"resourceType":128,"resourceTypeDesc":129,"sizeBytes":162,"sourceHtmlUrl":163},"scripts\u002Fmonitor_training.py",5866,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fazure-skills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fazure-skills\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Fscripts\u002Fmonitor_training.py",{"path":165,"resourceType":128,"resourceTypeDesc":129,"sizeBytes":166,"sourceHtmlUrl":167},"scripts\u002Fscore_dataset.py",7873,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fazure-skills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fazure-skills\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Fscripts\u002Fscore_dataset.py",{"path":169,"resourceType":128,"resourceTypeDesc":129,"sizeBytes":170,"sourceHtmlUrl":171},"scripts\u002Fsubmit_training.py",11070,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fazure-skills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fazure-skills\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Fscripts\u002Fsubmit_training.py",{"path":173,"resourceType":128,"resourceTypeDesc":129,"sizeBytes":174,"sourceHtmlUrl":175},"scripts\u002Fvalidate\u002F__init__.py",305,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fazure-skills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fazure-skills\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Fscripts\u002Fvalidate\u002F__init__.py",{"path":177,"resourceType":128,"resourceTypeDesc":129,"sizeBytes":178,"sourceHtmlUrl":179},"scripts\u002Fvalidate\u002Fdata_stats.py",6331,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fazure-skills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fazure-skills\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Fscripts\u002Fvalidate\u002Fdata_stats.py",{"path":181,"resourceType":128,"resourceTypeDesc":129,"sizeBytes":182,"sourceHtmlUrl":183},"scripts\u002Fvalidate\u002Fvalidate_dpo.py",3807,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fazure-skills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fazure-skills\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Fscripts\u002Fvalidate\u002Fvalidate_dpo.py",{"path":185,"resourceType":128,"resourceTypeDesc":129,"sizeBytes":186,"sourceHtmlUrl":187},"scripts\u002Fvalidate\u002Fvalidate_rft.py",8799,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fazure-skills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fazure-skills\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Fscripts\u002Fvalidate\u002Fvalidate_rft.py",{"path":189,"resourceType":128,"resourceTypeDesc":129,"sizeBytes":190,"sourceHtmlUrl":191},"scripts\u002Fvalidate\u002Fvalidate_sft.py",4573,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fazure-skills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fazure-skills\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Fscripts\u002Fvalidate\u002Fvalidate_sft.py",{"path":193,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":120,"sourceHtmlUrl":194},"workflows\u002Fdataset-creation.md","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fazure-skills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fazure-skills\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Fworkflows\u002Fdataset-creation.md",{"path":196,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":197,"sourceHtmlUrl":198},"workflows\u002Fdiagnose-poor-results.md",2401,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fazure-skills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fazure-skills\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Fworkflows\u002Fdiagnose-poor-results.md",{"path":200,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":201,"sourceHtmlUrl":202},"workflows\u002Ffull-pipeline.md",3167,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fazure-skills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fazure-skills\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Fworkflows\u002Ffull-pipeline.md",{"path":204,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":205,"sourceHtmlUrl":206},"workflows\u002Fiterative-training.md",3178,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fazure-skills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fazure-skills\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Fworkflows\u002Fiterative-training.md",{"path":208,"resourceType":78,"resourceTypeDesc":79,"sizeBytes":209,"sourceHtmlUrl":210},"workflows\u002Fquickstart.md",4600,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fazure-skills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fazure-skills\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Fworkflows\u002Fquickstart.md",[212,220,247,271,292,309],{"skillNo":213,"name":214,"nameZh":6,"description":215,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":216,"categories":217,"keywords":218,"publishedAt":219},"01M741F125HZK56E6BKPW36WRA","azure-advisor-cost-optimization","Analyze