[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6PSBKV1BXJDC0CBPFX1N192":3,"skill-same:01M6PSBKV1BXJDC0CBPFX1N192":146},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":23,"publishedAt":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":57,"commitSha":58,"skillDirectory":59,"forksCount":14,"repositoryHtmlUrl":60,"repositoryHomepageUrl":6,"ownerHtmlUrl":61,"ownerBlogUrl":62,"ownerDescription":6,"updatedAt":63,"install":64,"resources":77},"01M6PSBKV1BXJDC0CBPFX1N192","tao-finetune-clip",null,"CLIP vision-language model for image-text retrieval, zero-shot classification, embedding extraction, ONNX export, and TensorRT deployment. Use when fine-tuning or training CLIP, running zero-shot classification, computing image embeddings, or deploying CLIP to ONNX\u002FTensorRT.","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-finetune-clip\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000011","运维与部署","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"tao finetune clip","tao","finetune","clip","use","for","Zero-Shot","Vision-Language","embedding","container","image","model","classification","Fine-Tuning","NVIDIA","ZeRO","deployment","training","onnx","docker","2026-11-10 10:12:30",false,"---\nname: tao-finetune-clip\ndescription: CLIP vision-language model for image-text retrieval, zero-shot classification, embedding extraction, ONNX\n  export, and TensorRT deployment. Use when fine-tuning or training CLIP, running zero-shot classification, computing image\n  embeddings, or deploying CLIP to ONNX\u002FTensorRT.\nlicense: Apache-2.0\ncompatibility: Requires docker + nvidia-container-toolkit.\nmetadata:\n  author: NVIDIA Corporation\n  version: \"1.0.0\"\nallowed-tools: Read Bash\ntags:\n- vision-language\n- classification\n- embedding\n- zero-shot\n- deployment\n---\n\n# CLIP\n\nContrastive Language-Image Pre-training model for zero-shot and fine-tuned image classification, image-text retrieval, and embedding extraction. Fine-tuning adapts CLIP's shared image-text embedding space to domain-specific image-caption data.\n\nNo default NGC pretrained checkpoint is required. When `train.pretrained_model_path`, `evaluate.checkpoint`, `inference.checkpoint`, or `export.checkpoint` is unset, TAO loads pretrained weights from HuggingFace for SigLIP2\u002FOpenCLIP variants or `torch.hub` for Radio-CLIP, so first use needs network access or a local mirror.\n\nSupported actions: `train`, `evaluate`, `inference`, `export`, `gen_trt_engine`.\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## Instructions\n\nUse this skill for NVIDIA TAO CLIP jobs: training, evaluation, embedding inference, ONNX export, and TensorRT engine generation. Start by identifying the requested action, then load only the referenced files needed for that action: `defaults.json` for default parameters, `config.json` for action\u002Fdata-source wiring, `references\u002Fspec_template.yaml` for full spec shape, and `references\u002Fmodel_info.yaml` for SDK metadata.\n\nFor dataset-backed actions, collect the required image, caption, list, or prompt files from the user and place the resolved paths in `spec_overrides`. For `export` and `gen_trt_engine`, infer parent artifacts from the upstream job when available; otherwise require explicit checkpoint, ONNX, or engine paths. Run `gen_trt_engine`, TensorRT `evaluate`, and TensorRT `inference` in the TAO Deploy image.\n\nFor TAO Deploy TensorRT actions (`gen_trt_engine`, TensorRT `evaluate`, and TensorRT `inference`), read `references\u002Ftao-deploy-clip.md` first. Deploy spec templates live in this skill's `references\u002F` folder with the `spec_template_deploy_*.yaml` prefix.