[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6PKJ09WVYR9CCF3YBVVAZ0W":3,"skill-same:01M6PKJ09WVYR9CCF3YBVVAZ0W":190},{"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":51,"commitSha":52,"skillDirectory":53,"forksCount":14,"repositoryHtmlUrl":54,"repositoryHomepageUrl":6,"ownerHtmlUrl":55,"ownerBlogUrl":56,"ownerDescription":6,"updatedAt":57,"install":58,"resources":71},"01M6PKJ09WVYR9CCF3YBVVAZ0W","tao-train-dino",null,"DINO (DETR with Improved DeNoising Anchor Boxes) for 2D object detection. Transformer-based detector with denoising training, multi-scale features, and optional distillation support. Use when training, evaluating, exporting, distilling, quantizing, or running inference for a TAO DINO detector. Trigger phrases include \"train DINO\", \"DETR object detection\", \"TAO 2D detection\", \"DINO with distillation\".","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.agent\u002Fskills\u002Ftao-train-dino\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38],"tao train dino","tao","train","anchor","2d","for","object","with","Transformer","multi","trigger","docker","container","use","detr","Bash","NVIDIA","toolkit","training","support","2026-11-10 10:12:30",false,"---\nname: tao-train-dino\ndescription: DINO (DETR with Improved DeNoising Anchor Boxes) for 2D object detection. Transformer-based detector with\n  denoising training, multi-scale features, and optional distillation support. Use when training, evaluating, exporting,\n  distilling, quantizing, or running inference for a TAO DINO detector. Trigger phrases include \"train DINO\", \"DETR object\n  detection\", \"TAO 2D detection\", \"DINO with distillation\".\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# DINO\n\nDINO (DETR with Improved DeNoising Anchor Boxes) for 2D object detection. Transformer-based detector with denoising training, multi-scale features, and optional distillation support.\n\nUses pretrained backbone weights (e.g. ResNet-50 ImageNet). Set `model.pretrained_backbone_path` for backbone-only or `train.pretrained_model_path` for full model.\n\nFor TAO Deploy TensorRT actions (`gen_trt_engine`, TensorRT `evaluate`, and\nTensorRT `inference`), read `references\u002Ftao-deploy-dino.md` first. Deploy spec templates live\nin this skill's `references\u002F` folder with the `spec_template_deploy_*.yaml`\nprefix.\n\nGenerated TAO Core schemas are packaged in `schemas\u002F\u003Caction>.schema.json` (with `schemas\u002Fmanifest.json` listing actions); each schema emits a matching `references\u002Fspec_template_\u003Caction>.yaml`. See `references\u002Fsdk_orchestration.md` for the full dataclass-schema, spec-template, data-sources, and parent-model inference details used by SDK orchestration.\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\nThe agent MUST read this section before generating any training or AutoML script for DINO.\n\n- **Dataset type:** object_detection\n- **Formats:** coco, coco_raw\n- **Accepted dataset intents:** training, evaluation, testing, calibration\n- **Monitoring metric:** val_mAP50\n\n**Required datasets — MUST resolve both:**\n\n| Dataset | Required | Why |\n|---|---|---|\n| Train dataset URI | Yes | Training data (COCO format) |\n| Validation dataset URI | **Yes — ALWAYS** | DINO unconditionally builds a val dataloader. Omitting `val_data_sources` causes `FileNotFoundError` at startup regardless of the metric or workflow. If the user has no separate eval split, reuse the train URI. |\n\n**Required inputs before generating any training spec:**\n\n1. **Train dataset URI** — S3 path to COCO-format training data\n2. **Validation dataset URI** — S3 path to COCO-format val data (can be same as train)\n3. **`num_classes`** — How many object classes? Default 91 (COCO). Must be >= `max(category_id) + 1`. Too low causes `CUDA error: device-side assert triggered`.\n\nResolve these from the user request or the default profile below. Prompt only\nfor values that are still missing after applying the profile rules.