[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6PSMZ9NNKV4SWP4WNVSPYWM":3,"skill-same:01M6PSMZ9NNKV4SWP4WNVSPYWM":175},{"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":39,"linkOnly":40,"markdownContent":41,"markdownBody":42,"frontMatter":43,"refName":52,"commitSha":53,"skillDirectory":54,"forksCount":14,"repositoryHtmlUrl":55,"repositoryHomepageUrl":6,"ownerHtmlUrl":56,"ownerBlogUrl":57,"ownerDescription":6,"updatedAt":58,"install":59,"resources":72},"01M6PSMZ9NNKV4SWP4WNVSPYWM","tao-train-rtdetr",null,"RT-DETR (Real-Time DEtection TRansformer) for 2D object detection. Designed for real-time inference with competitive accuracy and supports distillation and quantization for deployment optimization. Use when training, evaluating, distilling, quantizing, exporting, or running inference for a TAO RT-DETR model. Trigger phrases include \"train RT-DETR\", \"real-time DETR\", \"low-latency object detection\", \"RT-DETR distillation \u002F quantization\".","headmktlucca-ui\u002Fneuroads-lp","headmktlucca-ui","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F247379838?v=4","01M6PDVAV6M1W96D1SR1PDF8CS","NeuroAds","01M6PDVAZ4P281GNDKD45CYTF5",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-train-rtdetr\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38],"train","tao train rtdetr","tao","time","training","deployment","2d","accuracy","for","competitive","trigger","latency","Optimization","docker","container","use","model","Bash","real-time","NVIDIA","2026-11-10 10:12:30",false,"---\nname: tao-train-rtdetr\ndescription: RT-DETR (Real-Time DEtection TRansformer) for 2D object detection. Designed for real-time inference with\n  competitive accuracy and supports distillation and quantization for deployment optimization. Use when training, evaluating,\n  distilling, quantizing, exporting, or running inference for a TAO RT-DETR model. Trigger phrases include \"train RT-DETR\",\n  \"real-time DETR\", \"low-latency object detection\", \"RT-DETR distillation \u002F quantization\".\nlicense: Apache-2.0\ncompatibility: Requires docker + nvidia-container-toolkit.\nmetadata:\n  version: \"0.1.0\"\n  author: NVIDIA Corporation\nallowed-tools: Read Bash\ntags:\n- object\n- detection\n---\n\n# RT-DETR\n\nRT-DETR (Real-Time DEtection TRansformer) for 2D object detection. Designed for real-time inference with competitive accuracy. Supports distillation and quantization for deployment optimization.\n\nSet model.pretrained_backbone_path for backbone weights or train.pretrained_model_path for full model.\n\nFor TAO Deploy TensorRT actions (`gen_trt_engine`, TensorRT `evaluate`, and TensorRT `inference`), read `references\u002Ftao-deploy-rtdetr.md` first. Deploy spec templates live in this skill's `references\u002F` folder with the `spec_template_deploy_*.yaml` prefix.\n\n## Dataclass Schemas\n\nGenerated TAO Core schemas are packaged in `schemas\u002F\u003Caction>.schema.json`, with `schemas\u002Fmanifest.json` listing available actions. Each generated schema also emits `references\u002Fspec_template_\u003Caction>.yaml` from the schema top-level `default` field. AutoML enablement is declared at the model layer in `references\u002Fskill_info.yaml` via `automl_enabled`. Runnable AutoML still requires `schemas\u002Ftrain.schema.json` and `references\u002Fspec_template_train.yaml` to exist and parse. Use the packaged train schema for `automl_default_parameters`, `automl_disabled_parameters`, defaults, min\u002Fmax bounds, enums, option weights, math conditions, dependencies, and popular parameters. Do not expect `~\u002Ftao-core` at runtime; maintainers regenerate schemas\u002Ftemplates before packaging the skill bank.\n\n## Train Action Policy\n\nThis model is AutoML-enabled at the model layer. Before handling any train-stage request, read `references\u002Fskill_info.yaml` and resolve the run override from either an explicit `automl_policy` value or the user's workflow request. Treat phrases like \"turn off AutoML\", \"disable AutoML\", \"no HPO\", or \"plain training\" as `automl_policy: off` for this run only; otherwise default to `auto`. When `automl_policy: auto`, `automl_enabled: true`, and both `schemas\u002Ftrain.schema.json` and `references\u002Fspec_template_train.yaml` are packaged, route the train action through `tao-skill-bank:tao-run-automl` by default with this model's `skill_dir`. Preserve workflow\u002Fapplication overrides for datasets, specs, output directories, GPU\u002Fplatform settings, parent checkpoints, and `automl_policy`. Use direct model training only when `automl_policy: off` or the packaged train schema\u002Ftemplate is missing; in the missing-schema case, report that AutoML is enabled but not runnable for this model until schemas are generated.\n\nNon-train actions such as `evaluate`, `inference`, `export`, and deploy flows stay in this model skill. The per-run `automl_policy` override does not change model metadata.