[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M69B0Z8P38G9M29CMXYGCW5P":3,"skill-same:01M69B0Z8P38G9M29CMXYGCW5P":213},{"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":47,"linkOnly":48,"markdownContent":49,"markdownBody":50,"frontMatter":51,"refName":54,"commitSha":55,"skillDirectory":56,"forksCount":57,"repositoryHtmlUrl":58,"repositoryHomepageUrl":59,"ownerHtmlUrl":60,"ownerBlogUrl":61,"ownerDescription":62,"updatedAt":63,"install":64,"resources":77},"01M69B0Z8P38G9M29CMXYGCW5P","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\u002Fskills","microsoft","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F6154722?v=4","01M698VYDXZ6JW5WH3CRV650R8","Microsoft","01M69AJYYW4E1RMSYCQDJ4FJSH",3202,"MIT","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\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",[5,24,25,26,27,28,29,30,31,32,33,34,35,36,9,37,38,39,40,41,42,43,44,45,46],"data","supervised","submission","for","Prompt Optimization","distillation","dataset","creation","optimizer","do","grader","model","tuning","Evaluation","Optimization","calibrate","deployment","training","model deployment","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":52,"description":7},{"author":12,"version":53},"0.0.0-placeholder","main","3f5b461b2314e01c400564051e92469114c5b68f",".github\u002Fplugins\u002Fazure-skills\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning",368,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills","https:\u002F\u002Fmicrosoft.github.io\u002Fskills\u002F","https:\u002F\u002Fgithub.com\u002Fmicrosoft","https:\u002F\u002Fopensource.microsoft.com","Open source projects and samples from Microsoft","2026-11-14 02:08:41",{"source":8,"skillName":5,"commands":65,"prompt":75,"zipAvailable":76},[66,69,72],{"tool":67,"command":68},"npx","npx skills add microsoft\u002Fskills --skill finetuning",{"tool":70,"command":71},"bunx","bunx skills add microsoft\u002Fskills --skill finetuning",{"tool":73,"command":74},"pnpm","pnpm dlx skills add microsoft\u002Fskills --skill finetuning","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fazure-skills\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002FSKILL.md",true,[78,84,88,92,96,100,104,108,112,116,120,124,128,134,138,142,146,150,154,158,162,166,170,174,178,182,186,190,194,197,201,205,209],{"path":79,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":82,"sourceHtmlUrl":83},"references\u002Fagentic-rft.md","REFERENCE","参考文档",3234,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fazure-skills\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Freferences\u002Fagentic-rft.md",{"path":85,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":86,"sourceHtmlUrl":87},"references\u002Fdataset-formats.md",3740,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fazure-skills\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Freferences\u002Fdataset-formats.md",{"path":89,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":90,"sourceHtmlUrl":91},"references\u002Fdeployment.md",3503,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fazure-skills\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Freferences\u002Fdeployment.md",{"path":93,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":94,"sourceHtmlUrl":95},"references\u002Fevaluation.md",5924,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fazure-skills\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Freferences\u002Fevaluation.md",{"path":97,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":98,"sourceHtmlUrl":99},"references\u002Fgrader-design.md",3437,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fazure-skills\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Freferences\u002Fgrader-design.md",{"path":101,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":102,"sourceHtmlUrl":103},"references\u002Fhyperparameters.md",3233,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fazure-skills\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Freferences\u002Fhyperparameters.md",{"path":105,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":106,"sourceHtmlUrl":107},"references\u002Flarge-file-uploads.md",927,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fazure-skills\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Freferences\u002Flarge-file-uploads.md",{"path":109,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":110,"sourceHtmlUrl":111},"references\u002Fplatform-gotchas.md",2069,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fazure-skills\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Freferences\u002