[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78DB2S00E4CWXE08CMA6RN9":3,"skill-same:01M78DB2S00E4CWXE08CMA6RN9":115},{"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":32,"commitSha":33,"skillDirectory":34,"forksCount":14,"repositoryHtmlUrl":35,"repositoryHomepageUrl":36,"ownerHtmlUrl":37,"ownerBlogUrl":38,"ownerDescription":39,"updatedAt":40,"install":41,"resources":54},"01M78DB2S00E4CWXE08CMA6RN9","tao-train-action-recognition",null,"Action recognition from video sequences. Supports RGB, optical flow, and joint (multi-stream) input types for classifying temporal actions in video clips. Use when training, evaluating, exporting, or running inference on a TAO action-recognition model. Trigger phrases include \"train action recognition\", \"video action classification\", \"RGB + optical flow action model\", \"TAO ActionRecognition\".","Solizardking\u002Fskillhub-main","Solizardking","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F108096810?v=4","01M786KDB10AYV042N0F9BD5B5","Clawd","01M786NYYXSZK1D05WM8JQPC48",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Ftao-train-action-recognition\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: tao-train-action-recognition\ndescription: Action recognition from video sequences. Supports RGB, optical flow, and joint (multi-stream) input types for\n  classifying temporal actions in video clips. Use when training, evaluating, exporting, or running inference on a TAO\n  action-recognition model. Trigger phrases include \"train action recognition\", \"video action classification\", \"RGB +\n  optical flow action model\", \"TAO ActionRecognition\".\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- action\n- recognition\n---\n\n# Action Recognition\n\nAction recognition from video sequences. Supports RGB, optical flow, and joint (multi-stream) input types for classifying temporal actions in video clips.\n\nSet model.pretrained_model_path for pretrained backbone weights.\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. Use `automl_policy: on` by default and only expose `on` \u002F `off` in new launch prompts. Treat phrases like \"turn off AutoML\", \"disable AutoML\", \"no HPO\", or \"plain training\" as `automl_policy: off` for this run only. When `automl_policy: on`, `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:** action_recognition\n- **Formats:** default\n- **Monitoring metric:** val_loss\n\n### Per-Action Dataset Requirements\n\n| Action | Spec Key | Source | Files | List? |\n|---|---|---|---|---|\n| evaluate | evaluate.test_dataset_dir | train_datasets | test\u002F extracted from test.tar.gz | No |\n| inference | inference.inference_dataset_dir | train_datasets | test\u002Fsmile\u002F extracted from test\u002Fsmile.tar.gz | No |\n| train | dataset.train_dataset_dir | train_datasets | train\u002F extracted from train.tar.gz | No |\n| train | dataset.val_dataset_dir | train_datasets | test\u002F extracted from test.tar.gz | 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\nLOCAL_DATA = \"\u002Fworkspace\u002Fdata\u002Fextracted\"\n```\n\nIf the source dataset is provided as the TAO sample archives\n`train.tar.gz`, `test.tar.gz`, or `test\u002Fsmile.tar.gz`, download and extract\nthem before launching the TAO container. The action-recognition entrypoints\nexpect directory paths and fail with `NotADirectoryError` when these spec keys\npoint at `.tar.gz` files.\n\n**train (mandatory data sources):**\n```python\n{\n    \"train.num_epochs\": 30,\n    \"train.checkpoint_interval\": 10,\n    \"train.validation_interval\": 10,\n    \"train.num_gpus\": 1,\n    \"dataset.label_map\": {\n        \"catch\": 0,\n        \"smile\": 1\n    },\n    \"dataset.batch_size\": 2,\n    \"dataset.train_dataset_dir\": f\"{LOCAL_DATA}\u002Ftrain\",\n    \"dataset.val_dataset_dir\": f\"{LOCAL_DATA}\u002Ftest\",\n}\n```\n\n**evaluate (mandatory data sources):**\n```python\n{\n    \"dataset.label_map\": {\n        \"catch\": 0,\n        \"smile\": 1\n    },\n    \"evaluate.test_dataset_dir\": f\"{LOCAL_DATA}\u002Ftest\",\n}\n```\n\n**inference (mandatory data sources):**\n```python\n{\n    \"dataset.label_map\": {\n        \"catch\": 0,\n        \"smile\": 1\n    },\n    \"inference.inference_dataset_dir\": f\"{LOCAL_DATA}\u002Fsmile_infer\u002Fsmile\",\n}\n```\n\n**export (mandatory checkpoint + output path):**\n```python\n{\n    \"export.checkpoint\": \"\u003Cselected train checkpoint>\",\n    \"export.onnx_file\": \"\u003Cresults_dir>\u002Faction_recognition.onnx\",\n}\n```\n\nFor direct local-docker chaining without the SDK resolver, select the concrete\ncheckpoint produced by training, for example\n`model_epoch_000_step_00005.pth`, and pass that exact file to `evaluate`,\n`inference`, and `export`. Do not use the `ar_model_latest.pth` symlink unless\nthe user explicitly requests latest-checkpoint behavior. For resume training,\nset `train.resume_training_checkpoint_path` to the exact epoch\u002Fstep checkpoint\nbeing resumed.