\n\n## Training Requirements\n\n- **Dataset type:** object_detection\n- **Formats:** coco, coco_raw\n- **Monitoring metric:** val_mAP50\n\n### Per-Action Dataset Requirements\n\n| Action | Spec Key | Source | Files | List? |\n|---|---|---|---|---|\n| distill | dataset.train_data_sources | train_datasets | image_dir: images.tar.gz, json_file: annotations.json | Yes |\n| distill | dataset.val_data_sources | eval_dataset | image_dir: images.tar.gz, json_file: annotations.json | No |\n| evaluate | dataset.test_data_sources | eval_dataset | image_dir: images.tar.gz, json_file: annotations.json | No |\n| gen_trt_engine | gen_trt_engine.tensorrt.calibration.cal_image_dir | calibration_dataset | images.tar.gz | Yes |\n| inference | dataset.infer_data_sources | inference_dataset | image_dir: images.tar.gz, classmap: label_map.txt | No |\n| quantize | dataset.train_data_sources | train_datasets | image_dir: images.tar.gz, json_file: annotations.json | Yes |\n| quantize | dataset.val_data_sources | eval_dataset | image_dir: images.tar.gz, json_file: annotations.json | No |\n| quantize | dataset.quant_calibration_data_sources | train_datasets | image_dir: images.tar.gz, json_file: annotations.json | No |\n| train | dataset.train_data_sources | train_datasets | image_dir: images.tar.gz, json_file: annotations.json | Yes |\n| train | dataset.val_data_sources | eval_dataset | image_dir: images.tar.gz, json_file: annotations.json | No |\n\n### Typical Spec Overrides\n\nData source overrides are **mandatory for every action** — the agent MUST construct data source paths from the Per-Action Dataset Requirements table above and include them in `spec_overrides`.\n\n```python\nS3_TRAIN = \"s3:\u002F\u002Fbucket\u002Fdata\u002Ftrain\"\nS3_EVAL = \"s3:\u002F\u002Fbucket\u002Fdata\u002Feval\"\n```\n\n**train (mandatory data sources):**\n```python\n{\n    \"train.num_epochs\": 10,\n    \"train.checkpoint_interval\": 10,\n    \"train.validation_interval\": 10,\n    \"train.num_gpus\": 1,\n    \"dataset.num_classes\": \"\u003Cnum_classes> + 1\",\n    \"dataset.train_data_sources\": [{\"image_dir\": f\"{S3_TRAIN}\u002Fimages.tar.gz\", \"json_file\": f\"{S3_TRAIN}\u002Fannotations.json\"}],\n    \"dataset.val_data_sources\": {\"image_dir\": f\"{S3_EVAL}\u002Fimages.tar.gz\", \"json_file\": f\"{S3_EVAL}\u002Fannotations.json\"},\n}\n```\n\n**evaluate (mandatory data sources):**\n```python\n{\n    \"dataset.num_classes\": \"\u003Cnum_classes> + 1\",\n    \"dataset.test_data_sources\": {\"image_dir\": f\"{S3_EVAL}\u002Fimages.tar.gz\", \"json_file\": f\"{S3_EVAL}\u002Fannotations.json\"},\n}\n```\n\n**export:**\n```python\n{\n    \"dataset.num_classes\": \"\u003Cnum_classes> + 1\",\n    \"export.input_height\": 640,\n    \"export.input_width\": 640,\n}\n```\n\n**quantize (mandatory data sources):**\n```python\n{\n    \"dataset.num_classes\": \"\u003Cnum_classes> + 1\",\n    \"quantize.layers\": [\n        {\n            \"module_name\": \"*\",\n            \"weights\": {\n                \"dtype\": \"float8_e4m3fn\"\n            },\n            \"activations\": {\n                \"dtype\": \"float8_e4m3fn\"\n            }\n        }\n    ],\n    \"dataset.train_data_sources\": [{\"image_dir\": f\"{S3_TRAIN}\u002Fimages.tar.gz\", \"json_file\": f\"{S3_TRAIN}\u002Fannotations.json\"}],\n    \"dataset.val_data_sources\": {\"image_dir\": f\"{S3_EVAL}\u002Fimages.tar.gz\", \"json_file\": f\"{S3_EVAL}\u002Fannotations.json\"},\n    \"dataset.quant_calibration_data_sources\": {\"image_dir\": f\"{S3_TRAIN}\u002Fimages.tar.gz\", \"json_file\": f\"{S3_TRAIN}\u002Fannotations.json\"},\n}\n```\n\n**gen_trt_engine (mandatory data sources):**\n```python\n{\n    \"gen_trt_engine.tensorrt.data_type\": \"FP16\",\n    \"gen_trt_engine.tensorrt.calibration.cal_image_dir\": [f\"{S3_TRAIN}\u002Fimages.tar.gz\"],\n}\n```\n\n**inference (mandatory data sources):**\n```python\n{\n    \"dataset.num_classes\": \"\u003Cnum_classes> + 1\",\n    \"dataset.infer_data_sources\": {\"image_dir\": f\"{S3_EVAL}\u002Fimages.tar.gz\", \"classmap\": f\"{S3_EVAL}\u002Flabel_map.txt\"},\n}\n```\n\n**distill (mandatory data sources):**\n```python\n{\n    \"dataset.train_data_sources\": [{\"image_dir\": f\"{S3_TRAIN}\u002Fimages.tar.gz\", \"json_file\": f\"{S3_TRAIN}\u002Fannotations.json\"}],\n    \"dataset.val_data_sources\": {\"image_dir\": f\"{S3_EVAL}\u002Fimages.tar.gz\", \"json_file\": f\"{S3_EVAL}\u002Fannotations.json\"},\n}\n```\n## Eval Dataset\n\nOptional. Provides validation mAP at each checkpoint if supplied.\n\n## Important Parameters\n\n- **dataset.num_classes**: Number of classes. Default 80 (MSCOCO 80-class). Must match your dataset annotations.\n- **model.backbone**: Default resnet_50. Supported: ResNet variants, ConvNeXt, FAN, EfficientViT. RT-DETR is optimized for real-time with lighter backbones.\n- **train.optim.lr**: Learning rate. Default 1e-4 (lower than DINO's 2e-4). lr_backbone defaults to 1e-5.\n- **dataset.augmentation.train_spatial_size**: Training input size. Default [640, 640]. Smaller than DINO's multi-scale (up to 1333). Key to RT-DETR's speed.\n- **model.num_feature_levels**: Default 3 (vs DINO's 4). return_interm_indices is [1,2,3].\n- **train.enable_ema**: Exponential moving average. Default False. Enable for potentially smoother convergence.\n- **dataset.remap_mscoco_category**: Default False. Set True only for original MSCOCO dataset with 91-to-80 category ID remapping.\n\n## Multi-GPU \u002F Multi-Node\n\n**Launch method:** `torchrun` (LIGHTNING_EXCLUDED_NETWORK). The entrypoint runs `torchrun --nnodes=N --nproc-per-node=M train.py`, NOT plain `python`.