[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7CVEGYG4PWMEN8ZBNDVS5QF":3,"skill-same:01M7CVEGYG4PWMEN8ZBNDVS5QF":184},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":27,"commitSha":28,"skillDirectory":29,"forksCount":14,"repositoryHtmlUrl":30,"repositoryHomepageUrl":6,"ownerHtmlUrl":31,"ownerBlogUrl":32,"ownerDescription":33,"updatedAt":34,"install":35,"resources":48},"01M7CVEGYG4PWMEN8ZBNDVS5QF","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).","Henrique1601\u002FSkiilsToIAs","Henrique1601","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F92006691?v=4","01M7CRXVT0GVXVK80JT1GR687S","Henrique Bezerra Dos Santos","01M7CRXVTN5Y8TMWJ1MDSKCQ1T",0,"MIT","https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Fdevops-cloud\u002Fmicrosoft-foundry\u002Ffinetuning\u002FSKILL.md",[],[],"2026-11-15 14:19:17",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- 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- 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":24,"description":7},{"author":25,"version":26},"Microsoft","0.0.0-placeholder","main","a73152352c0612252131e5cf84e91312a6cf17dc","devops-cloud\u002Fmicrosoft-foundry\u002Ffinetuning","https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs","https:\u002F\u002Fgithub.com\u002FHenrique1601","https:\u002F\u002Fbezerraportifolio.netlify.app\u002F","Full Stack Developer | React, Next.js, TypeScript, Node.js & IA | Construindo produtos digitais e soluções SaaS","2026-11-15 02:56:04",{"source":8,"skillName":5,"commands":36,"prompt":46,"zipAvailable":47},[37,40,43],{"tool":38,"command":39},"npx","npx skills add Henrique1601\u002FSkiilsToIAs --skill finetuning",{"tool":41,"command":42},"bunx","bunx skills add Henrique1601\u002FSkiilsToIAs --skill finetuning",{"tool":44,"command":45},"pnpm","pnpm dlx skills add Henrique1601\u002FSkiilsToIAs --skill finetuning","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Fdevops-cloud\u002Fmicrosoft-foundry\u002Ffinetuning\u002FSKILL.md",true,[49,55,59,63,67,71,74,78,82,86,90,94,98,104,108,112,116,120,124,128,132,136,140,144,148,152,156,160,164,168,172,176,180],{"path":50,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":53,"sourceHtmlUrl":54},"references\u002Fagentic-rft.md","REFERENCE","参考文档",3233,"https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Fdevops-cloud\u002Fmicrosoft-foundry\u002Ffinetuning\u002Freferences\u002Fagentic-rft.md",{"path":56,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":57,"sourceHtmlUrl":58},"references\u002Fdataset-formats.md",3740,"https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Fdevops-cloud\u002Fmicrosoft-foundry\u002Ffinetuning\u002Freferences\u002Fdataset-formats.md",{"path":60,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":61,"sourceHtmlUrl":62},"references\u002Fdeployment.md",3503,"https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Fdevops-cloud\u002Fmicrosoft-foundry\u002Ffinetuning\u002Freferences\u002Fdeployment.md",{"path":64,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":65,"sourceHtmlUrl":66},"references\u002Fevaluation.md",5924,"https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Fdevops-cloud\u002Fmicrosoft-foundry\u002Ffinetuning\u002Freferences\u002Fevaluation.md",{"path":68,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":69,"sourceHtmlUrl":70},"references\u002Fgrader-design.md",3437,"https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Fdevops-cloud\u002Fmicrosoft-foundry\u002Ffinetuning\u002Freferences\u002Fgrader-design.md",{"path":72,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":53,"sourceHtmlUrl":73},"references\u002Fhyperparameters.md","https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Fdevops-cloud\u002Fmicrosoft-foundry\u002Ffinetuning\u002Freferences\u002Fhyperparameters.md",{"path":75,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":76,"sourceHtmlUrl":77},"references\u002Flarge-file-uploads.md",927,"https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Fdevops-cloud\u002Fmicrosoft-foundry\u002Ffinetuning\u002Freferences\u002Flarge-file-uploads.md",{"path":79,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":80,"sourceHtmlUrl":81},"references\u002Fplatform-gotchas.md",2069,"https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Fdevops-cloud\u002Fmicrosoft-foundry\u002Ffinetuning\u002Freferences\u002Fplatform-gotchas.md",{"path":83,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":84,"sourceHtmlUrl":85},"references\u002Freward-hacking.md",2945,"https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Fdevops-cloud\u002Fmicrosoft-foundry\u002Ffinetuning\u002Freferences\u002Freward-hacking.md",{"path":87,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":88,"sourceHtmlUrl":89},"references\u002Ftraining-curves.md",4183,"https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Fdevops-cloud\u002Fmicrosoft-foundry\u002Ffinetuning\u002Freferences\u002Ftraining-curves.md",{"path":91,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":92,"sourceHtmlUrl":93},"references\u002Ftraining-types.md",3158,"https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Fdevops-cloud\u002Fmicrosoft-foundry\u002Ffinetuning\u002Freferences\u002Ftraining-types.md",{"path":95,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":96,"sourceHtmlUrl":97},"references\u002Fvision-fine-tuning.md",4205,"https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Fdevops-cloud\u002Fmicrosoft-foundry\u002Ffinetuning\u002Freferences\u002Fvision-fine-tuning.md",{"path":99,"resourceType":100,"resourceTypeDesc":101,"sizeBytes":102,"sourceHtmlUrl":103},"scripts\u002Fcalibrate_grader.py","SCRIPT","脚本",9493,"https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Fdevops-cloud\u002Fmicrosoft-foundry\u002Ffinetuning\u002Fscripts\u002Fcalibrate_grader.py",{"path":105,"resourceType":100,"resourceTypeDesc":101,"sizeBytes":106,"sourceHtmlUrl":107},"scripts\u002Fcheck_training.py",7987,"https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Fdevops-cloud\u002Fmicrosoft-foundry\u002Ffinetuning\u002Fscripts\u002Fcheck_training.py",{"path":109,"resourceType":100,"resourceTypeDesc":101,"sizeBytes":110,"sourceHtmlUrl":111},"scripts\u002Fcleanup.py",9687,"https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Fdevops-cloud\u002Fmicrosoft-foundry\u002Ffinetuning\u002Fscripts\u002Fcleanup.py",{"path":113,"resourceType":100,"resourceTypeDesc":101,"sizeBytes":114,"sourceHtmlUrl":115},"scripts\u002Fcommon.py",7806,"https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Fdevops-cloud\u002Fmicrosoft-foundry\u002Ffinetuning\u002Fscripts\u002Fcommon.py",{"path":117,"resourceType":100,"resourceTypeDesc":101,"sizeBytes":118,"sourceHtmlUrl":119},"scripts\u002Fconvert_dataset.py",10936,"https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Fdevops-cloud\u002Fmicrosoft-foundry\u002Ffinetuning\u002Fscripts\u002Fconvert_dataset.py",{"path":121,"resourceType":100,"resourceTypeDesc":101,"sizeBytes":122,"sourceHtmlUrl":123},"scripts\u002Fdeploy_model.py",9616,"https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Fdevops-cloud\u002Fmicrosoft-foundry\u002Ffinetuning\u002Fscripts\u002Fdeploy_model.py",{"path":125,"resourceType":100,"resourceTypeDesc":101,"sizeBytes":126,"sourceHtmlUrl":127},"scripts\u002Fevaluate_model.py",11690,"https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Fdevops-cloud\u002Fmicrosoft-foundry\u002Ffinetuning\u002Fscripts\u002Fevaluate_model.py",{"path":129,"resourceType