\n\n## Training Requirements\n\n- **Dataset type:** image_text\n- **Formats:** custom image\u002Fcaption folders or WebDataset shards\n- **Monitoring metric:** val\u002Ft2i_mAP\n\n### Supported Models\n\n- **SigLIP2:** `siglip2-so400m-patch16-256` (default), `siglip2-so400m-patch14-224`, `siglip2-so400m-patch14-384`, `siglip2-so400m-patch16-384`, `siglip2-so400m-patch16-512`, `siglip2-so400m-patch16-naflex`\n- **Radio-CLIP:** `c-radio_v3-b`, `c-radio_v3-l`, `c-radio_v3-h`, `c-radio_v3-g`\n- **OpenCLIP \u002F NV-CLIP:** `ViT-L-14-SigLIP-CLIPA-224`, `ViT-L-14-SigLIP-CLIPA-336`, `ViT-H-14-SigLIP-CLIPA-224`, `ViT-H-14-SigLIP-CLIPA-336`, `ViT-H-14-SigLIP-CLIPA-574`\n\nRadio-CLIP requires `model.adaptor_name` to be set to `siglip` or `clip`.\n\n### Per-Action Dataset Requirements\n\n| Action | Spec Key | Source | Files | List? |\n|---|---|---|---|---|\n| train | dataset.train.datasets | train_datasets | image_dir: images.tar.gz, image_list_file: image_list.txt, caption_dir: captions.tar.gz | Yes |\n| train | dataset.train.wds.root_dir | train_wds_dataset | root directory containing `.tar` shards | No |\n| train | dataset.train.wds.shard_list_file | train_wds_dataset | shards.txt listing shard paths | No |\n| train | dataset.val.datasets | eval_dataset | image_dir: images.tar.gz, image_list_file: image_list.txt, caption_dir: captions.tar.gz | Yes |\n| evaluate | dataset.val.datasets | eval_dataset | image_dir: images.tar.gz, image_list_file: image_list.txt, caption_dir: captions.tar.gz | Yes |\n| inference | inference.datasets | inference_dataset | image_dir: images.tar.gz | Yes |\n| inference | inference.text_file | inference_dataset | prompts.txt | No |\n| export | export.checkpoint | parent train job or explicit checkpoint | checkpoint .pth, optional for pretrained export | No |\n| gen_trt_engine | gen_trt_engine.onnx_file | parent export job or explicit ONNX | clip_model.onnx | No |\n\nFor custom training, set `dataset.train.type: custom` and provide `dataset.train.datasets` entries. Image and caption files must share the same base name. `caption_file_suffix` defaults to `.txt`, and `image_list_file` is optional.\n\nFor WDS training, set `dataset.train.type: wds` and provide at least one of `dataset.train.wds.root_dir` or `dataset.train.wds.shard_list_file`. `root_dir` is scanned recursively for `.tar` shards. `shard_list_file` is a text file with one shard path per line; relative lines resolve under the list-file directory unless `root_dir` is also supplied, in which case they resolve under `root_dir`. Validation\u002Fevaluation data remains custom format via `dataset.val.datasets`.\n\n### Typical Spec Overrides\n\nData source overrides are mandatory for dataset-backed actions. Construct paths from the Per-Action Dataset Requirements table and include them in `spec_overrides`. For inference, provide at least one of `inference.datasets` or `inference.text_file`.\n\n```python\nS3_TRAIN = \"s3:\u002F\u002Fbucket\u002Fdata\u002Ftrain\"\nS3_WDS = \"s3:\u002F\u002Fbucket\u002Fdata\u002Fwds\"\nS3_EVAL = \"s3:\u002F\u002Fbucket\u002Fdata\u002Feval\"\nS3_INFER = \"s3:\u002F\u002Fbucket\u002Fdata\u002Finfer\"\n```\n\n**train, custom dataset:**\n```python\n{\n    \"train.num_epochs\": 10,\n    \"dataset.train.type\": \"custom\",\n    \"dataset.train.datasets\": [{\"image_dir\": f\"{S3_TRAIN}\u002Fimages.tar.gz\", \"image_list_file\": f\"{S3_TRAIN}\u002Fimage_list.txt\", \"caption_dir\": f\"{S3_TRAIN}\u002Fcaptions.tar.gz\"}],\n    \"dataset.val.datasets\": [{\"image_dir\": f\"{S3_EVAL}\u002Fimages.tar.gz\", \"image_list_file\": f\"{S3_EVAL}\u002Fimage_list.txt\", \"caption_dir\": f\"{S3_EVAL}\u002Fcaptions.tar.gz\"}],\n}\n```\n\n**train, WDS dataset:**\n```python\n{\n    \"train.num_epochs\": 10,\n    \"dataset.train.type\": \"wds\",\n    \"dataset.train.wds.root_dir\": f\"{S3_WDS}\",\n    \"dataset.train.wds.shard_list_file\": f\"{S3_WDS}\u002Fshards.txt\",\n    \"dataset.train.wds.samples_per_shard\": 10000,\n    \"dataset.val.datasets\": [{\"image_dir\": f\"{S3_EVAL}\u002Fimages.tar.gz\", \"image_list_file\": f\"{S3_EVAL}\u002Fimage_list.txt\", \"caption_dir\": f\"{S3_EVAL}\u002Fcaptions.tar.gz\"}],\n}\n```\n\n**evaluate:**\n```python\n{\n    \"dataset.val.datasets\": [{\"image_dir\": f\"{S3_EVAL}\u002Fimages.tar.gz\", \"image_list_file\": f\"{S3_EVAL}\u002Fimage_list.txt\", \"caption_dir\": f\"{S3_EVAL}\u002Fcaptions.tar.gz\"}],\n}\n```\n\nLeave `evaluate.checkpoint` unset for zero-shot evaluation with pretrained weights. Set `evaluate.trt_engine` instead of `evaluate.checkpoint` for TensorRT evaluation.