Fplatform-gotchas.md",{"path":113,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":114,"sourceHtmlUrl":115},"references\u002Freward-hacking.md",2945,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fazure-skills\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Freferences\u002Freward-hacking.md",{"path":117,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":118,"sourceHtmlUrl":119},"references\u002Ftraining-curves.md",4183,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fazure-skills\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Freferences\u002Ftraining-curves.md",{"path":121,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":122,"sourceHtmlUrl":123},"references\u002Ftraining-types.md",3161,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fazure-skills\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Freferences\u002Ftraining-types.md",{"path":125,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":126,"sourceHtmlUrl":127},"references\u002Fvision-fine-tuning.md",4205,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fazure-skills\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Freferences\u002Fvision-fine-tuning.md",{"path":129,"resourceType":130,"resourceTypeDesc":131,"sizeBytes":132,"sourceHtmlUrl":133},"scripts\u002Fcalibrate_grader.py","SCRIPT","脚本",9493,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fazure-skills\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Fscripts\u002Fcalibrate_grader.py",{"path":135,"resourceType":130,"resourceTypeDesc":131,"sizeBytes":136,"sourceHtmlUrl":137},"scripts\u002Fcheck_training.py",7987,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fazure-skills\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Fscripts\u002Fcheck_training.py",{"path":139,"resourceType":130,"resourceTypeDesc":131,"sizeBytes":140,"sourceHtmlUrl":141},"scripts\u002Fcleanup.py",9687,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fazure-skills\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Fscripts\u002Fcleanup.py",{"path":143,"resourceType":130,"resourceTypeDesc":131,"sizeBytes":144,"sourceHtmlUrl":145},"scripts\u002Fcommon.py",7808,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fazure-skills\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Fscripts\u002Fcommon.py",{"path":147,"resourceType":130,"resourceTypeDesc":131,"sizeBytes":148,"sourceHtmlUrl":149},"scripts\u002Fconvert_dataset.py",10936,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fazure-skills\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Fscripts\u002Fconvert_dataset.py",{"path":151,"resourceType":130,"resourceTypeDesc":131,"sizeBytes":152,"sourceHtmlUrl":153},"scripts\u002Fdeploy_model.py",9618,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fazure-skills\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Fscripts\u002Fdeploy_model.py",{"path":155,"resourceType":130,"resourceTypeDesc":131,"sizeBytes":156,"sourceHtmlUrl":157},"scripts\u002Fevaluate_model.py",11690,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fazure-skills\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Fscripts\u002Fevaluate_model.py",{"path":159,"resourceType":130,"resourceTypeDesc":131,"sizeBytes":160,"sourceHtmlUrl":161},"scripts\u002Fgenerate_distillation_data.py",10299,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fazure-skills\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Fscripts\u002Fgenerate_distillation_data.py",{"path":163,"resourceType":130,"resourceTypeDesc":131,"sizeBytes":164,"sourceHtmlUrl":165},"scripts\u002Fmonitor_training.py",5866,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fazure-skills\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Fscripts\u002Fmonitor_training.py",{"path":167,"resourceType":130,"resourceTypeDesc":131,"sizeBytes":168,"sourceHtmlUrl":169},"scripts\u002Fscore_dataset.py",7873,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fazure-skills\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Fscripts\u002Fscore_dataset.py",{"path":171,"resourceType":130,"resourceTypeDesc":131,"sizeBytes":172,"sourceHtmlUrl":173},"scripts\u002Fsubmit_training.py",11070,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fazure-skills\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Fscripts\u002Fsubmit_training.py",{"path":175,"resourceType":130,"resourceTypeDesc":131,"sizeBytes":176,"sourceHtmlUrl":177},"scripts\u002Fvalidate\u002F__init__.py",305,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fazure-skills\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Fscripts\u002Fvalidate\u002F__init__.py",{