\n\n| Spec Key | Description | Default |\n|----------|-------------|---------|\n| `train.num_gpus` | Number of GPUs per node | 1 |\n| `train.gpu_ids` | GPU device indices | [0] |\n| `train.num_nodes` | Number of nodes | 1 |\n| `train.distributed_strategy` | `ddp` or `fsdp` | `ddp` |\n\n- `CUDA_VISIBLE_DEVICES` is explicitly set (unlike Lightning-managed models which use `TAO_VISIBLE_DEVICES`)\n- `ddp` with activation checkpointing: `find_unused_parameters=False`\n- `ddp` without: `find_unused_parameters=True`\n- `fsdp` supported, forces FP16\n\n**Multi-node env vars** (set by orchestrator):\n\n| Variable | Purpose |\n|----------|---------|\n| `WORLD_SIZE` | Number of nodes (triggers multinode mode) |\n| `NODE_RANK` | This node's rank (0-indexed) |\n| `MASTER_ADDR` | Rank-0 node IP |\n| `MASTER_PORT` | Rank-0 port (default 29500) |\n| `NUM_GPU_PER_NODE` | GPUs per node (default: all visible) |\n\n**CRITICAL:** `NODE_RANK` is copied to `RANK` if `RANK` is unset. This is required for torchrun multinode.\n\n## Export \u002F TRT Defaults\n\n- Export input: 640x640, opset 17\n- TRT data types: FP32, FP16, INT8\n- TRT workspace: 1024 MB\n- TRT max_batch_size: 4\n\nFull TAO Deploy reference: [tao-deploy-rtdetr](references\u002Ftao-deploy-rtdetr.md).\n\n## Distillation\n\nRT-DETR supports knowledge distillation with a teacher model. Requires `distill` action with teacher model path and distillation bindings configuration.\n\n## Hardware\n\nMinimum 1 GPU(s), recommended 2 GPU(s). 16GB+ (V100 or A100) VRAM per GPU. RT-DETR is more memory-efficient than DINO\u002FGDINO due to smaller input size (640x640) and fewer feature levels. Trains well on single GPU for small-medium datasets.\n\n## Error Patterns\n\n**CUDA out of memory**: Reduce batch_size. RT-DETR at 640x640 is lighter than DINO at 1333px, but batch_size > 8 may still OOM on 16GB GPUs.\n\n**num_classes mismatch**: RT-DETR defaults to 80 (not 91 like DINO). Ensure dataset.num_classes matches your annotation categories.\n\n**return_interm_indices vs num_feature_levels**: Default is [1,2,3] with num_feature_levels=3. Must be consistent if changed.\n\n## Spec Param \u002F Parent Model Inference\n\nModel-specific inference mappings belong in this MD file, not in `config.json`. Generated runners should read this section and apply the mappings with SDK helpers before `create_job()`. This mirrors the old microservices `infer_params.py` flow.\n\nInference mappings from TAO Core `rtdetr.config.json`:\n\n| Action | Spec Field | Inference Function | Meaning |\n|---|---|---|---|\n| distill | `distill.pretrained_teacher_model_path` | `parent_model` | model file inferred from the parent job results folder |\n| distill | `encryption_key` | `key` | encryption key |\n| distill | `results_dir` | `output_dir` | current job results directory |\n| evaluate | `encryption_key` | `key` | encryption key |\n| evaluate | `evaluate.checkpoint` | `parent_model` | model file inferred from the parent job results folder |\n| evaluate | `evaluate.trt_engine` | `parent_model` | model file inferred from the parent job results folder |\n| evaluate | `results_dir` | `output_dir` | current job results directory |\n| export | `encryption_key` | `key` | encryption key |\n| export | `export.checkpoint` | `parent_model` | model file inferred from the parent job results folder |\n| export | `export.onnx_file` | `create_onnx_file` | output ONNX path |\n| export | `results_dir` | `output_dir` | current job results directory |\n| gen_trt_engine | `encryption_key` | `key` | encryption key |\n| gen_trt_engine | `gen_trt_engine.onnx_file` | `parent_model` | model file inferred from the parent job results folder |\n| gen_trt_engine | `gen_trt_engine.tensorrt.calibration.cal_cache_file` | `create_cal_cache` | calibration cache path |\n| gen_trt_engine | `gen_trt_engine.trt_engine` | `create_engine_file` | output TensorRT engine path |\n| gen_trt_engine | `results_dir` | `output_dir` | current job results directory |\n| inference | `encryption_key` | `key` | encryption key |\n| inference | `inference.checkpoint` | `parent_model` | model file inferred from the parent job results folder |\n| inference | `inference.trt_engine` | `parent_model` | model file inferred from the parent job results folder |\n| inference | `results_dir` | `output_dir` | current job results directory |\n| quantize | `encryption_key` | `key` | encryption key |\n| quantize | `quantize.model_path` | `parent_model` | model file inferred from the parent job results folder |\n| quantize | `results_dir` | `output_dir` | current job results directory |\n| train | `encryption_key` | `key` | encryption key |\n| train | `model.pretrained_backbone_path` | `ptm_if_no_resume_model` | PTM when no resume checkpoint exists |\n| train | `results_dir` | `output_dir` | current job results directory |\n| train | `train.pretrained_model_path` | `ptm_if_no_resume_model` | PTM when no resume checkpoint exists |\n| train | `train.resume_training_checkpoint_path` | `resume_model` | model file inferred from the current job results folder |\n\nFor `parent_model` or `parent_model_folder`, pass the upstream train\u002Fexport\u002FAutoML child job id as `parent_job_id`. The SDK lists the parent result folder, filters checkpoint artifacts, and returns the selected model file or folder. Do not add these mappings back to `config.json` and do not patch generated runner scripts to guess checkpoint paths.\n","# RT-DETR\n\nRT-DETR (Real-Time DEtection TRansformer) for 2D object detection. Designed for real-time inference with competitive accuracy. Supports distillation and quantization for deployment optimization.