\n\n**inference:**\n```python\n{\n    \"inference.datasets\": [{\"image_dir\": f\"{S3_INFER}\u002Fimages.tar.gz\"}],\n    \"inference.text_file\": f\"{S3_INFER}\u002Fprompts.txt\",\n}\n```\n\nInference writes `image_embeddings.h5` and\u002For `text_embeddings.h5` under `results_dir`. The saved embeddings are L2-normalized.\n\n**export:**\n```python\n{\n    \"export.onnx_file\": \"${results_dir}\u002Fexport\u002Fclip_model.onnx\",\n    \"export.encoder_type\": \"combined\",\n    \"export.batch_size\": -1,\n}\n```\n\nSet `export.encoder_type: separate` when deployment should use independent vision and text encoders. Separate export writes `_vision.onnx` and `_text.onnx` variants derived from the base `export.onnx_file`.\n\n**gen_trt_engine:**\n```python\n{\n    \"gen_trt_engine.onnx_file\": \"${results_dir}\u002Fexport\u002Fclip_model.onnx\",\n    \"gen_trt_engine.trt_engine\": \"${results_dir}\u002Fdeploy\u002Fclip_model.engine\",\n    \"gen_trt_engine.batch_size\": -1,\n    \"gen_trt_engine.tensorrt.data_type\": \"fp16\",\n    \"gen_trt_engine.tensorrt.min_batch_size\": 1,\n    \"gen_trt_engine.tensorrt.opt_batch_size\": 1,\n    \"gen_trt_engine.tensorrt.max_batch_size\": 16,\n}\n```\n\n## Eval Dataset\n\nOptional for training. If provided, validation metrics are computed at validation intervals. Required for `evaluate`.\n\n## Deploy Workflow\n\nThe skill exposes `gen_trt_engine` as the deploy action. In generated SDK runners, use `model_info[\"actions\"][\"gen_trt_engine\"]` and run it in the TAO Deploy image, not the PyTorch training image. The in-container command is `clip gen_trt_engine -e {config_path}`; direct TAO Launcher usage spells the same action as `tao deploy clip gen_trt_engine -e \u002Fpath\u002Fto\u002Fspec.yaml`.\n\nTAO Deploy supports both combined and separate encoder formats. For separate encoders, pass the base path without `_vision` or `_text` to `gen_trt_engine.onnx_file` and `gen_trt_engine.trt_engine`; TAO detects or writes the suffixed vision\u002Ftext files.\n\nUse `evaluate.trt_engine` for TensorRT evaluation and `inference.trt_engine` for TensorRT embedding extraction. These TensorRT paths also run in the TAO Deploy image. Direct TAO Launcher usage spells these as `tao deploy clip evaluate` and `tao deploy clip inference`.\n\nFull TAO Deploy reference: [tao-deploy-clip](references\u002Ftao-deploy-clip.md).\n\n## Important Parameters\n\n- **model.type**: Backbone family and resolution. Use fixed-resolution SigLIP2\u002FOpenCLIP variants for deployment.\n- **model.adaptor_name**: Required for Radio-CLIP. Set to `siglip` or `clip`.\n- **model.image_size**: Training transform image resolution. Keep it aligned with the selected fixed-resolution backbone.\n- **train.num_epochs**: CLIP fine-tuning often converges quickly. Start with 10-20 epochs for domain adaptation, then increase only if validation loss is still improving.\n- **train.optim.vision_lr \u002F train.optim.text_lr**: Learning rates for the two encoders. CLIP is sensitive to high learning rates; reduce both if loss is unstable.\n- **model.freeze_vision_encoder \u002F model.freeze_text_encoder**: Defaults are false. Freezing one encoder can help when the dataset is small or only one modality needs adaptation.\n- **train.loss_type**: `siglip` is recommended for SigLIP2 and Radio-CLIP. Use `clip` for CLIP-style softmax loss.\n- **export.encoder_type**: `combined` exports one ONNX graph. `separate` exports independent vision and text graphs.