"path":179,"resourceType":130,"resourceTypeDesc":131,"sizeBytes":180,"sourceHtmlUrl":181},"scripts\u002Fvalidate\u002Fdata_stats.py",6331,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fazure-skills\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Fscripts\u002Fvalidate\u002Fdata_stats.py",{"path":183,"resourceType":130,"resourceTypeDesc":131,"sizeBytes":184,"sourceHtmlUrl":185},"scripts\u002Fvalidate\u002Fvalidate_dpo.py",3807,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fazure-skills\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Fscripts\u002Fvalidate\u002Fvalidate_dpo.py",{"path":187,"resourceType":130,"resourceTypeDesc":131,"sizeBytes":188,"sourceHtmlUrl":189},"scripts\u002Fvalidate\u002Fvalidate_rft.py",8799,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fazure-skills\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Fscripts\u002Fvalidate\u002Fvalidate_rft.py",{"path":191,"resourceType":130,"resourceTypeDesc":131,"sizeBytes":192,"sourceHtmlUrl":193},"scripts\u002Fvalidate\u002Fvalidate_sft.py",4573,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fazure-skills\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Fscripts\u002Fvalidate\u002Fvalidate_sft.py",{"path":195,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":122,"sourceHtmlUrl":196},"workflows\u002Fdataset-creation.md","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fazure-skills\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Fworkflows\u002Fdataset-creation.md",{"path":198,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":199,"sourceHtmlUrl":200},"workflows\u002Fdiagnose-poor-results.md",2401,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fazure-skills\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Fworkflows\u002Fdiagnose-poor-results.md",{"path":202,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":203,"sourceHtmlUrl":204},"workflows\u002Ffull-pipeline.md",3167,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fazure-skills\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Fworkflows\u002Ffull-pipeline.md",{"path":206,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":207,"sourceHtmlUrl":208},"workflows\u002Fiterative-training.md",3178,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fazure-skills\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Fworkflows\u002Fiterative-training.md",{"path":210,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":211,"sourceHtmlUrl":212},"workflows\u002Fquickstart.md",4600,"https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fplugins\u002Fazure-skills\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Fworkflows\u002Fquickstart.md",[214,237,273,300,321,359],{"skillNo":215,"name":216,"nameZh":6,"description":217,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":218,"categories":219,"keywords":221,"publishedAt":47},"01M69B4JCRQV5SPXAFCKXQRV0H","skill-creator","Guide for creating effective skills for AI coding agents working with Azure SDKs and Microsoft Foundry services. Use when creating new skills or updating existing skills.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fskill-creator\u002FSKILL.md",[220],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[222,223,224,9,46,45,225,226,227,228,229,230,231,232,233,27,234,235,236],"skill creator","creator","coding agents","ai coding agents","azure","services","coding","guide","use","ai coding","with","sdks","Existing","when","new",{"skillNo":238,"name":239,"nameZh":6,"description":240,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":241,"categories":242,"keywords":253,"publishedAt":47},"01M69B4FD57V1MYKRWAJJECTZ7","podcast-generation","Generate AI-powered podcast-style audio narratives using Azure OpenAI's GPT Realtime Mini model via WebSocket. Use when building text-to-speech features, audio narrative generation, podcast creation from content, or integrating with Azure OpenAI Realtime API for real audio output. Covers full-stack implementation from React frontend to Python FastAPI backend with WebSocket streaming.