":100,"resourceTypeDesc":101,"sizeBytes":130,"sourceHtmlUrl":131},"scripts\u002Fgenerate_distillation_data.py",10299,"https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Fdevops-cloud\u002Fmicrosoft-foundry\u002Ffinetuning\u002Fscripts\u002Fgenerate_distillation_data.py",{"path":133,"resourceType":100,"resourceTypeDesc":101,"sizeBytes":134,"sourceHtmlUrl":135},"scripts\u002Fmonitor_training.py",5866,"https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Fdevops-cloud\u002Fmicrosoft-foundry\u002Ffinetuning\u002Fscripts\u002Fmonitor_training.py",{"path":137,"resourceType":100,"resourceTypeDesc":101,"sizeBytes":138,"sourceHtmlUrl":139},"scripts\u002Fscore_dataset.py",7873,"https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Fdevops-cloud\u002Fmicrosoft-foundry\u002Ffinetuning\u002Fscripts\u002Fscore_dataset.py",{"path":141,"resourceType":100,"resourceTypeDesc":101,"sizeBytes":142,"sourceHtmlUrl":143},"scripts\u002Fsubmit_training.py",11068,"https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Fdevops-cloud\u002Fmicrosoft-foundry\u002Ffinetuning\u002Fscripts\u002Fsubmit_training.py",{"path":145,"resourceType":100,"resourceTypeDesc":101,"sizeBytes":146,"sourceHtmlUrl":147},"scripts\u002Fvalidate\u002F__init__.py",305,"https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Fdevops-cloud\u002Fmicrosoft-foundry\u002Ffinetuning\u002Fscripts\u002Fvalidate\u002F__init__.py",{"path":149,"resourceType":100,"resourceTypeDesc":101,"sizeBytes":150,"sourceHtmlUrl":151},"scripts\u002Fvalidate\u002Fdata_stats.py",6331,"https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Fdevops-cloud\u002Fmicrosoft-foundry\u002Ffinetuning\u002Fscripts\u002Fvalidate\u002Fdata_stats.py",{"path":153,"resourceType":100,"resourceTypeDesc":101,"sizeBytes":154,"sourceHtmlUrl":155},"scripts\u002Fvalidate\u002Fvalidate_dpo.py",3806,"https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Fdevops-cloud\u002Fmicrosoft-foundry\u002Ffinetuning\u002Fscripts\u002Fvalidate\u002Fvalidate_dpo.py",{"path":157,"resourceType":100,"resourceTypeDesc":101,"sizeBytes":158,"sourceHtmlUrl":159},"scripts\u002Fvalidate\u002Fvalidate_rft.py",8797,"https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Fdevops-cloud\u002Fmicrosoft-foundry\u002Ffinetuning\u002Fscripts\u002Fvalidate\u002Fvalidate_rft.py",{"path":161,"resourceType":100,"resourceTypeDesc":101,"sizeBytes":162,"sourceHtmlUrl":163},"scripts\u002Fvalidate\u002Fvalidate_sft.py",4572,"https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Fdevops-cloud\u002Fmicrosoft-foundry\u002Ffinetuning\u002Fscripts\u002Fvalidate\u002Fvalidate_sft.py",{"path":165,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":166,"sourceHtmlUrl":167},"workflows\u002Fdataset-creation.md",3161,"https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Fdevops-cloud\u002Fmicrosoft-foundry\u002Ffinetuning\u002Fworkflows\u002Fdataset-creation.md",{"path":169,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":170,"sourceHtmlUrl":171},"workflows\u002Fdiagnose-poor-results.md",2401,"https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Fdevops-cloud\u002Fmicrosoft-foundry\u002Ffinetuning\u002Fworkflows\u002Fdiagnose-poor-results.md",{"path":173,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":174,"sourceHtmlUrl":175},"workflows\u002Ffull-pipeline.md",3165,"https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Fdevops-cloud\u002Fmicrosoft-foundry\u002Ffinetuning\u002Fworkflows\u002Ffull-pipeline.md",{"path":177,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":178,"sourceHtmlUrl":179},"workflows\u002Fiterative-training.md",3178,"https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Fdevops-cloud\u002Fmicrosoft-foundry\u002Ffinetuning\u002Fworkflows\u002Fiterative-training.md",{"path":181,"resourceType":51,"resourceTypeDesc":52,"sizeBytes":182,"sourceHtmlUrl":183},"workflows\u002Fquickstart.md",4598,"https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Fdevops-cloud\u002Fmicrosoft-foundry\u002Ffinetuning\u002Fworkflows\u002Fquickstart.md",[185,192,199,207,214,221],{"skillNo":186,"name":187,"nameZh":6,"description":188,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":189,"categories":190,"keywords":191,"publishedAt":19},"01M7E2ANBW9V6AVX5JXNCEAWF8","rag-architect-agent","Agente