\n\n**Bankable local default profile for DINO AutoML smoke runs:**\n\nUse this profile only when the user asks to run DINO AutoML and does not provide\ndataset or class-count inputs. This profile is intentionally small and local to\nthis skill bank; it is for smoke\u002Fiteration runs, not a production benchmark.\nDo not search previous runners, logs, session state, shell history, or the home\ndirectory to recover these values.\n\n```python\nDINO_AUTOML_PROFILE = {\n    \"train_dataset_uri\": \"s3:\u002F\u002Fnvcf-storage-handling\u002Fdata\u002Ftao_od_synthetic_subset_train_no_convert\",\n    \"validation_dataset_uri\": \"s3:\u002F\u002Fnvcf-storage-handling\u002Fdata\u002Ftao_od_synthetic_subset_val_no_convert\",\n    \"object_classes\": 4,\n    \"dataset_num_classes\": 5,\n    \"image_archive\": \"images.tar.gz\",\n    \"annotation_file\": \"annotations.json\",\n    \"max_recommendations\": 10,\n    \"train_num_epochs\": 10,\n    \"train_checkpoint_interval\": 10,\n    \"train_validation_interval\": 1,\n    \"train_num_gpus\": 1,\n}\n```\n\nIf the user supplies any dataset URI or class-count value, prefer the user value\nand ask for any remaining required DINO value. Do not partially mix a user's\ncustom dataset with this profile's class count unless the user confirms it.\n\n**Do not prompt for image layout for the standard DINO dataset.** The standard\nTAO DINO dataset artifact is `images.tar.gz` plus `annotations.json`. Use\n`images.tar.gz` in the remote `image_dir` spec override. The SDK downloads the\narchive and rewrites the runtime spec to the extracted folder named after the\narchive stem (`images.tar.gz` -> `images`). Only deviate if the user explicitly\nprovides a different image artifact name.\n\n## Spec Overrides, Datasets, and Parameters\n\nData source overrides are **mandatory for every action** — DINO's `config.json` has empty `data_sources` because the runner cannot auto-resolve array-of-objects spec keys. The agent MUST build data source paths and include them in `spec_overrides`.\n\nSee `references\u002Fspec_overrides.md` for: the per-action dataset requirements table; the mandatory `spec_overrides` blocks for `train`, `evaluate`, `export`, `gen_trt_engine`, `inference`, `quantize`, and `distill`; checkpoint resolution via `parent_model` inference and the `results_dir\u002Ftrain\u002Fdino_model_latest.pth` fallback; the COCO dataset format and `images.tar.gz` archive-stem rules; per-action data-source layouts; the full **Important Parameters** list (num_classes, backbone and its supported values, lr\u002Flr_backbone, num_epochs, lr_steps, num_queries, batch_size); **Default Values** (num_epochs 10, batch_size 4, learning_rate 2e-4, lr_backbone 2e-5, num_classes 91, backbone resnet_50); **Evaluate Defaults**; **Export Defaults** (input 640x640, opset 17, trt_data_types [FP32, FP16, INT8], trt_workspace_size_mb 1024); and **Hardware** guidance (1 GPU minimum, 4 recommended, 24GB+ A100). Full TAO Deploy reference: [tao-deploy-dino](references\u002Ftao-deploy-dino.md).\n\nWhen generating an `evaluate` spec, carry forward the winning AutoML rec's structural model settings (`model.backbone`, `model.num_queries`, `model.dropout_ratio`, `dataset.num_classes`) so the checkpoint shape matches the evaluation model.\n\n## Error Patterns\n\nCommon failures include CUDA OOM, `num_select \u003C num_queries * num_classes`, spec\u002Fschema merge errors, dataset-smaller-than-batch, `return_interm_indices` vs `num_feature_levels` mismatch, `FileNotFoundError` on images or missing val data, `CUDA device-side assert` from low `num_classes`, S3 inputs not downloaded, and evaluate checkpoint not found at the result root. See `references\u002Ftroubleshooting.md` for each error pattern and its fix.