\n- **gen_trt_engine.tensorrt.data_type**: TensorRT deployment supports `fp16` and `fp32`.\n\n## Hardware\n\nSingle-GPU training works for small datasets. Use 4+ GPUs for datasets with more than 100k images or large backbones. Use 16GB+ VRAM per GPU for small\u002Ffixed-resolution runs and larger GPUs for Radio-CLIP or high-resolution OpenCLIP variants.\n\n## Error Patterns\n\n**CUDA out of memory**: Reduce `dataset.train.batch_size`, `dataset.val.batch_size`, or the TensorRT opt\u002Fmax batch sizes. For export\u002Fdeploy, check `export.input_height` and `export.input_width` against the selected fixed-resolution backbone.\n\n**NaN loss**: Learning rate is too high for fine-tuning. Reduce `train.optim.vision_lr` and `train.optim.text_lr`, increase `train.optim.warmup_steps`, and verify that captions are valid non-empty text.\n\n**Zero retrieval or classification quality**: Check that captions and prompts match the target label vocabulary. CLIP compares image and text embeddings, so prompt wording matters.\n\n**Dataset size smaller than total batch size**: The total batch size is `batch_size * num_gpus`. If the dataset, especially validation, has fewer samples than this, reduce `dataset.val.batch_size` or `dataset.train.batch_size`.\n\n**Radio-CLIP config validation error**: Set `model.adaptor_name` explicitly to `siglip` or `clip`.\n\n**Naflex export failure**: `siglip2-so400m-patch16-naflex` is training-only in the current TAO docs and cannot be exported to ONNX or TensorRT. Use a fixed-resolution variant such as `siglip2-so400m-patch16-384`.\n\n**ONNX external data missing**: Models larger than 2 GB export an ONNX file plus an external data file. Keep both files in the same directory and do not rename the external data file before `gen_trt_engine`.\n\n**TensorRT shape mismatch**: When using dynamic batch export, provide min\u002Fopt\u002Fmax shape profiles for every input. Text sequence length must match the tokenizer length, commonly 77 for CLIP tokenizers and 64 for SigLIP2 tokenizers.\n\n**attention_mask warning**: `attention_mask` is currently accepted by exported graphs for compatibility, but TAO ignores its values and may remove it in a future release. Do not build new direct-ONNX inference code that depends on mask values.\n\n**Error merging spec.yaml with schema**: A Hydra\u002FOmegaConf config validation error. Common causes are putting `num_epochs` or `num_gpus` at the spec root instead of under `train.*`, or mixing up training image size (`model.image_size`) with export dimensions (`export.input_height` and `export.input_width`).\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 `clip.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 | `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.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| train | `encryption_key` | `key` | encryption key |\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","# CLIP\n\nContrastive Language-Image Pre-training model for zero-shot and fine-tuned image classification, image-text retrieval, and embedding extraction. Fine-tuning adapts CLIP's shared image-text embedding space to domain-specific image-caption data.\n\nNo default NGC pretrained checkpoint is required. When `train.pretrained_model_path`, `evaluate.checkpoint`, `inference.checkpoint`, or `export.checkpoint` is unset, TAO loads pretrained weights from HuggingFace for SigLIP2\u002FOpenCLIP variants or `torch.hub` for Radio-CLIP, so first use needs network access or a local mirror.\n\nSupported actions: `train`, `evaluate`, `inference`, `export`, `gen_trt_engine`.\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## Instructions\n\nUse this skill for NVIDIA TAO CLIP jobs: training, evaluation, embedding inference, ONNX export, and TensorRT engine generation. Start by identifying the requested action, then load only the referenced files needed for that action: `defaults.json` for default parameters, `config.json` for action\u002Fdata-source wiring, `references\u002Fspec_template.yaml` for full spec shape, and `references\u002Fmodel_info.yaml` for SDK metadata.