Arquiteto de RAG, Embeddings & Busca Vetorial. Especialista em design e implementação de pipelines de Retrieval-Augmented Generation de alta fidelidade: chunking semântico, modelagem pgvector no PostgreSQL (Neon\u002FSupabase), busca híbrida (cosseno + BM25), reranking, validação via TypeSafe AI e filosofia Ponytail (anti-overengineering).","https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Fcustom-agents\u002Frag-architect-agent\u002FSKILL.md",[],[],{"skillNo":193,"name":194,"nameZh":6,"description":195,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":196,"categories":197,"keywords":198,"publishedAt":19},"01M7E29KKF8R02ZRGYE2MJM67G","rag-architecture-patterns","Padrões arquiteturais e implementação de pipelines RAG (Retrieval-Augmented Generation) de alta fidelidade para qualquer projeto ou sistema. Cobre chunking semântico, embeddings, busca híbrida (pgvector + BM25), reranking, validação via TypeSafe AI e filosofia Ponytail (anti-overengineering).","https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Fai-agents\u002Frag-architecture-patterns\u002FSKILL.md",[],[],{"skillNo":200,"name":201,"nameZh":6,"description":202,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":203,"licenseFileUrl":6,"sourceHtmlUrl":204,"categories":205,"keywords":206,"publishedAt":19},"01M7CWRA8E3BJ7CPY8N8EG28J1","skill-repair","Use this to fix and re-install agent skills that have failed installation.\nThis skill provides the necessary context and permissions to surgically update\nthe `manifest.json` after a fix has been applied.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Futilities\u002Fskill-repair\u002FSKILL.md",[],[],{"skillNo":208,"name":209,"nameZh":6,"description":210,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":211,"categories":212,"keywords":213,"publishedAt":19},"01M7CWR66FZP8FA47WVZ4Z2EXC","security-scan","Scan your Claude Code configuration (.claude\u002F directory) for security vulnerabilities, misconfigurations, and injection risks using AgentShield. Checks CLAUDE.md, settings.json, MCP servers, hooks, and agent definitions.","https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Futilities\u002Fsecurity-scan\u002FSKILL.md",[],[],{"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":220,"publishedAt":19},"01M7CWR0QPY58QPTR1P759TFNG","security-review","Use this skill when adding authentication, handling user input, working with secrets, creating API endpoints, or implementing payment\u002Fsensitive features. Provides comprehensive security checklist and patterns.","https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Futilities\u002Fsecurity-review\u002FSKILL.md",[],[],{"skillNo":222,"name":223,"nameZh":6,"description":224,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":225,"categories":226,"keywords":227,"publishedAt":19},"01M7CWQXCE40XWT4FZ3VWZFGDP","security-bounty-hunter","Hunt for exploitable, bounty-worthy security issues in repositories. Focuses on remotely reachable vulnerabilities that qualify for real reports instead of noisy local-only findings.","https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Futilities\u002Fsecurity-bounty-hunter\u002FSKILL.md",[],[]]