Azure Advisor Cost\u002FIdleResources findings and prevalidate deletion safety, including Service Groups. WHEN: \"find unused Azure resources\", \"what resources am I paying for but no longer using\", \"idle-resource savings\", \"historical idle-resource savings\", \"are these idle resources safe to delete\". Generic Cost, other subcategories, and cross-category requests use azure-advisor.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fazure-skills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fazure-advisor\u002Fskills\u002Fazure-advisor-cost-optimization\u002FSKILL.md",[],[],"2026-11-11 15:11:14",{"skillNo":221,"name":222,"nameZh":6,"description":223,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":224,"categories":225,"keywords":229,"publishedAt":46},"01M699VFT1T15GFDGC4K4ZHY4N","python-appservice-deploy","Deploy Python (Flask\u002FDjango\u002FFastAPI) code to Azure App Service Linux. WHEN: \"Flask App Service\", \"Django App Service\", \"FastAPI App Service\", \"deploy Python to App Service\". DO NOT USE FOR: Container Apps, Functions, non-Python, Terraform\u002FBicep\u002FIaC, full infra — use azure-prepare.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fazure-skills\u002Fblob\u002Fmain\u002Fskills\u002Fpython-appservice-deploy\u002FSKILL.md",[226],{"categoryNo":227,"categoryName":228,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000011","运维与部署",[230,42,231,232,233,234,33,235,27,236,237,238,239,240,241,242,243,244,245,246],"python appservice deploy","python","linux","infra","app","django","azure app service","azure","container","iac","fastapi","use","apps","when","code","functions","fastapi app",{"skillNo":248,"name":249,"nameZh":6,"description":250,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":251,"categories":252,"keywords":255,"publishedAt":46},"01M699VDV3PT5P0YDXRT4GM2TJ","preset","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\u002Fazure-skills\u002Fblob\u002Fmain\u002Fskills\u002Fmicrosoft-foundry\u002Fmodels\u002Fdeploy-model\u002Fpreset\u002FSKILL.md",[253,254],{"categoryNo":227,"categoryName":228,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[249,42,256,9,257,258,33,259,260,27,40,261,262,237,263,264,265,241,266,267,268,269,270],"setup","capacity","customize","quick","availability","alternatives","selection","custom","deployments","high availability","version","across","check","multi","first",{"skillNo":272,"name":258,"nameZh":6,"description":273,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":274,"categories":275,"keywords":277,"publishedAt":46},"01M699VBT6YFAKBWCK890XDB6N","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\u002Fazure-skills\u002Fblob\u002Fmain\u002Fskills\u002Fmicrosoft-foundry\u002Fmodels\u002Fdeploy-model\u002Fcustomize\u002FSKILL.md",[276],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[258,249,9,257,278,279,259,280,281,35,282,283,262,284,285,286,287,288,289,290,291,33,27,40],"policy","SET","processing","advanced","select","choose","configure","filter","azure openai","options","flow","openai","throughput","full",{"skillNo":293,"name":257,"nameZh":6,"description":294,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":295,"categories":296,"keywords":297,"publishedAt":46},"01M699V9FXHBSWG3Y48057VAYZ","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\u002Fazure-skills\u002Fblob\u002Fmain\u002Fskills\u002Fmicrosoft-foundry\u002Fmodels\u002Fdeploy-model\u002Fcapacity\u002FSKILL.md",[],[257,249,42,9,258,298,35,299,300,301,302,303,267,286,304,305,289,306,307,33,260,27,308,40],"projects","project","search","analysis","listing","hand","limits","azure portal","direct","TPM","discovery",{"skillNo":310,"name":311,"nameZh":6,"description":312,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":313,"categories":314,"keywords":317,"publishedAt":46},"01M699V7GW2RF4AB3RE3Z8Y048","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\u002Fazure-skills\u002Fblob\u002Fmain\u002Fskills\u002Fmicrosoft-foundry\u002Fmodels\u002Fdeploy-model\u002FSKILL.md",[315,316],{"categoryNo":227,"categoryName":228,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[42,318,35,249,319,45,9,257,278,279,298,259,31,299,320,301,302,267,321,286,322,323,289,33,260],"deploy model","MCP","up","create","intent","list"]