\n\nSet model.pretrained_backbone_path for backbone weights or train.pretrained_model_path for full model.\n\nFor TAO Deploy TensorRT actions (`gen_trt_engine`, TensorRT `evaluate`, and TensorRT `inference`), read `references\u002Ftao-deploy-rtdetr.md` first. Deploy spec templates live in this skill's `references\u002F` folder with the `spec_template_deploy_*.yaml` prefix.\n\n## Dataclass Schemas\n\nGenerated TAO Core schemas are packaged in `schemas\u002F\u003Caction>.schema.json`, with `schemas\u002Fmanifest.json` listing available actions. Each generated schema also emits `references\u002Fspec_template_\u003Caction>.yaml` from the schema top-level `default` field. AutoML enablement is declared at the model layer in `references\u002Fskill_info.yaml` via `automl_enabled`. Runnable AutoML still requires `schemas\u002Ftrain.schema.json` and `references\u002Fspec_template_train.yaml` to exist and parse. Use the packaged train schema for `automl_default_parameters`, `automl_disabled_parameters`, defaults, min\u002Fmax bounds, enums, option weights, math conditions, dependencies, and popular parameters. Do not expect `~\u002Ftao-core` at runtime; maintainers regenerate schemas\u002Ftemplates before packaging the skill bank.\n\n## Train Action Policy\n\nThis model is AutoML-enabled at the model layer. Before handling any train-stage request, read `references\u002Fskill_info.yaml` and resolve the run override from either an explicit `automl_policy` value or the user's workflow request. Treat phrases like \"turn off AutoML\", \"disable AutoML\", \"no HPO\", or \"plain training\" as `automl_policy: off` for this run only; otherwise default to `auto`. When `automl_policy: auto`, `automl_enabled: true`, and both `schemas\u002Ftrain.schema.json` and `references\u002Fspec_template_train.yaml` are packaged, route the train action through `tao-skill-bank:tao-run-automl` by default with this model's `skill_dir`. Preserve workflow\u002Fapplication overrides for datasets, specs, output directories, GPU\u002Fplatform settings, parent checkpoints, and `automl_policy`. Use direct model training only when `automl_policy: off` or the packaged train schema\u002Ftemplate is missing; in the missing-schema case, report that AutoML is enabled but not runnable for this model until schemas are generated.\n\nNon-train actions such as `evaluate`, `inference`, `export`, and deploy flows stay in this model skill. The per-run `automl_policy` override does not change model metadata.\n\n## Training Requirements\n\n- **Dataset type:** object_detection\n- **Formats:** coco, coco_raw\n- **Monitoring metric:** val_mAP50\n\n### Per-Action Dataset Requirements\n\n| Action | Spec Key | Source | Files | List? |\n|---|---|---|---|---|\n| distill | dataset.train_data_sources | train_datasets | image_dir: images.tar.gz, json_file: annotations.json | Yes |\n| distill | dataset.val_data_sources | eval_dataset | image_dir: images.tar.gz, json_file: annotations.json | No |\n| evaluate | dataset.test_data_sources | eval_dataset | image_dir: images.tar.gz, json_file: annotations.json | No |\n| gen_trt_engine | gen_trt_engine.tensorrt.calibration.cal_image_dir | calibration_dataset | images.tar.gz | Yes |\n| inference | dataset.infer_data_sources | inference_dataset | image_dir: images.tar.gz, classmap: label_map.txt | No |\n| quantize | dataset.train_data_sources | train_datasets | image_dir: images.tar.gz, json_file: annotations.json | Yes |\n| quantize | dataset.val_data_sources | eval_dataset | image_dir: images.tar.gz, json_file: annotations.json | No |\n| quantize | dataset.quant_calibration_data_sources | train_datasets | image_dir: images.tar.gz, json_file: annotations.json | No |\n| train | dataset.train_data_sources | train_datasets | image_dir: images.tar.gz, json_file: annotations.json | Yes |\n| train | dataset.val_data_sources | eval_dataset | image_dir: images.tar.gz, json_file: annotations.json | No |\n\n### Typical Spec Overrides\n\nData source overrides are **mandatory for every action** — the agent MUST construct data source paths from the Per-Action Dataset Requirements table above and include them in `spec_overrides`.\n\n```python\nS3_TRAIN = \"s3:\u002F\u002Fbucket\u002Fdata\u002Ftrain\"\nS3_EVAL = \"s3:\u002F\u002Fbucket\u002Fdata\u002Feval\"\n```\n\n**train (mandatory data sources):**\n```python\n{\n    \"train.num_epochs\": 10,\n    \"train.checkpoint_interval\": 10,\n    \"train.validation_interval\": 10,\n    \"train.num_gpus\": 1,\n    \"dataset.num_classes\": \"\u003Cnum_classes> + 1\",\n    \"dataset.train_data_sources\": [{\"image_dir\": f\"{S3_TRAIN}\u002Fimages.tar.gz\", \"json_file\": f\"{S3_TRAIN}\u002Fannotations.json\"}],\n    \"dataset.val_data_sources\": {\"image_dir\": f\"{S3_EVAL}\u002Fimages.tar.gz\", \"json_file\": f\"{S3_EVAL}\u002Fannotations.json\"},\n}\n```\n\n**evaluate (mandatory data sources):**\n```python\n{\n    \"dataset.num_classes\": \"\u003Cnum_classes> + 1\",\n    \"dataset.test_data_sources\": {\"image_dir\": f\"{S3_EVAL}\u002Fimages.tar.gz\", \"json_file\": f\"{S3_EVAL}\u002Fannotations.json\"},\n}\n```\n\n**export:**\n```python\n{\n    \"dataset.num_classes\": \"\u003Cnum_classes> + 1\",\n    \"export.input_height\": 640,\n    \"export.input_width\": 640,\n}\n```\n\n**quantize (mandatory data sources):**\n```python\n{\n    \"dataset.num_classes\": \"\u003Cnum_classes> + 1\",\n    \"quantize.layers\": [\n        {\n            \"module_name\": \"*\",\n            \"weights\": {\n                \"dtype\": \"float8_e4m3fn\"\n            },\n            \"activations\": {\n                \"dtype\": \"float8_e4m3fn\"\n            }\n        }\n    ],\n    \"dataset.train_data_sources\": [{\"image_dir\": f\"{S3_TRAIN}\u002Fimages.tar.gz\", \"json_file\": f\"{S3_TRAIN}\u002Fannotations.json\"}],\n    \"dataset.val_data_sources\": {\"image_dir\": f\"{S3_EVAL}\u002Fimages.tar.gz\", \"json_file\": f\"{S3_EVAL}\u002Fannotations.json\"},\n    \"dataset.quant_calibration_data_sources\": {\"image_dir\": f\"{S3_TRAIN}\u002Fimages.tar.gz\", \"json_file\": f\"{S3_TRAIN}\u002Fannotations.json\"},\n}\n```\n\n**gen_trt_engine (mandatory data sources):**\n```python\n{\n    \"gen_trt_engine.tensorrt.data_type\": \"FP16\",\n    \"gen_trt_engine.tensorrt.calibration.cal_image_dir\": [f\"{S3_TRAIN}\u002Fimages.tar.gz\"],\n}\n```\n\n**inference (mandatory data sources):**\n```python\n{\n    \"dataset.num_classes\": \"\u003Cnum_classes> + 1\",\n    \"dataset.infer_data_sources\": {\"image_dir\": f\"{S3_EVAL}\u002Fimages.tar.gz\", \"classmap\": f\"{S3_EVAL}\u002Flabel_map.txt\"},\n}\n```\n\n**distill (mandatory data sources):**\n```python\n{\n    \"dataset.train_data_sources\": [{\"image_dir\": f\"{S3_TRAIN}\u002Fimages.tar.gz\", \"json_file\": f\"{S3_TRAIN}\u002Fannotations.json\"}],\n    \"dataset.val_data_sources\": {\"image_dir\": f\"{S3_EVAL}\u002Fimages.tar.gz\", \"json_file\": f\"{S3_EVAL}\u002Fannotations.json\"},\n}\n```\n## Eval Dataset\n\nOptional. Provides validation mAP at each checkpoint if supplied.\n\n## Important Parameters\n\n- **dataset.num_classes**: Number of classes. Default 80 (MSCOCO 80-class). Must match your dataset annotations.\n- **model.backbone**: Default resnet_50. Supported: ResNet variants, ConvNeXt, FAN, EfficientViT. RT-DETR is optimized for real-time with lighter backbones.\n- **train.optim.lr**: Learning rate. Default 1e-4 (lower than DINO's 2e-4). lr_backbone defaults to 1e-5.\n- **dataset.augmentation.train_spatial_size**: Training input size. Default [640, 640]. Smaller than DINO's multi-scale (up to 1333). Key to RT-DETR's speed.\n- **model.num_feature_levels**: Default 3 (vs DINO's 4). return_interm_indices is [1,2,3].\n- **train.enable_ema**: Exponential moving average. Default False. Enable for potentially smoother convergence.\n- **dataset.remap_mscoco_category**: Default False. Set True only for original MSCOCO dataset with 91-to-80 category ID remapping.\n\n## Multi-GPU \u002F Multi-Node\n\n**Launch method:** `torchrun` (LIGHTNING_EXCLUDED_NETWORK). The entrypoint runs `torchrun --nnodes=N --nproc-per-node=M train.py`, NOT plain `python`.\n\n| Spec Key | Description | Default |\n|----------|-------------|---------|\n| `train.num_gpus` | Number of GPUs per node | 1 |\n| `train.gpu_ids` | GPU device indices | [0] |\n| `train.num_nodes` | Number of nodes | 1 |\n| `train.distributed_strategy` | `ddp` or `fsdp` | `ddp` |\n\n- `CUDA_VISIBLE_DEVICES` is explicitly set (unlike Lightning-managed models which use `TAO_VISIBLE_DEVICES`)\n- `ddp` with activation checkpointing: `find_unused_parameters=False`\n- `ddp` without: `find_unused_parameters=True`\n- `fsdp` supported, forces FP16\n\n**Multi-node env vars** (set by orchestrator):\n\n| Variable | Purpose |\n|----------|---------|\n| `WORLD_SIZE` | Number of nodes (triggers multinode mode) |\n| `NODE_RANK` | This node's rank (0-indexed) |\n| `MASTER_ADDR` | Rank-0 node IP |\n| `MASTER_PORT` | Rank-0 port (default 29500) |\n| `NUM_GPU_PER_NODE` | GPUs per node (default: all visible) |\n\n**CRITICAL:** `NODE_RANK` is copied to `RANK` if `RANK` is unset. This is required for torchrun multinode.\n\n## Export \u002F TRT Defaults\n\n- Export input: 640x640, opset 17\n- TRT data types: FP32, FP16, INT8\n- TRT workspace: 1024 MB\n- TRT max_batch_size: 4\n\nFull TAO Deploy reference: [tao-deploy-rtdetr](references\u002Ftao-deploy-rtdetr.md).\n\n## Distillation\n\nRT-DETR supports knowledge distillation with a teacher model. Requires `distill` action with teacher model path and distillation bindings configuration.\n\n## Hardware\n\nMinimum 1 GPU(s), recommended 2 GPU(s). 16GB+ (V100 or A100) VRAM per GPU. RT-DETR is more memory-efficient than DINO\u002FGDINO due to smaller input size (640x640) and fewer feature levels. Trains well on single GPU for small-medium datasets.\n\n## Error Patterns\n\n**CUDA out of memory**: Reduce batch_size. RT-DETR at 640x640 is lighter than DINO at 1333px, but batch_size > 8 may still OOM on 16GB GPUs.\n\n**num_classes mismatch**: RT-DETR defaults to 80 (not 91 like DINO). Ensure dataset.num_classes matches your annotation categories.\n\n**return_interm_indices vs num_feature_levels**: Default is [1,2,3] with num_feature_levels=3. Must be consistent if changed.\n\n## Spec Param \u002F Parent Model Inference\n\nModel-specific inference mappings belong in this MD file, not in `config.json`. Generated runners should read this section and apply the mappings with SDK helpers before `create_job()`. This mirrors the old microservices `infer_params.py` flow.