\n\n## AutoML \u002F HPO Notes\n\nAutoML runs training — all **Training Requirements** above apply, and the no-input case uses `DINO_AUTOML_PROFILE`. Do not inspect previous AutoML runs to infer dataset URIs, `num_classes`, recommendation count, or interval settings. Use explicit `metric=\"mAP50\"` with `direction=\"maximize\"` and a custom `metric_extractor` reading `Validation mAP50` rather than `metric=\"kpi\"`. See `references\u002Fautoml.md` for the recommended metric extractor, hyperparameter list, `custom_param_ranges`, the `train.optim.weight_decay` note, and the backbone-constraint guidance.\n\n## Optional: running via the TAO SDK\n\nThe SDK `script_runner` orchestration, S3 I\u002FO wrapping, AutoML internals, spec-template generation, the data-sources gap, the `config.json` `inputs` declarations, and the full per-action spec-param \u002F parent-model inference mapping table are documented in `references\u002Fsdk_orchestration.md`. Skip this when running locally with `docker run`.\n","# DINO\n\nDINO (DETR with Improved DeNoising Anchor Boxes) for 2D object detection. Transformer-based detector with denoising training, multi-scale features, and optional distillation support.\n\nUses pretrained backbone weights (e.g. ResNet-50 ImageNet). Set `model.pretrained_backbone_path` for backbone-only or `train.pretrained_model_path` for full model.\n\nFor TAO Deploy TensorRT actions (`gen_trt_engine`, TensorRT `evaluate`, and\nTensorRT `inference`), read `references\u002Ftao-deploy-dino.md` first. Deploy spec templates live\nin this skill's `references\u002F` folder with the `spec_template_deploy_*.yaml`\nprefix.\n\nGenerated TAO Core schemas are packaged in `schemas\u002F\u003Caction>.schema.json` (with `schemas\u002Fmanifest.json` listing actions); each schema emits a matching `references\u002Fspec_template_\u003Caction>.yaml`. See `references\u002Fsdk_orchestration.md` for the full dataclass-schema, spec-template, data-sources, and parent-model inference details used by SDK orchestration.\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\nThe agent MUST read this section before generating any training or AutoML script for DINO.\n\n- **Dataset type:** object_detection\n- **Formats:** coco, coco_raw\n- **Accepted dataset intents:** training, evaluation, testing, calibration\n- **Monitoring metric:** val_mAP50\n\n**Required datasets — MUST resolve both:**\n\n| Dataset | Required | Why |\n|---|---|---|\n| Train dataset URI | Yes | Training data (COCO format) |\n| Validation dataset URI | **Yes — ALWAYS** | DINO unconditionally builds a val dataloader. Omitting `val_data_sources` causes `FileNotFoundError` at startup regardless of the metric or workflow. If the user has no separate eval split, reuse the train URI. |\n\n**Required inputs before generating any training spec:**\n\n1. **Train dataset URI** — S3 path to COCO-format training data\n2. **Validation dataset URI** — S3 path to COCO-format val data (can be same as train)\n3. **`num_classes`** — How many object classes? Default 91 (COCO). Must be >= `max(category_id) + 1`. Too low causes `CUDA error: device-side assert triggered`.\n\nResolve these from the user request or the default profile below. Prompt only\nfor values that are still missing after applying the profile rules.\n\n**Bankable local default profile for DINO AutoML smoke runs:**\n\nUse this profile only when the user asks to run DINO AutoML and does not provide\ndataset or class-count inputs. This profile is intentionally small and local to\nthis skill bank; it is for smoke\u002Fiteration runs, not a production benchmark.\nDo not search previous runners, logs, session state, shell history, or the home\ndirectory to recover these values.