[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6CQ9VM61CV40BVKZBVRS1A5":3,"skill-same:01M6CQ9VM61CV40BVKZBVRS1A5":237},{"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":54,"linkOnly":55,"markdownContent":56,"markdownBody":57,"frontMatter":58,"refName":62,"commitSha":63,"skillDirectory":64,"forksCount":14,"repositoryHtmlUrl":65,"repositoryHomepageUrl":66,"ownerHtmlUrl":67,"ownerBlogUrl":68,"ownerDescription":69,"updatedAt":70,"install":71,"resources":84},"01M6CQ9VM61CV40BVKZBVRS1A5","finetuning",null,"Fine-tune models on Azure AI 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).","Trollz1004\u002FANTIGRAVITY","Trollz1004","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F132442315?v=4","01M6CQ4Z97ERZA2CXR388F6NZ1","Joshua Coleman","01M6CQ4ZCYE67QPNWBBV8H9DBE",0,"MIT","https:\u002F\u002Fgithub.com\u002FTrollz1004\u002FANTIGRAVITY\u002Fblob\u002Fmain\u002F.agents\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",[5,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53],"data","supervised","for","Prompt Optimization","distillation","dataset","creation","optimizer","do","general","models","use","grader","prompt","model","tuning","microsoft","DPO","Fine-Tuning","Evaluation","Optimization","calibrate","file","azure ai foundry","deployment","training","model deployment","azure","azure ai","placeholder","2026-11-10 10:12:30",false,"---\nname: finetuning\ndescription: 'Fine-tune models on Azure AI 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 Azure AI 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\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 Azure AI 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\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":59,"description":7},{"author":60,"version":61},"Microsoft","0.0.0-placeholder","main","6deb42cc8c67a99d7613cb5802f8bbe01a0f3d12",".agents\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning","https:\u002F\u002Fgithub.com\u002FTrollz1004\u002FANTIGRAVITY","https:\u002F\u002Fwww.ai-solutions.store","https:\u002F\u002Fgithub.com\u002FTrollz1004","https:\u002F\u002Fyouandinotai.com","Founder building YouAndINotAI, OnlineRecycle, and AIDoesItAll through Trash Or Treasure Online Recycler LLC.","2026-11-13 22:54:18",{"source":8,"skillName":5,"commands":72,"prompt":82,"zipAvailable":83},[73,76,79],{"tool":74,"command":75},"npx","npx skills add Trollz1004\u002FANTIGRAVITY --skill finetuning",{"tool":77,"command":78},"bunx","bunx skills add Trollz1004\u002FANTIGRAVITY --skill finetuning",{"tool":80,"command":81},"pnpm","pnpm dlx skills add Trollz1004\u002FANTIGRAVITY --skill finetuning","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FTrollz1004\u002FANTIGRAVITY\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002FSKILL.md",true,[85,91,95,99,103,107,111,115,119,123,127,131,135,139,143,147,151,155,161,165,169,173,177,181,185,189,193,197,201,205,209,213,217,221,225,229,233],{"path":86,"resourceType":87,"resourceTypeDesc":88,"sizeBytes":89,"sourceHtmlUrl":90},"references\u002F_images.md","REFERENCE","参考文档",308,"https:\u002F\u002Fgithub.com\u002FMishit18\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fai-research\u002Ffine-tuning-llama-factory\u002Freferences\u002F_images.md",{"path":92,"resourceType":87,"resourceTypeDesc":88,"sizeBytes":93,"sourceHtmlUrl":94},"references\u002Fadvanced.md",47824,"https:\u002F\u002Fgithub.com\u002FMishit18\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fai-research\u002Ffine-tuning-llama-factory\u002Freferences\u002Fadvanced.md",{"path":96,"resourceType":87,"resourceTypeDesc":88,"sizeBytes":97,"sourceHtmlUrl":98},"references\u002Fagentic-rft.md",3833,"https:\u002F\u002Fgithub.com\u002FTrollz1004\u002FANTIGRAVITY\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Freferences\u002Fagentic-rft.md",{"path":100,"resourceType":87,"resourceTypeDesc":88,"sizeBytes":101,"sourceHtmlUrl":102},"references\u002Fdataset-formats.md",3988,"https:\u002F\u002Fgithub.com\u002FTrollz1004\u002FANTIGRAVITY\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Freferences\u002Fdataset-formats.md",{"path":104,"resourceType":87,"resourceTypeDesc":88,"sizeBytes":105,"sourceHtmlUrl":106},"references\u002Fdeployment.md",