\n\nInference mappings from TAO Core `rtdetr.config.json`:\n\n| Action | Spec Field | Inference Function | Meaning |\n|---|---|---|---|\n| distill | `distill.pretrained_teacher_model_path` | `parent_model` | model file inferred from the parent job results folder |\n| distill | `encryption_key` | `key` | encryption key |\n| distill | `results_dir` | `output_dir` | current job results directory |\n| evaluate | `encryption_key` | `key` | encryption key |\n| evaluate | `evaluate.checkpoint` | `parent_model` | model file inferred from the parent job results folder |\n| evaluate | `evaluate.trt_engine` | `parent_model` | model file inferred from the parent job results folder |\n| evaluate | `results_dir` | `output_dir` | current job results directory |\n| export | `encryption_key` | `key` | encryption key |\n| export | `export.checkpoint` | `parent_model` | model file inferred from the parent job results folder |\n| export | `export.onnx_file` | `create_onnx_file` | output ONNX path |\n| export | `results_dir` | `output_dir` | current job results directory |\n| gen_trt_engine | `encryption_key` | `key` | encryption key |\n| gen_trt_engine | `gen_trt_engine.onnx_file` | `parent_model` | model file inferred from the parent job results folder |\n| gen_trt_engine | `gen_trt_engine.tensorrt.calibration.cal_cache_file` | `create_cal_cache` | calibration cache path |\n| gen_trt_engine | `gen_trt_engine.trt_engine` | `create_engine_file` | output TensorRT engine path |\n| gen_trt_engine | `results_dir` | `output_dir` | current job results directory |\n| inference | `encryption_key` | `key` | encryption key |\n| inference | `inference.checkpoint` | `parent_model` | model file inferred from the parent job results folder |\n| inference | `inference.trt_engine` | `parent_model` | model file inferred from the parent job results folder |\n| inference | `results_dir` | `output_dir` | current job results directory |\n| quantize | `encryption_key` | `key` | encryption key |\n| quantize | `quantize.model_path` | `parent_model` | model file inferred from the parent job results folder |\n| quantize | `results_dir` | `output_dir` | current job results directory |\n| train | `encryption_key` | `key` | encryption key |\n| train | `model.pretrained_backbone_path` | `ptm_if_no_resume_model` | PTM when no resume checkpoint exists |\n| train | `results_dir` | `output_dir` | current job results directory |\n| train | `train.pretrained_model_path` | `ptm_if_no_resume_model` | PTM when no resume checkpoint exists |\n| train | `train.resume_training_checkpoint_path` | `resume_model` | model file inferred from the current job results folder |\n\nFor `parent_model` or `parent_model_folder`, pass the upstream train\u002Fexport\u002FAutoML child job id as `parent_job_id`. The SDK lists the parent result folder, filters checkpoint artifacts, and returns the selected model file or folder. Do not add these mappings back to `config.json` and do not patch generated runner scripts to guess checkpoint paths.\n",{"name":5,"tags":44,"license":15,"metadata":47,"description":7,"allowed-tools":50,"compatibility":51},[45,46],"object","detection",{"author":48,"version":49},"NVIDIA Corporation","0.1.0","Read Bash","Requires docker + nvidia-container-toolkit.","main","7a940b8e5af16c95e5c190a524421d32fc7445a9",".claude\u002Fskills\u002Ftao-train-rtdetr","https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp","https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui","https:\u002F\u002Fneuroads.com.br","2026-08-12 00:42:44",{"source":8,"skillName":5,"commands":60,"prompt":70,"zipAvailable":71},[61,64,67],{"tool":62,"command":63},"npx","npx skills add headmktlucca-ui\u002Fneuroads-lp --skill tao-train-rtdetr",{"tool":65,"command":66},"bunx","bunx skills add headmktlucca-ui\u002Fneuroads-lp --skill tao-train-rtdetr",{"tool":68,"command":69},"pnpm","pnpm dlx skills add headmktlucca-ui\u002Fneuroads-lp --skill tao-train-rtdetr","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-train-rtdetr\u002FSKILL.md",true,[73,79,83,87,91,95,99,103,107,111,115,119,122,125,129,133,137,141,145,149,153,157,161,165,169],{"path":74,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":77,"sourceHtmlUrl":78},"BENCHMARK.md","REFERENCE","参考文档",4374,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-train-rtdetr\u002FBENCHMARK.md",{"path":80,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":81,"sourceHtmlUrl":82},"evals\u002Fevals.json",741,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-train-rtdetr\u002Fevals\u002Fevals.json",{"path":84,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":85,"sourceHtmlUrl":86},"references\u002Fskill_info.yaml",2089,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-train-rtdetr\u002Freferences\u002Fskill_info.yaml",{"path":88,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":89,"sourceHtmlUrl":90},"references\u002Fspec_template_deploy_evaluate.yaml",473,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-train-rtdetr\u002Freferences\u002Fspec_template_deploy_evaluate.yaml",{"path":92,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":93,"sourceHtmlUrl":94},"references\u002Fspec_template_deploy_gen_trt_engine.yaml",733,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-train-rtdetr\u002Freferences\u002Fspec_template_deploy_gen_trt_engine.yaml",{"path":96,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":97,"sourceHtmlUrl":98},"references\u002Fspec_template_deploy_inference.yaml",483,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-train-rtdetr\u002Freferences\u002Fspec_template_deploy_inference.yaml",{"path":100,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":101,"sourceHtmlUrl":102},"references\u002Fspec_template