\n\n```python\nDINO_AUTOML_PROFILE = {\n    \"train_dataset_uri\": \"s3:\u002F\u002Fnvcf-storage-handling\u002Fdata\u002Ftao_od_synthetic_subset_train_no_convert\",\n    \"validation_dataset_uri\": \"s3:\u002F\u002Fnvcf-storage-handling\u002Fdata\u002Ftao_od_synthetic_subset_val_no_convert\",\n    \"object_classes\": 4,\n    \"dataset_num_classes\": 5,\n    \"image_archive\": \"images.tar.gz\",\n    \"annotation_file\": \"annotations.json\",\n    \"max_recommendations\": 10,\n    \"train_num_epochs\": 10,\n    \"train_checkpoint_interval\": 10,\n    \"train_validation_interval\": 1,\n    \"train_num_gpus\": 1,\n}\n```\n\nIf the user supplies any dataset URI or class-count value, prefer the user value\nand ask for any remaining required DINO value. Do not partially mix a user's\ncustom dataset with this profile's class count unless the user confirms it.\n\n**Do not prompt for image layout for the standard DINO dataset.** The standard\nTAO DINO dataset artifact is `images.tar.gz` plus `annotations.json`. Use\n`images.tar.gz` in the remote `image_dir` spec override. The SDK downloads the\narchive and rewrites the runtime spec to the extracted folder named after the\narchive stem (`images.tar.gz` -> `images`). Only deviate if the user explicitly\nprovides a different image artifact name.\n\n## Spec Overrides, Datasets, and Parameters\n\nData source overrides are **mandatory for every action** — DINO's `config.json` has empty `data_sources` because the runner cannot auto-resolve array-of-objects spec keys. The agent MUST build data source paths and include them in `spec_overrides`.\n\nSee `references\u002Fspec_overrides.md` for: the per-action dataset requirements table; the mandatory `spec_overrides` blocks for `train`, `evaluate`, `export`, `gen_trt_engine`, `inference`, `quantize`, and `distill`; checkpoint resolution via `parent_model` inference and the `results_dir\u002Ftrain\u002Fdino_model_latest.pth` fallback; the COCO dataset format and `images.tar.gz` archive-stem rules; per-action data-source layouts; the full **Important Parameters** list (num_classes, backbone and its supported values, lr\u002Flr_backbone, num_epochs, lr_steps, num_queries, batch_size); **Default Values** (num_epochs 10, batch_size 4, learning_rate 2e-4, lr_backbone 2e-5, num_classes 91, backbone resnet_50); **Evaluate Defaults**; **Export Defaults** (input 640x640, opset 17, trt_data_types [FP32, FP16, INT8], trt_workspace_size_mb 1024); and **Hardware** guidance (1 GPU minimum, 4 recommended, 24GB+ A100). Full TAO Deploy reference: [tao-deploy-dino](references\u002Ftao-deploy-dino.md).\n\nWhen generating an `evaluate` spec, carry forward the winning AutoML rec's structural model settings (`model.backbone`, `model.num_queries`, `model.dropout_ratio`, `dataset.num_classes`) so the checkpoint shape matches the evaluation model.\n\n## Error Patterns\n\nCommon failures include CUDA OOM, `num_select \u003C num_queries * num_classes`, spec\u002Fschema merge errors, dataset-smaller-than-batch, `return_interm_indices` vs `num_feature_levels` mismatch, `FileNotFoundError` on images or missing val data, `CUDA device-side assert` from low `num_classes`, S3 inputs not downloaded, and evaluate checkpoint not found at the result root. See `references\u002Ftroubleshooting.md` for each error pattern and its fix.\n\n## AutoML \u002F HPO Notes\n\nAutoML runs training — all **Training Requirements** above apply, and the no-input case uses `DINO_AUTOML_PROFILE`. Do not inspect previous AutoML runs to infer dataset URIs, `num_classes`, recommendation count, or interval settings. Use explicit `metric=\"mAP50\"` with `direction=\"maximize\"` and a custom `metric_extractor` reading `Validation mAP50` rather than `metric=\"kpi\"`. See `references\u002Fautoml.md` for the recommended metric extractor, hyperparameter list, `custom_param_ranges`, the `train.optim.weight_decay` note, and the backbone-constraint guidance.\n\n## Optional: running via the TAO SDK\n\nThe SDK `script_runner` orchestration, S3 I\u002FO wrapping, AutoML internals, spec-template generation, the data-sources gap, the `config.json` `inputs` declarations, and the full per-action spec-param \u002F parent-model inference mapping table are documented in `references\u002Fsdk_orchestration.md`. Skip this when running locally with `docker run`.