\n## Eval Dataset\n\nOptional. Test dataset may be distributed as `test.tar.gz` separate from\ntraining; extract it and point the spec to the extracted `test\u002F` directory.\nTAO training emits `val_loss` as the validation scalar for the packaged sample\ndata; use `val_loss` with minimize direction for AutoML selection unless a\ncustom evaluator supplies an accuracy metric.\n\n## Important Parameters\n\n- **model.model_type**: Input type: rgb, of (optical flow), or joint (multi-stream).\n- **model.backbone**: Default resnet_18. Used as the spatial feature extractor.\n- **dataset.label_map**: Dictionary mapping class names to indices.\n- **model.rgb_seq_length**: Number of frames per clip for RGB input.\n- **model.of_seq_length**: Number of frames for optical flow input.\n- **train.optim.lr**: Learning rate. Default 5e-4.\n\n## Multi-GPU \u002F Multi-Node\n\n**Launch method:** Lightning-managed (single `python` process, Lightning spawns workers).\n\n| Spec Key | Description | Default |\n|----------|-------------|---------|\n| `train.num_gpus` | Number of GPUs | 1 |\n| `train.gpu_ids` | GPU device indices | [0] |\n\n- Strategy: `auto` (Lightning picks best strategy automatically)\n- No explicit `num_nodes` or `distributed_strategy` config — single-node oriented\n\n## Hardware\n\nMinimum 1 GPU(s), recommended 2 GPU(s). 16GB+ VRAM per GPU. Memory depends on sequence length and input resolution. batch_size=2 is conservative for video data.\n\n## Error Patterns\n\n**Sequence length mismatch**: Ensure video clips have enough frames for the configured rgb_seq_length or of_seq_length.\n\n**Evaluate\u002Finference missing label map**: Downstream actions rebuild the\nActionRecognitionModel before loading the checkpoint, so they need the same\n`dataset.label_map` used during training. Include it with every evaluate or\ninference spec; otherwise model construction fails before the checkpoint can be\nvalidated.\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 `action_recognition.config.json`:\n\n| Action | Spec Field | Inference Function | Meaning |\n|---|---|---|---|\n| evaluate | `encryption_key` | `key` | encryption key |\n| evaluate | `evaluate.checkpoint` | `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| inference | `encryption_key` | `key` | encryption key |\n| inference | `inference.checkpoint` | `parent_model` | model file inferred from the parent job results folder |\n| inference | `results_dir` | `output_dir` | current job results directory |\n| train | `encryption_key` | `key` | encryption key |\n| train | `model.of_pretrained_model_path` | `ptm_if_no_resume_model` | PTM when no resume checkpoint exists |\n| train | `model.rgb_pretrained_model_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.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","# Action Recognition\n\nAction recognition from video sequences. Supports RGB, optical flow, and joint (multi-stream) input types for classifying temporal actions in video clips.\n\nSet model.pretrained_model_path for pretrained backbone weights.\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. Use `automl_policy: on` by default and only expose `on` \u002F `off` in new launch prompts. Treat phrases like \"turn off AutoML\", \"disable AutoML\", \"no HPO\", or \"plain training\" as `automl_policy: off` for this run only. When `automl_policy: on`, `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:** action_recognition\n- **Formats:** default\n- **Monitoring metric:** val_loss\n\n### Per-Action Dataset Requirements\n\n| Action | Spec Key | Source | Files | List? |\n|---|---|---|---|---|\n| evaluate | evaluate.test_dataset_dir | train_datasets | test\u002F extracted from test.tar.gz | No |\n| inference | inference.inference_dataset_dir | train_datasets | test\u002Fsmile\u002F extracted from test\u002Fsmile.tar.gz | No |\n| train | dataset.train_dataset_dir | train_datasets | train\u002F extracted from train.tar.gz | No |\n| train | dataset.val_dataset_dir | train_datasets | test\u002F extracted from test.tar.gz | 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\nLOCAL_DATA = \"\u002Fworkspace\u002Fdata\u002Fextracted\"\n```\n\nIf the source dataset is provided as the TAO sample archives\n`train.tar.gz`, `test.tar.gz`, or `test\u002Fsmile.tar.gz`, download and extract\nthem before launching the TAO container. The action-recognition entrypoints\nexpect directory paths and fail with `NotADirectoryError` when these spec keys\npoint at `.tar.gz` files.