_distill.yaml",2966,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-train-rtdetr\u002Freferences\u002Fspec_template_distill.yaml",{"path":104,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":105,"sourceHtmlUrl":106},"references\u002Fspec_template_evaluate.yaml",3136,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-train-rtdetr\u002Freferences\u002Fspec_template_evaluate.yaml",{"path":108,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":109,"sourceHtmlUrl":110},"references\u002Fspec_template_export.yaml",3233,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-train-rtdetr\u002Freferences\u002Fspec_template_export.yaml",{"path":112,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":113,"sourceHtmlUrl":114},"references\u002Fspec_template_gen_trt_engine.yaml",3361,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-train-rtdetr\u002Freferences\u002Fspec_template_gen_trt_engine.yaml",{"path":116,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":117,"sourceHtmlUrl":118},"references\u002Fspec_template_inference.yaml",3216,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-train-rtdetr\u002Freferences\u002Fspec_template_inference.yaml",{"path":120,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":101,"sourceHtmlUrl":121},"references\u002Fspec_template_quantize.yaml","https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-train-rtdetr\u002Freferences\u002Fspec_template_quantize.yaml",{"path":123,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":101,"sourceHtmlUrl":124},"references\u002Fspec_template_train.yaml","https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-train-rtdetr\u002Freferences\u002Fspec_template_train.yaml",{"path":126,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":127,"sourceHtmlUrl":128},"references\u002Ftao-deploy-rtdetr.md",5164,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-train-rtdetr\u002Freferences\u002Ftao-deploy-rtdetr.md",{"path":130,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":131,"sourceHtmlUrl":132},"references\u002Ftao-deploy-rtdetr.skill_info.yaml",2194,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-train-rtdetr\u002Freferences\u002Ftao-deploy-rtdetr.skill_info.yaml",{"path":134,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":135,"sourceHtmlUrl":136},"schemas\u002Fdistill.schema.json",51766,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-train-rtdetr\u002Fschemas\u002Fdistill.schema.json",{"path":138,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":139,"sourceHtmlUrl":140},"schemas\u002Fevaluate.schema.json",55417,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-train-rtdetr\u002Fschemas\u002Fevaluate.schema.json",{"path":142,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":143,"sourceHtmlUrl":144},"schemas\u002Fexport.schema.json",55982,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-train-rtdetr\u002Fschemas\u002Fexport.schema.json",{"path":146,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":147,"sourceHtmlUrl":148},"schemas\u002Fgen_trt_engine.schema.json",60313,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-train-rtdetr\u002Fschemas\u002Fgen_trt_engine.schema.json",{"path":150,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":151,"sourceHtmlUrl":152},"schemas\u002Finference.schema.json",56357,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-train-rtdetr\u002Fschemas\u002Finference.schema.json",{"path":154,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":155,"sourceHtmlUrl":156},"schemas\u002Fmanifest.json",21415,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-train-rtdetr\u002Fschemas\u002Fmanifest.json",{"path":158,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":159,"sourceHtmlUrl":160},"schemas\u002Fquantize.schema.json",51768,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-train-rtdetr\u002Fschemas\u002Fquantize.schema.json",{"path":162,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":163,"sourceHtmlUrl":164},"schemas\u002Ftrain.schema.json",51762,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-train-rtdetr\u002Fschemas\u002Ftrain.schema.json",{"path":166,"resourceType":75,"resourceTypeDesc":76,"sizeBytes":167,"sourceHtmlUrl":168},"skill-card.md",3841,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-train-rtdetr\u002Fskill-card.md",{"path":170,"resourceType":171,"resourceTypeDesc":172,"sizeBytes":173,"sourceHtmlUrl":174},"skill.oms.sig","OTHER","其他",9841,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-train-rtdetr\u002Fskill.oms.sig",[176,202,226,252,270,305],{"skillNo":177,"name":178,"nameZh":6,"description":179,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":180,"licenseFileUrl":6,"sourceHtmlUrl":181,"categories":182,"keywords":191,"publishedAt":39},"01M6PTDCZTXTGSTX4RFK901YSZ","xunit-skill","Generates xUnit.net tests in C#. Covers Fact\u002FTheory, constructor injection, IClassFixture, and FluentAssertions. Use when user mentions \"xUnit\", \"[Fact]\", \"[Theory]\", \"Assert.Equal\", \"C# xUnit\". Triggers on: \"xUnit\", \"[Fact]\", \"[Theory]\", \"Assert.Equal C#\", \"xUnit.net\".","MIT","https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fxunit-skill\u002FSKILL.md",[183,188],{"categoryNo":184,"categoryName":185,"taxonomyType":186,"taxonomyTypeDesc":187},"01JBSEEDCAT000000000000008","测试与质量","SCENARIO","使用场景",{"categoryNo":189,"categoryName":190,"taxonomyType":186,"taxonomyTypeDesc":187},"01JBSEEDCAT000000000000023","Skill与智能体开发",[192,193,194,195,196,34,197,198,199,200,201],"xunit","xunit