\n",{"name":5,"tags":44,"license":15,"metadata":46,"description":7,"allowed-tools":49,"compatibility":50},[25,45],"detection",{"author":47,"version":48},"NVIDIA Corporation","0.1.0","Read Bash","Requires docker + nvidia-container-toolkit.","main","7a940b8e5af16c95e5c190a524421d32fc7445a9",".agent\u002Fskills\u002Ftao-train-dino","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":59,"prompt":69,"zipAvailable":70},[60,63,66],{"tool":61,"command":62},"npx","npx skills add headmktlucca-ui\u002Fneuroads-lp --skill tao-train-dino",{"tool":64,"command":65},"bunx","bunx skills add headmktlucca-ui\u002Fneuroads-lp --skill tao-train-dino",{"tool":67,"command":68},"pnpm","pnpm dlx skills add headmktlucca-ui\u002Fneuroads-lp --skill tao-train-dino","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Ftao-train-dino\u002FSKILL.md",true,[72,78,82,86,90,94,98,102,106,110,114,118,122,126,130,133,136,140,144,148,152,156,160,164,168,172,176,180,184],{"path":73,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":76,"sourceHtmlUrl":77},"BENCHMARK.md","REFERENCE","参考文档",4501,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Ftao-train-dino\u002FBENCHMARK.md",{"path":79,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":80,"sourceHtmlUrl":81},"evals\u002Fevals.json",730,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Ftao-train-dino\u002Fevals\u002Fevals.json",{"path":83,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":84,"sourceHtmlUrl":85},"references\u002Fautoml.md",2131,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Ftao-train-dino\u002Freferences\u002Fautoml.md",{"path":87,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":88,"sourceHtmlUrl":89},"references\u002Fsdk_orchestration.md",6808,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Ftao-train-dino\u002Freferences\u002Fsdk_orchestration.md",{"path":91,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":92,"sourceHtmlUrl":93},"references\u002Fskill_info.yaml",2222,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Ftao-train-dino\u002Freferences\u002Fskill_info.yaml",{"path":95,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":96,"sourceHtmlUrl":97},"references\u002Fspec_overrides.md",11061,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Ftao-train-dino\u002Freferences\u002Fspec_overrides.md",{"path":99,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":100,"sourceHtmlUrl":101},"references\u002Fspec_template_deploy_evaluate.yaml",598,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Ftao-train-dino\u002Freferences\u002Fspec_template_deploy_evaluate.yaml",{"path":103,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":104,"sourceHtmlUrl":105},"references\u002Fspec_template_deploy_gen_trt_engine.yaml",735,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Ftao-train-dino\u002Freferences\u002Fspec_template_deploy_gen_trt_engine.yaml",{"path":107,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":108,"sourceHtmlUrl":109},"references\u002Fspec_template_deploy_inference.yaml",600,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Ftao-train-dino\u002Freferences\u002Fspec_template_deploy_inference.yaml",{"path":111,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":112,"sourceHtmlUrl":113},"references\u002Fspec_template_distill.yaml",3062,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Ftao-train-dino\u002Freferences\u002Fspec_template_distill.yaml",{"path":115,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":116,"sourceHtmlUrl":117},"references\u002Fspec_template_evaluate.yaml",3210,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Ftao-train-dino\u002Freferences\u002Fspec_template_evaluate.yaml",{"path":119,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":120,"sourceHtmlUrl":121},"references\u002Fspec_template_export.yaml",3307,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Ftao-train-dino\u002Freferences\u002Fspec_template_export.yaml",{"path":123,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":124,"sourceHtmlUrl":125