4122,"https:\u002F\u002Fgithub.com\u002FTrollz1004\u002FANTIGRAVITY\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Freferences\u002Fdeployment.md",{"path":108,"resourceType":87,"resourceTypeDesc":88,"sizeBytes":109,"sourceHtmlUrl":110},"references\u002Fevaluation.md",6401,"https:\u002F\u002Fgithub.com\u002FTrollz1004\u002FANTIGRAVITY\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Freferences\u002Fevaluation.md",{"path":112,"resourceType":87,"resourceTypeDesc":88,"sizeBytes":113,"sourceHtmlUrl":114},"references\u002Fgetting_started.md",16189,"https:\u002F\u002Fgithub.com\u002FMishit18\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fai-research\u002Ffine-tuning-llama-factory\u002Freferences\u002Fgetting_started.md",{"path":116,"resourceType":87,"resourceTypeDesc":88,"sizeBytes":117,"sourceHtmlUrl":118},"references\u002Fgrader-design.md",4143,"https:\u002F\u002Fgithub.com\u002FTrollz1004\u002FANTIGRAVITY\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Freferences\u002Fgrader-design.md",{"path":120,"resourceType":87,"resourceTypeDesc":88,"sizeBytes":121,"sourceHtmlUrl":122},"references\u002Fhyperparameters.md",4224,"https:\u002F\u002Fgithub.com\u002FTrollz1004\u002FANTIGRAVITY\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Freferences\u002Fhyperparameters.md",{"path":124,"resourceType":87,"resourceTypeDesc":88,"sizeBytes":125,"sourceHtmlUrl":126},"references\u002Findex.md",263,"https:\u002F\u002Fgithub.com\u002FMishit18\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fai-research\u002Ffine-tuning-llama-factory\u002Freferences\u002Findex.md",{"path":128,"resourceType":87,"resourceTypeDesc":88,"sizeBytes":129,"sourceHtmlUrl":130},"references\u002Flarge-file-uploads.md",989,"https:\u002F\u002Fgithub.com\u002FTrollz1004\u002FANTIGRAVITY\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Freferences\u002Flarge-file-uploads.md",{"path":132,"resourceType":87,"resourceTypeDesc":88,"sizeBytes":133,"sourceHtmlUrl":134},"references\u002Fother.md",1167,"https:\u002F\u002Fgithub.com\u002FMishit18\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fai-research\u002Ffine-tuning-llama-factory\u002Freferences\u002Fother.md",{"path":136,"resourceType":87,"resourceTypeDesc":88,"sizeBytes":137,"sourceHtmlUrl":138},"references\u002Fplatform-gotchas.md",2069,"https:\u002F\u002Fgithub.com\u002FTrollz1004\u002FANTIGRAVITY\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Freferences\u002Fplatform-gotchas.md",{"path":140,"resourceType":87,"resourceTypeDesc":88,"sizeBytes":141,"sourceHtmlUrl":142},"references\u002Freward-hacking.md",3422,"https:\u002F\u002Fgithub.com\u002FTrollz1004\u002FANTIGRAVITY\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Freferences\u002Freward-hacking.md",{"path":144,"resourceType":87,"resourceTypeDesc":88,"sizeBytes":145,"sourceHtmlUrl":146},"references\u002Ftraining-curves.md",5284,"https:\u002F\u002Fgithub.com\u002FTrollz1004\u002FANTIGRAVITY\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Freferences\u002Ftraining-curves.md",{"path":148,"resourceType":87,"resourceTypeDesc":88,"sizeBytes":149,"sourceHtmlUrl":150},"references\u002Ftraining-types.md",3914,"https:\u002F\u002Fgithub.com\u002FTrollz1004\u002FANTIGRAVITY\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Freferences\u002Ftraining-types.md",{"path":152,"resourceType":87,"resourceTypeDesc":88,"sizeBytes":153,"sourceHtmlUrl":154},"references\u002Fvision-fine-tuning.md",5043,"https:\u002F\u002Fgithub.com\u002FTrollz1004\u002FANTIGRAVITY\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Freferences\u002Fvision-fine-tuning.md",{"path":156,"resourceType":157,"resourceTypeDesc":158,"sizeBytes":159,"sourceHtmlUrl":160},"scripts\u002Fcalibrate_grader.py","SCRIPT","脚本",9493,"https:\u002F\u002Fgithub.com\u002FTrollz1004\u002FANTIGRAVITY\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Fscripts\u002Fcalibrate_grader.py",{"path":162,"resourceType":157,"resourceTypeDesc":158,"sizeBytes":163,"sourceHtmlUrl":164},"scripts\u002Fcheck_training.py",7987,"https:\u002F\u002Fgithub.com\u002FTrollz1004\u002FANTIGRAVITY\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Fscripts\u002Fcheck_training.py",{"path":166,"resourceType":157,"resourceTypeDesc":158,"sizeBytes":167,"sourceHtmlUrl":168},"scripts\u002Fcleanup.py",9687,"https:\u002F\u002Fgithub.com\u002FTrollz1004\u002FANTIGRAVITY\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Fscripts\u002Fcleanup.py",{"path":170,"resourceType":157,"resourceTypeDesc":158,"sizeBytes":171,"sourceHtmlUrl":172},"scripts\u002Fcommon.py",7806,"https:\u002F\u002Fgithub.com\u002FTrollz1004\u002FANTIGRAVITY\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Fscripts\u002Fcommon.py",{"path":174,"resourceType":157,"resourceTypeDesc":158,"sizeBytes":175,"sourceHtmlUrl":176},"scripts\u002Fconvert_dataset.py",10936,"https:\u002F\u002Fgithub.com\u002FTrollz1004\u002FANTIGRAVITY\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Fscripts\u002Fconvert_dataset.py",{"path":178,"resourceType":157,"resourceTypeDesc":158,"sizeBytes":179,"sourceHtmlUrl":180},"scripts\u002Fdeploy_model.py",9616,"https:\u002F\u002Fgithub.com\u002FTrollz1004\u002FANTIGRAVITY\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Fscripts\u002Fdeploy_model.py",{"path":182,"resourceType":157,"resourceTypeDesc":158,"sizeBytes":183,"sourceHtmlUrl":184},"scripts\u002Fevaluate_model.py",11690,"https:\u002F\u002Fgithub.com\u002FTrollz1004\u002FANTIGRAVITY\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Fscripts\u002Fevaluate_model.py",{"path":186,"resourceType":157,"resourceTypeDesc":158,"sizeBytes":187,"sourceHtmlUrl":188},"scripts\u002Fgenerate_distillation_data.py",10299,"https:\u002F\u002Fgithub.com\u002FTrollz1004\u002FANTIGRAVITY\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Fscripts\u002Fgenerate_distillation_data.py",{"path":190,"resourceType":157,"resourceTypeDesc":158,"sizeBytes":191,"sourceHtmlUrl":192},"scripts\u002Fmonitor_training.py",5866,"https:\u002F\u002Fgithub.com\u002FTrollz1004\u002FANTIGRAVITY\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Fscripts\u002Fmonitor_training.py",{"path":194,"resourceType":157,"resourceTypeDesc":158,"sizeBytes":195,"sourceHtmlUrl":196},"scripts\u002Fscore_dataset.py",7873,"https:\u002F\u002Fgithub.com\u002FTrollz1004\u002FANTIGRAVITY\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Fscripts\u002Fscore_dataset.py",{"path":198,"resourceType":157,"resourceTypeDesc":158,"sizeBytes":199,"sourceHtmlUrl":200},"scripts\u002Fsubmit_training.py",11068,"https:\u002F\u002Fgithub.com\u002FTrollz1004\u002FANTIGRAVITY\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Fscripts\u002Fsubmit_training.py",{"path":202,"resourceType":157,"resourceTypeDesc":158,"sizeBytes":203,"sourceHtmlUrl":204},"scripts\u002Fvalidate\u002Fdata_stats.py",6331,"https:\u002F\u002Fgithub.com\u002FTrollz1004\u002FANTIGRAVITY\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Fscripts\u002Fvalidate\u002Fdata_stats.py",{"path":206,"resourceType":157,"resourceTypeDesc":158,"sizeBytes":207,"sourceHtmlUrl":208},"scripts\u002Fvalidate\u002Fvalidate_dpo.py",3806,"https:\u002F\u002Fgithub.com\u002FTrollz1004\u002FANTIGRAVITY\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Fscripts\u002Fvalidate\u002Fvalidate_dpo.py",{"path":210,"resourceType":157,"resourceTypeDesc":158,"sizeBytes":211,"sourceHtmlUrl":212},"scripts\u002Fvalidate\u002Fvalidate_rft.py",8797,"https:\u002F\u002Fgithub.com\u002FTrollz1004\u002FANTIGRAVITY\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Fscripts\u002Fvalidate\u002Fvalidate_rft.py",{"path":214,"resourceType":157,"resourceTypeDesc":158,"sizeBytes":215,"sourceHtmlUrl":216},"scripts\u002Fvalidate\u002Fvalidate_sft.py",4572,"https:\u002F\u002Fgithub.com\u002FTrollz1004\u002FANTIGRAVITY\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Fscripts\u002Fvalidate\u002Fvalidate_sft.py",{"path":218,"resourceType":87,"resourceTypeDesc":88,"sizeBytes":219,"sourceHtmlUrl":220},"workflows\u002Fdataset-creation.md",3166,"https:\u002F\u002Fgithub.com\u002FTrollz1004\u002FANTIGRAVITY\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Fworkflows\u002Fdataset-creation.md",{"path":222,"resourceType":87,"resourceTypeDesc":88,"sizeBytes":223,"sourceHtmlUrl":224},"workflows\u002Fdiagnose-poor-results.md",3602,"https:\u002F\u002Fgithub.com\u002FTrollz1004\u002FANTIGRAVITY\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Fworkflows