\n\n**train (mandatory data sources):**\n```python\n{\n    \"train.num_epochs\": 30,\n    \"train.checkpoint_interval\": 10,\n    \"train.validation_interval\": 10,\n    \"train.num_gpus\": 1,\n    \"dataset.label_map\": {\n        \"catch\": 0,\n        \"smile\": 1\n    },\n    \"dataset.batch_size\": 2,\n    \"dataset.train_dataset_dir\": f\"{LOCAL_DATA}\u002Ftrain\",\n    \"dataset.val_dataset_dir\": f\"{LOCAL_DATA}\u002Ftest\",\n}\n```\n\n**evaluate (mandatory data sources):**\n```python\n{\n    \"dataset.label_map\": {\n        \"catch\": 0,\n        \"smile\": 1\n    },\n    \"evaluate.test_dataset_dir\": f\"{LOCAL_DATA}\u002Ftest\",\n}\n```\n\n**inference (mandatory data sources):**\n```python\n{\n    \"dataset.label_map\": {\n        \"catch\": 0,\n        \"smile\": 1\n    },\n    \"inference.inference_dataset_dir\": f\"{LOCAL_DATA}\u002Fsmile_infer\u002Fsmile\",\n}\n```\n\n**export (mandatory checkpoint + output path):**\n```python\n{\n    \"export.checkpoint\": \"\u003Cselected train checkpoint>\",\n    \"export.onnx_file\": \"\u003Cresults_dir>\u002Faction_recognition.onnx\",\n}\n```\n\nFor direct local-docker chaining without the SDK resolver, select the concrete\ncheckpoint produced by training, for example\n`model_epoch_000_step_00005.pth`, and pass that exact file to `evaluate`,\n`inference`, and `export`. Do not use the `ar_model_latest.pth` symlink unless\nthe user explicitly requests latest-checkpoint behavior. For resume training,\nset `train.resume_training_checkpoint_path` to the exact epoch\u002Fstep checkpoint\nbeing resumed.\n## Eval Dataset\n\nOptional. Test dataset may be distributed as `test.tar.gz` separate from\ntraining; extract it and point the spec to the extracted `test\u002F` directory.\nTAO training emits `val_loss` as the validation scalar for the packaged sample\ndata; use `val_loss` with minimize direction for AutoML selection unless a\ncustom evaluator supplies an accuracy metric.\n\n## Important Parameters\n\n- **model.model_type**: Input type: rgb, of (optical flow), or joint (multi-stream).\n- **model.backbone**: Default resnet_18. Used as the spatial feature extractor.\n- **dataset.label_map**: Dictionary mapping class names to indices.\n- **model.rgb_seq_length**: Number of frames per clip for RGB input.\n- **model.of_seq_length**: Number of frames for optical flow input.\n- **train.optim.lr**: Learning rate. Default 5e-4.\n\n## Multi-GPU \u002F Multi-Node\n\n**Launch method:** Lightning-managed (single `python` process, Lightning spawns workers).\n\n| Spec Key | Description | Default |\n|----------|-------------|---------|\n| `train.num_gpus` | Number of GPUs | 1 |\n| `train.gpu_ids` | GPU device indices | [0] |\n\n- Strategy: `auto` (Lightning picks best strategy automatically)\n- No explicit `num_nodes` or `distributed_strategy` config — single-node oriented\n\n## Hardware\n\nMinimum 1 GPU(s), recommended 2 GPU(s). 16GB+ VRAM per GPU. Memory depends on sequence length and input resolution. batch_size=2 is conservative for video data.\n\n## Error Patterns\n\n**Sequence length mismatch**: Ensure video clips have enough frames for the configured rgb_seq_length or of_seq_length.\n\n**Evaluate\u002Finference missing label map**: Downstream actions rebuild the\nActionRecognitionModel before loading the checkpoint, so they need the same\n`dataset.label_map` used during training. Include it with every evaluate or\ninference spec; otherwise model construction fails before the checkpoint can be\nvalidated.\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 `action_recognition.config.json`:\n\n| Action | Spec Field | Inference Function | Meaning |\n|---|---|---|---|\n| evaluate | `encryption_key` | `key` | encryption key |\n| evaluate | `evaluate.checkpoint` | `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| inference | `encryption_key` | `key` | encryption key |\n| inference | `inference.checkpoint` | `parent_model` | model file inferred from the parent job results folder |\n| inference | `results_dir` | `output_dir` | current job results directory |\n| train | `encryption_key` | `key` | encryption key |\n| train | `model.of_pretrained_model_path` | `ptm_if_no_resume_model` | PTM when no resume checkpoint exists |\n| train | `model.rgb_pretrained_model_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.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":24,"license":15,"metadata":27,"description":7,"allowed-tools":30,"compatibility":31},[25,26],"action","recognition",{"author":28,"version":29},"NVIDIA Corporation","0.1.0","Read Bash","Requires docker + nvidia-container-toolkit.","main","be3de0244dc1a57e323d8160787ebb40fb64930e","skills\u002Fnvidia\u002Ftao-train-action-recognition","https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main","https:\u002F\u002Fskills.x402.wtf","https:\u002F\u002Fgithub.com\u002FSolizardking","https:\u002F\u002Fmusebook.trade","Got a mile high and never came down","2026-10-08 23:20:13",{"source":8,"skillName":5,"commands":42,"prompt":52,"zipAvailable":53},[43,46,49],{"tool":44,"command":45},"npx","npx skills add Solizardking\u002Fskillhub-main --skill tao-train-action-recognition",{"tool":47,"command":48},"bunx","bunx skills add Solizardking\u002Fskillhub-main --skill tao-train-action-recognition",{"tool":50,"command":51},"pnpm","pnpm dlx skills add Solizardking\u002Fskillhub-main --skill tao-train-action-recognition","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Ftao-train-action-recognition\u002FSKILL.md",true,[55,61,65,69,73,77,81,85,89,93,97,101,105,109],{"path":56,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":59,"sourceHtmlUrl":60},"BENCHMARK.md","REFERENCE","参考文档",4125,"https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Ftao-train-action-recognition\u002FBENCHMARK.md",{"path":62,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":63,"sourceHtmlUrl":64},"evals\u002Fevals.json",816,"https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Ftao-train-action-recognition\u002Fevals\u002Fevals.json",{"path":66,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":67,"sourceHtmlUrl":68},"references\u002Fskill_info.yaml",2717,"https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Ftao-train-action-recognition\u002Freferences\u002Fskill_info.yaml",{"path":70,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":71,"sourceHtmlUrl":72},"references\u002Fspec_template_evaluate.yaml",1802,"https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Ftao-train-action-recognition\u002Freferences\u002Fspec_template_evaluate.yaml",{"path":74,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":75,"sourceHtmlUrl":76},"references\u002Fspec_template_export.yaml",1690,"https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Ftao-train-action-recognition\u002Freferences\u002Fspec_template_export.yaml",{"path":78,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":79,"sourceHtmlUrl":80},"references\u002Fspec_template_inference.yaml",1806,"https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Ftao-train-action-recognition\u002Freferences\u002Fspec_template_inference.yaml",{"path":82,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":83,"sourceHtmlUrl":84},"references\u002Fspec_template_train.yaml",1641,"https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Ftao-train-action-recognition\u002Freferences\u002Fspec_template_train.yaml",{"path":86,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":87,"sourceHtmlUrl":88},"schemas\u002Fevaluate.schema.json",27177,"https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Ftao-train-action-recognition\u002Fschemas\u002Fevaluate.schema.json",{"path":90,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":91,"sourceHtmlUrl":92},"schemas\u002Fexport.schema.json",24946,"https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Ftao-train-action-recognition\u002Fschemas\u002Fexport.schema.json",{"path":94,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":95,"sourceHtmlUrl":96},"schemas\u002Finference.schema.json",27162,"https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Ftao-train-action-recognition\u002Fschemas\u002Finference.schema.json",{"path":98,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":99,"sourceHtmlUrl":100},"schemas\u002Fmanifest.json",6234,"https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Ftao-train