},"references\u002Fspec_template_gen_trt_engine.yaml",3457,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Ftao-train-dino\u002Freferences\u002Fspec_template_gen_trt_engine.yaml",{"path":127,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":128,"sourceHtmlUrl":129},"references\u002Fspec_template_inference.yaml",3290,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Ftao-train-dino\u002Freferences\u002Fspec_template_inference.yaml",{"path":131,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":112,"sourceHtmlUrl":132},"references\u002Fspec_template_quantize.yaml","https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Ftao-train-dino\u002Freferences\u002Fspec_template_quantize.yaml",{"path":134,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":112,"sourceHtmlUrl":135},"references\u002Fspec_template_train.yaml","https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Ftao-train-dino\u002Freferences\u002Fspec_template_train.yaml",{"path":137,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":138,"sourceHtmlUrl":139},"references\u002Ftao-deploy-dino.md",8411,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Ftao-train-dino\u002Freferences\u002Ftao-deploy-dino.md",{"path":141,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":142,"sourceHtmlUrl":143},"references\u002Ftao-deploy-dino.skill_info.yaml",2744,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Ftao-train-dino\u002Freferences\u002Ftao-deploy-dino.skill_info.yaml",{"path":145,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":146,"sourceHtmlUrl":147},"references\u002Ftroubleshooting.md",2254,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Ftao-train-dino\u002Freferences\u002Ftroubleshooting.md",{"path":149,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":150,"sourceHtmlUrl":151},"schemas\u002Fdistill.schema.json",52542,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Ftao-train-dino\u002Fschemas\u002Fdistill.schema.json",{"path":153,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":154,"sourceHtmlUrl":155},"schemas\u002Fevaluate.schema.json",55904,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Ftao-train-dino\u002Fschemas\u002Fevaluate.schema.json",{"path":157,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":158,"sourceHtmlUrl":159},"schemas\u002Fexport.schema.json",56469,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Ftao-train-dino\u002Fschemas\u002Fexport.schema.json",{"path":161,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":162,"sourceHtmlUrl":163},"schemas\u002Fgen_trt_engine.schema.json",61147,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Ftao-train-dino\u002Fschemas\u002Fgen_trt_engine.schema.json",{"path":165,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":166,"sourceHtmlUrl":167},"schemas\u002Finference.schema.json",56844,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Ftao-train-dino\u002Fschemas\u002Finference.schema.json",{"path":169,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":170,"sourceHtmlUrl":171},"schemas\u002Fmanifest.json",22062,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Ftao-train-dino\u002Fschemas\u002Fmanifest.json",{"path":173,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":174,"sourceHtmlUrl":175},"schemas\u002Fquantize.schema.json",52544,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Ftao-train-dino\u002Fschemas\u002Fquantize.schema.json",{"path":177,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":178,"sourceHtmlUrl":179},"schemas\u002Ftrain.schema.json",52538,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Ftao-train-dino\u002Fschemas\u002Ftrain.schema.json",{"path":181,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":182,"sourceHtmlUrl":183},"skill-card.md",3963,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Ftao-train-dino\u002Fskill-card.md",{"path":185,"resourceType":186,"resourceTypeDesc":187,"sizeBytes":188,"sourceHtmlUrl":189},"skill.oms.sig","OTHER","