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fpodcast-generation\u002FSKILL.md",[243,246,249,252],{"categoryNo":244,"categoryName":245,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000009","前端开发",{"categoryNo":247,"categoryName":248,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":250,"categoryName":251,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000016","图像与多媒体",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[254,255,256,257,258,259,260,226,261,262,263,264,265,266,267,35,268,31,269,270,271,235,272],"podcast generation","podcast","generation","frontend","python","react","realtime","azure openai","generate","streaming","api","Audio","stack","text","fastapi","python fastapi","narrative","features","fastapi backend",{"skillNo":274,"name":275,"nameZh":6,"description":276,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":277,"categories":278,"keywords":280,"publishedAt":47},"01M69B4CYPM5SESY5ZWEFDXEQZ","microsoft-docs","Understand Microsoft technologies by querying official documentation. Use whenever the user asks how something works, wants tutorials, needs configuration options, limits, quotas, or best practices for any Microsoft technology (Azure, .NET, M365, Windows, Power Platform, etc.)—even if they don't mention \"docs.\" If the question is about understanding a concept rather than writing code, this is the right skill.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fmicrosoft-docs\u002FSKILL.md",[279],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[281,9,282,283,284,285,286,287,288,289,290,226,291,292,293,230,294,67,295,296,297,298,299,27],"docs","microsoft docs","MCP","writing","cli","mcp server","windows","power platform","official","documentation","learn","best practices","question","power","back","technology","platform","learn mcp","concept",{"skillNo":301,"name":302,"nameZh":6,"description":303,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":304,"categories":305,"keywords":307,"publishedAt":47},"01M69B49C3YPD1ZJ3NC0HPCY58","mcp-builder","Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP), Node\u002FTypeScript (MCP SDK), or C#\u002F.NET (Microsoft MCP SDK).","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fmcp-builder\u002FSKILL.md",[306],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[283,308,309,310,258,311,312,313,9,314,315,35,316,317,229,230,318,319,320,232,27,235],"mcp builder","builder","typescript","llms","sdk","model context protocol","fastmcp","Tools","node","context","integrate","mcp sdk","building mcp servers",{"skillNo":322,"name":323,"nameZh":6,"description":324,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":325,"categories":326,"keywords":339,"publishedAt":47},"01M69B467A7CDMFQ0T6Q0ZA12Q","kql","KQL language expertise for writing correct, efficient Kusto Query Language queries. Covers syntax gotchas, join patterns, dynamic types, datetime pitfalls, regex patterns, serialization, memory management, result-size discipline, and advanced functions (geo, vector, graph). USE THIS SKILL whenever writing, debugging, or reviewing KQL queries — even simple ones — because the gotchas section prevents the most common errors that waste tool calls and cause expensive retry cascades. Trigger on: KQL, Kusto, ADX, Azure Data Explorer, Fabric Real-Time Intelligence, EventHouse, Log Analytics, log analysis, data exploration, time series, anomaly detection, summarize, where clause, join, extend, project, let statement, parse operator, extract function, any mention of pipe-forward query syntax.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fkql\u002FSKILL.md",[327,330,331,336],{"categoryNo":328,"categoryName":329,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":332,"categoryName":333,"taxonomyType":334,"taxonomyTypeDesc":335},"01JBSEEDCAT000000000000033","数据分析师","PROFESSION","适用职业",{"categoryNo":337,"categoryName":338,"taxonomyType":334,"taxonomyTypeDesc":335},"01JBSEEDCAT000000000000036","内容创作者",[323,284,340,341,342,226,343,344,345,346,347,348,349,350,351,352,353,354,355,27,356,357,358],"summarize","memory","analytics","vector","time series","tool","discipline","log","geo","exploration","pipe","time","project","regex","join","datetime","section","anomaly","parse",{"skillNo":360,"name":361,"nameZh":6,"description":362,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":363,"categories":364,"keywords":365,"publishedAt":47},"01M69B44HJQ7897EZ7NE7DWQX3","github-issue-creator","Convert raw notes, error logs, voice dictation, or screenshots into crisp GitHub-flavored markdown issue reports. Use when the user pastes bug info, error messages, or informal descriptions and wants a structured GitHub issue. Supports images\u002FGIFs for visual evidence.","https:\u002F\u002Fgithub.com\u002Fmicrosoft\u002Fskills\u002Fblob\u002Fmain\u002F.github\u002Fskills\u002Fgithub-issue-creator\u002FSKILL.md",[],[366,367,368,369,223,370,371,372,373,374,375,376,230,377,378,379,380,381,382,27,235],"github","github issue creator","github issue","issue","issue creator","screenshots","notes","logs","error messages","messages","convert","evidence","reports","images","info","visual","error"]