-action-recognition\u002Fschemas\u002Fmanifest.json",{"path":102,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":103,"sourceHtmlUrl":104},"schemas\u002Ftrain.schema.json",23799,"https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Ftao-train-action-recognition\u002Fschemas\u002Ftrain.schema.json",{"path":106,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":107,"sourceHtmlUrl":108},"skill-card.md",3975,"https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Ftao-train-action-recognition\u002Fskill-card.md",{"path":110,"resourceType":111,"resourceTypeDesc":112,"sizeBytes":113,"sourceHtmlUrl":114},"skill.oms.sig","OTHER","其他",7049,"https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fskills\u002Fnvidia\u002Ftao-train-action-recognition\u002Fskill.oms.sig",[116,124,131,138,145,153],{"skillNo":117,"name":118,"nameZh":6,"description":119,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":120,"licenseFileUrl":6,"sourceHtmlUrl":121,"categories":122,"keywords":123,"publishedAt":19},"01M78E0TGCAMNPS207BA3G07S7","zkrouter","Self-hosted OpenAI-compatible LLM router — smart tier-based routing, ZK-stamped routing decisions, mode overrides, free OpenRouter at install via the Birth bot. Save 60-80% on inference costs by routing to the cheapest capable model across 12+ OpenRouter models.","MIT","https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fskills\u002Fzkrouter\u002FSKILL.md",[],[],{"skillNo":125,"name":126,"nameZh":6,"description":127,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":120,"licenseFileUrl":6,"sourceHtmlUrl":128,"categories":129,"keywords":130,"publishedAt":19},"01M78E0R1Z8BDT6EDTHY17MTNB","zk","For custom ZK Solana programs and privacy-preserving applications to prevent double spending. Guide to integrate rent-free nullifier PDAs for double-spend prevention.","https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fskills\u002Fzk\u002FSKILL.md",[],[],{"skillNo":132,"name":133,"nameZh":6,"description":134,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":120,"licenseFileUrl":6,"sourceHtmlUrl":135,"categories":136,"keywords":137,"publishedAt":19},"01M78E0P3ZTZ1YWF8MD5MM23QE","zk-omni-messaging","Zero-knowledge omnichain messaging between Robinhood Chain and Solana using CheshireZkOmniMessenger (msgType 4) with nullifier anti-replay and the zk-omni-relayer service.","https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fskills\u002Fzk-omni-messaging\u002FSKILL.md",[],[],{"skillNo":139,"name":140,"nameZh":6,"description":141,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":120,"licenseFileUrl":6,"sourceHtmlUrl":142,"categories":143,"keywords":144,"publishedAt":19},"01M78E0JXZ2PNB1896VXAGDBWD","zerion-wallet-data","Use when the user asks to check a wallet's portfolio, token balances, DeFi positions, PnL, transaction history, or NFTs. Provides interpreted on-chain data across 40+ EVM chains and Solana via x402 pay-per-request or API key — no raw RPC decoding needed.","https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fskills\u002Fzerion-wallet-data\u002FSKILL.md",[],[],{"skillNo":146,"name":147,"nameZh":6,"description":148,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":120,"licenseFileUrl":149,"sourceHtmlUrl":150,"categories":151,"keywords":152,"publishedAt":19},"01M78E0G14FH9GRRTQYMKD5E59","youtube-clipper","YouTube 视频智能剪辑工具。下载视频和字幕，AI 分析生成精细章节（几分钟级别）， 用户选择片段后自动剪辑、翻译字幕为中英双语、烧录字幕到视频，并生成总结文案。 使用场景：当用户需要剪辑 YouTube 视频、生成短视频片段、制作双语字幕版本时。 关键词：视频剪辑、YouTube、字幕翻译、双语字幕、视频下载、clip video","https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fskills\u002Fyoutube-clipper\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fskills\u002Fyoutube-clipper\u002FSKILL.md",[],[],{"skillNo":154,"name":155,"nameZh":6,"description":156,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":120,"licenseFileUrl":6,"sourceHtmlUrl":157,"categories":158,"keywords":159,"publishedAt":19},"01M78E0C2ZYA99CFFDNB7ZMK5S","yield-optimization","Multi-chain yield optimization via yield.xyz (StakeKit). Discover 2,988+ yield opportunities across 75+ blockchains, build deposit\u002Fwithdrawal transactions with shell scripts, and sign them with a MoonPay wallet. Use when the user wants to earn yield, find the best lending or staking rate, enter\u002Fexit a position, or check portfolio balances.","https:\u002F\u002Fgithub.com\u002FSolizardking\u002Fskillhub-main\u002Fblob\u002Fmain\u002Fskills\u002Fyield-optimization\u002FSKILL.md",[],[]]