skill","testing","injection","user","tests","triggers","unit","unit-testing","C#",{"skillNo":203,"name":204,"nameZh":6,"description":205,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":180,"licenseFileUrl":6,"sourceHtmlUrl":206,"categories":207,"keywords":210,"publishedAt":39},"01M6PTCB59ZTG5FTMWGPYEMMBP","xcuitest-skill","Generates XCUITest UI tests for iOS\u002FiPadOS apps in Swift. Apple's native testing framework for reliable, fast UI automation. Supports local simulators and TestMu AI cloud real devices. Use when user mentions \"XCUITest\", \"XCTest\", \"iOS UI test\", \"Swift test\", \"XCUIApplication\". Triggers on: \"XCUITest\", \"XCTest UI\", \"iOS UI test\", \"Swift UI test\", \"XCUIApplication\", \"TestMu\".","https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fxcuitest-skill\u002FSKILL.md",[208,209],{"categoryNo":184,"categoryName":185,"taxonomyType":186,"taxonomyTypeDesc":187},{"categoryNo":189,"categoryName":190,"taxonomyType":186,"taxonomyTypeDesc":187},[211,212,194,213,214,215,216,217,34,218,219,220,221,222,197,198,223,224,27,225],"xcuitest","xcuitest skill","automation","test","testing framework","ios","devices","mobile","mobile-testing","ui test","local","apple","apps","native","objective",{"skillNo":227,"name":228,"nameZh":6,"description":229,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":180,"licenseFileUrl":6,"sourceHtmlUrl":230,"categories":231,"keywords":236,"publishedAt":39},"01M6PTATMNTY9NF4J7KSR76YK6","world-builder","Create and manage generative game zones for Dorothy's Pokemon-style world. Use this skill when creating, updating, or designing game worlds via MCP tools.","https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fworld-builder\u002FSKILL.md",[232,235],{"categoryNo":233,"categoryName":234,"taxonomyType":186,"taxonomyTypeDesc":187},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":189,"categoryName":190,"taxonomyType":186,"taxonomyTypeDesc":187},[237,238,239,240,241,242,243,244,34,245,246,247,248,249,250,27,251],"builder","world","world builder","MCP","create","mcp tools","Tools","game","pokemon","manage","style","via","theme","zone","generative",{"skillNo":253,"name":254,"nameZh":6,"description":255,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":180,"licenseFileUrl":6,"sourceHtmlUrl":256,"categories":257,"keywords":260,"publishedAt":39},"01M6PT9Z92JTSQEHE1QR0NNW5F","webdriverio-skill","Generates WebdriverIO (WDIO) automation tests in JavaScript or TypeScript. Supports local and TestMu AI cloud. Use when user mentions \"WebdriverIO\", \"WDIO\", \"wdio.conf\", \"browser.url\", \"$\", \"$$\". Triggers on: \"WebdriverIO\", \"WDIO\", \"wdio\", \"browser.$\".","https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fwebdriverio-skill\u002FSKILL.md",[258,259],{"categoryNo":184,"categoryName":185,"taxonomyType":186,"taxonomyTypeDesc":187},{"categoryNo":189,"categoryName":190,"taxonomyType":186,"taxonomyTypeDesc":187},[261,194,262,213,263,264,265,266,196,34,267,221,197,198,268,269],"webdriverio skill","typescript","javascript","browser","cloud","e2e","e2e-testing","URL","conf",{"skillNo":271,"name":272,"nameZh":6,"description":273,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":180,"licenseFileUrl":6,"sourceHtmlUrl":274,"categories":275,"keywords":285,"publishedAt":39},"01M6PT9NVK36ZWCQ69YXK3FR4K","web-design-guidelines","Web platform design and accessibility guidelines. Use when building web interfaces, auditing accessibility, implementing responsive layouts, or reviewing web UI code. Triggers on tasks involving HTML, CSS, web components, WCAG compliance, responsive design, or web performance.","https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fweb\u002FSKILL.md",[276,279,280],{"categoryNo":277,"categoryName":278,"taxonomyType":186,"taxonomyTypeDesc":187},"01JBSEEDCAT000000000000009","前端开发",{"categoryNo":233,"categoryName":234,"taxonomyType":186,"taxonomyTypeDesc":187},{"categoryNo":281,"categoryName":282,"taxonomyType":283,"taxonomyTypeDesc":284},"01JBSEEDCAT000000000000032","设计师","PROFESSION","适用职业",[286,287,288,289,290,291,292,293,294,295,296,297,298,299,300,301,302,303,198,304],"design","web","guidelines","web design guidelines","web design","css","performance","components","web components","tasks","code","web performance","ui","platform design","html","responsive design","responsive","platform","implementing",{"skillNo":306,"name":307,"nameZh":6,"description":308,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":180,"licenseFileUrl":6,"sourceHtmlUrl":309,"categories":310,"keywords":313,"publishedAt":39},"01M6PT9A3JKRE3X34276F2FW5R","watchos-design-guidelines","Apple Human Interface Guidelines for Apple Watch. Use when building watchOS apps, complications, or workout features. Triggers on tasks involving Watch UI, Digital Crown, glanceable interfaces, or wrist-based interactions.","https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fwatchos\u002FSKILL.md",[311,312],{"categoryNo":233,"categoryName":234,"taxonomyType":186,"taxonomyTypeDesc":187},{"categoryNo":281,"categoryName":282,"taxonomyType":283,"taxonomyTypeDesc":284},[286,288,314,295,298,34,315,316,222,303,317,198,223,318,27,319,320],"watchos design guidelines","workout","human","watch","interface","platform-design","features"]