\u002Fdiagnose-poor-results.md",{"path":226,"resourceType":87,"resourceTypeDesc":88,"sizeBytes":227,"sourceHtmlUrl":228},"workflows\u002Ffull-pipeline.md",3299,"https:\u002F\u002Fgithub.com\u002FTrollz1004\u002FANTIGRAVITY\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Fworkflows\u002Ffull-pipeline.md",{"path":230,"resourceType":87,"resourceTypeDesc":88,"sizeBytes":231,"sourceHtmlUrl":232},"workflows\u002Fiterative-training.md",3458,"https:\u002F\u002Fgithub.com\u002FTrollz1004\u002FANTIGRAVITY\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Fworkflows\u002Fiterative-training.md",{"path":234,"resourceType":87,"resourceTypeDesc":88,"sizeBytes":235,"sourceHtmlUrl":236},"workflows\u002Fquickstart.md",4601,"https:\u002F\u002Fgithub.com\u002FTrollz1004\u002FANTIGRAVITY\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fmicrosoft-foundry\u002Ffinetuning\u002Fworkflows\u002Fquickstart.md",[238,264,302,325,352,376],{"skillNo":239,"name":240,"nameZh":6,"description":241,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":242,"sourceHtmlUrl":243,"categories":244,"keywords":245,"publishedAt":54},"01M6M5BT49KEBHJM9D0P5NM8ED","security-audit","Security guidance and vulnerability review for codebases, APIs, services, CLI tools, libraries, and daemons. Use for security questions, focused reviews, vulnerability research, security audits, or pen tests. Run the complete workflow only for explicit codebase audit or pen-test requests, full\u002Fcomprehensive\u002Fend-to-end reviews, or requested report artifacts.","https:\u002F\u002Fgithub.com\u002FTrollz1004\u002FANTIGRAVITY\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fsecurity-audit\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FTrollz1004\u002FANTIGRAVITY\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fsecurity-audit\u002FSKILL.md",[],[246,247,248,249,250,251,252,253,254,255,256,257,258,259,26,260,261,262,263,35],"security audit","audit","security","reviews","end","only","workflow","vulnerability","review","libraries","cli","run","Tools","full","complete","security guidance","codebase audit","tests",{"skillNo":265,"name":266,"nameZh":6,"description":267,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":268,"licenseFileUrl":269,"sourceHtmlUrl":270,"categories":271,"keywords":283,"publishedAt":54},"01M6M5B16Q534MKFHKBHRZ2773","impeccable","Use when the user wants to design, redesign, shape, critique, audit, polish, simplify, harden, animate, or otherwise improve a frontend interface: websites, landing pages, dashboards, product UI, components, forms, settings, onboarding, empty states, and native iOS or Android screens. Handles UX review, hierarchy, layout, typography, color, motion, UX copy, accessibility, responsive behavior, edge cases, and capturing or documenting design systems (DESIGN.md, tokens). Also for making bland UI bolder, loud UI quieter, or ambitious visual effects. Not for backend-only or non-UI tasks.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FTrollz1004\u002FANTIGRAVITY\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fimpeccable\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FTrollz1004\u002FANTIGRAVITY\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fimpeccable\u002FSKILL.md",[272,275,278],{"categoryNo":273,"categoryName":274,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000009","前端开发",{"categoryNo":276,"categoryName":277,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":279,"categoryName":280,"taxonomyType":281,"taxonomyTypeDesc":282},"01JBSEEDCAT000000000000032","设计师","PROFESSION","适用职业",[266,284,285,286,287,288,289,290,251,291,292,293,294,295,254,296,297,298,299,300,301],"ux copy","states","quieter","frontend","improve","design","interface","design systems","effects","simplify","tasks","components","hierarchy","critique","native","product","layout","when",{"skillNo":303,"name":304,"nameZh":6,"description":305,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":306,"sourceHtmlUrl":307,"categories":308,"keywords":311,"publishedAt":54},"01M6M5AHHV2NPZYVMW48HP7A6H","hallmark","Design skill for websites and new pages that look designed, not generated. Use when the user asks to build or design something new, or names Hallmark. Never use it on an existing design unless the user names Hallmark, as in `\u002Fhallmark redesign \u003Cpath>`.","https:\u002F\u002Fgithub.com\u002FTrollz1004\u002FANTIGRAVITY\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fhallmark\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FTrollz1004\u002FANTIGRAVITY\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fhallmark\u002FSKILL.md",[309,310],{"categoryNo":276,"categoryName":277,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[304,312,313,26,314,315,289,316,35,317,37,318,247,319,320,321,322,323,324,301],"as","never","true","pages","generated","Existing","build","redesign","look","it","user","path","new",{"skillNo":326,"name":327,"nameZh":6,"description":328,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":268,"licenseFileUrl":329,"sourceHtmlUrl":330,"categories":331,"keywords":336,"publishedAt":54},"01M6CQDXJ785JCD5PMKYD239ZZ","webapp-testing","Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.","https:\u002F\u002Fgithub.com\u002FTrollz1004\u002FANTIGRAVITY\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwebapp-testing\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002FTrollz1004\u002FANTIGRAVITY\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwebapp-testing\u002FSKILL.md",[332,335],{"categoryNo":333,"categoryName":334,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":273,"categoryName":274,"taxonomyType":21,"taxonomyTypeDesc":22},[337,338,339,340,287,341,342,343,344,345,346,347,348,349,26,350,351],"webapp","testing","webapp testing","applications","debugging","toolkit","logs","browser","playwright","web","behavior","ui","screenshots","local","with",{"skillNo":353,"name":354,"nameZh":6,"description":355,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":356,"sourceHtmlUrl":357,"categories":358,"keywords":359,"publishedAt":54},"01M6CQ5HBDE9Q5WJZXQ7G72MYD","appinsights-instrumentation","Guidance for instrumenting webapps with Azure Application Insights. Provides telemetry patterns, SDK setup, and configuration references. USE FOR: how to instrument app, App Insights SDK, telemetry patterns, what is App Insights, Application Insights guidance, instrumentation examples, APM best practices. DO NOT USE FOR: adding App Insights to my app (use azure-prepare), add telemetry to my project (use azure-prepare), add monitoring (use azure-prepare). This skill provides guidance—azure-prepare orchestrates component changes.","https:\u002F\u002Fgithub.com\u002FTrollz1004\u002FANTIGRAVITY\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fappinsights-instrumentation\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002FTrollz1004\u002FANTIGRAVITY\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fappinsights-instrumentation\u002FSKILL.md",[],[360,361,32,51,362,35,363,364,365,366,367,368,369,370,371,372,373,374,375,26],"appinsights instrumentation","instrumentation","telemetry","monitoring","references","component","how","patterns","apm","sdk setup","app","project","insights","how to","my","add",{"skillNo":377,"name":378,"nameZh":6,"description":379,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":380,"categories":381,"keywords":395,"publishedAt":54},"01M6CQNQ5FNDP6K32RKXQ9X157","youtube-automation","YouTube automation: upload, SEO, thumbnails, scheduling, analytics.","https:\u002F\u002Fgithub.com\u002FTrollz1004\u002FANTIGRAVITY\u002Fblob\u002Fmain\u002Fops\u002Fskills\u002Fyoutube-automation\u002FSKILL.md",[382,385,388,389,392],{"categoryNo":383,"categoryName":384,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000013","分析与可视化",{"categoryNo":386,"categoryName":387,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000019","营销推广",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":390,"categoryName":391,"taxonomyType":281,"taxonomyTypeDesc":282},"01JBSEEDCAT000000000000033","数据分析师",{"categoryNo":393,"categoryName":394,"taxonomyType":281,"taxonomyTypeDesc":282},"01JBSEEDCAT000000000000035","市场营销",[396,397,398,399,400,401,402,403,404,405,406,407,408,409],"automation","youtube","youtube automation","windows","seo","linux","scheduling","thumbnails","hermes","analytics","hermes agent","content","macos","upload"]