其他",10793,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.agent\u002Fskills\u002Ftao-train-dino\u002Fskill.oms.sig",[191,217,241,267,285,320],{"skillNo":192,"name":193,"nameZh":6,"description":194,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":195,"licenseFileUrl":6,"sourceHtmlUrl":196,"categories":197,"keywords":206,"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",[198,203],{"categoryNo":199,"categoryName":200,"taxonomyType":201,"taxonomyTypeDesc":202},"01JBSEEDCAT000000000000008","测试与质量","SCENARIO","使用场景",{"categoryNo":204,"categoryName":205,"taxonomyType":201,"taxonomyTypeDesc":202},"01JBSEEDCAT000000000000023","Skill与智能体开发",[207,208,209,210,211,32,212,213,214,215,216],"xunit","xunit skill","testing","injection","user","tests","triggers","unit","unit-testing","C#",{"skillNo":218,"name":219,"nameZh":6,"description":220,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":195,"licenseFileUrl":6,"sourceHtmlUrl":221,"categories":222,"keywords":225,"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",[223,224],{"categoryNo":199,"categoryName":200,"taxonomyType":201,"taxonomyTypeDesc":202},{"categoryNo":204,"categoryName":205,"taxonomyType":201,"taxonomyTypeDesc":202},[226,227,209,228,229,230,231,232,32,233,234,235,236,237,212,213,238,239,24,240],"xcuitest","xcuitest skill","automation","test","testing framework","ios","devices","mobile","mobile-testing","ui test","local","apple","apps","native","objective",{"skillNo":242,"name":243,"nameZh":6,"description":244,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":195,"licenseFileUrl":6,"sourceHtmlUrl":245,"categories":246,"keywords":251,"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",[247,250],{"categoryNo":248,"categoryName":249,"taxonomyType":201,"taxonomyTypeDesc":202},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":204,"categoryName":205,"taxonomyType":201,"taxonomyTypeDesc":202},[252,253,254,255,256,257,258,259,32,260,261,262,263,264,265,24,266],"builder","world","world builder","MCP","create","mcp tools","Tools","game","pokemon","manage","style","via","theme","zone","generative",{"skillNo":268,"name":269,"nameZh":6,"description":270,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":195,"licenseFileUrl":6,"sourceHtmlUrl":271,"categories":272,"keywords":275,"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",[273,274],{"categoryNo":199,"categoryName":200,"taxonomyType":201,"taxonomyTypeDesc":202},{"categoryNo":204,"categoryName":205,"taxonomyType":201,"taxonomyTypeDesc":202},[276,209,277,228,278,279,280,281,211,32,282,236,212,213,283,284],"webdriverio skill","typescript","javascript","browser","cloud","e2e","e2e-testing","URL","conf",{"skillNo":286,"name":287,"nameZh":6,"description":288,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":195,"licenseFileUrl":6,"sourceHtmlUrl":289,"categories":290,"keywords":300,"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",[291,294,295],{"categoryNo":292,"categoryName":293,"taxonomyType":201,"taxonomyTypeDesc":202},"01JBSEEDCAT000000000000009","前端开发",{"categoryNo":248,"categoryName":249,"taxonomyType":201,"taxonomyTypeDesc":202},{"categoryNo":296,"categoryName":297,"taxonomyType":298,"taxonomyTypeDesc":299},"01JBSEEDCAT000000000000032","设计师","PROFESSION","适用职业",[301,302,303,304,305,306,307,308,309,310,311,312,313,314,315,316,317,318,213,319],"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":321,"name":322,"nameZh":6,"description":323,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":195,"licenseFileUrl":6,"sourceHtmlUrl":324,"categories":325,"keywords":328,"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",[326,327],{"categoryNo":248,"categoryName":249,"taxonomyType":201,"taxonomyTypeDesc":202},{"categoryNo":296,"categoryName":297,"taxonomyType":298,"taxonomyTypeDesc":299},[301,303,329,310,313,32,330,331,237,318,332,213,238,333,24,334,335],"watchos design guidelines","workout","human","watch","interface","platform-design","features"]