\n\nFor dataset-backed actions, collect the required image, caption, list, or prompt files from the user and place the resolved paths in `spec_overrides`. For `export` and `gen_trt_engine`, infer parent artifacts from the upstream job when available; otherwise require explicit checkpoint, ONNX, or engine paths. Run `gen_trt_engine`, TensorRT `evaluate`, and TensorRT `inference` in the TAO Deploy image.\n\nFor TAO Deploy TensorRT actions (`gen_trt_engine`, TensorRT `evaluate`, and TensorRT `inference`), read `references\u002Ftao-deploy-clip.md` first. Deploy spec templates live in this skill's `references\u002F` folder with the `spec_template_deploy_*.yaml` prefix.\n\n## Training Requirements\n\n- **Dataset type:** image_text\n- **Formats:** custom image\u002Fcaption folders or WebDataset shards\n- **Monitoring metric:** val\u002Ft2i_mAP\n\n### Supported Models\n\n- **SigLIP2:** `siglip2-so400m-patch16-256` (default), `siglip2-so400m-patch14-224`, `siglip2-so400m-patch14-384`, `siglip2-so400m-patch16-384`, `siglip2-so400m-patch16-512`, `siglip2-so400m-patch16-naflex`\n- **Radio-CLIP:** `c-radio_v3-b`, `c-radio_v3-l`, `c-radio_v3-h`, `c-radio_v3-g`\n- **OpenCLIP \u002F NV-CLIP:** `ViT-L-14-SigLIP-CLIPA-224`, `ViT-L-14-SigLIP-CLIPA-336`, `ViT-H-14-SigLIP-CLIPA-224`, `ViT-H-14-SigLIP-CLIPA-336`, `ViT-H-14-SigLIP-CLIPA-574`\n\nRadio-CLIP requires `model.adaptor_name` to be set to `siglip` or `clip`.\n\n### Per-Action Dataset Requirements\n\n| Action | Spec Key | Source | Files | List? |\n|---|---|---|---|---|\n| train | dataset.train.datasets | train_datasets | image_dir: images.tar.gz, image_list_file: image_list.txt, caption_dir: captions.tar.gz | Yes |\n| train | dataset.train.wds.root_dir | train_wds_dataset | root directory containing `.tar` shards | No |\n| train | dataset.train.wds.shard_list_file | train_wds_dataset | shards.txt listing shard paths | No |\n| train | dataset.val.datasets | eval_dataset | image_dir: images.tar.gz, image_list_file: image_list.txt, caption_dir: captions.tar.gz | Yes |\n| evaluate | dataset.val.datasets | eval_dataset | image_dir: images.tar.gz, image_list_file: image_list.txt, caption_dir: captions.tar.gz | Yes |\n| inference | inference.datasets | inference_dataset | image_dir: images.tar.gz | Yes |\n| inference | inference.text_file | inference_dataset | prompts.txt | No |\n| export | export.checkpoint | parent train job or explicit checkpoint | checkpoint .pth, optional for pretrained export | No |\n| gen_trt_engine | gen_trt_engine.onnx_file | parent export job or explicit ONNX | clip_model.onnx | No |\n\nFor custom training, set `dataset.train.type: custom` and provide `dataset.train.datasets` entries. Image and caption files must share the same base name. `caption_file_suffix` defaults to `.txt`, and `image_list_file` is optional.\n\nFor WDS training, set `dataset.train.type: wds` and provide at least one of `dataset.train.wds.root_dir` or `dataset.train.wds.shard_list_file`. `root_dir` is scanned recursively for `.tar` shards. `shard_list_file` is a text file with one shard path per line; relative lines resolve under the list-file directory unless `root_dir` is also supplied, in which case they resolve under `root_dir`. Validation\u002Fevaluation data remains custom format via `dataset.val.datasets`.\n\n### Typical Spec Overrides\n\nData source overrides are mandatory for dataset-backed actions. Construct paths from the Per-Action Dataset Requirements table and include them in `spec_overrides`. For inference, provide at least one of `inference.datasets` or `inference.text_file`.\n\n```python\nS3_TRAIN = \"s3:\u002F\u002Fbucket\u002Fdata\u002Ftrain\"\nS3_WDS = \"s3:\u002F\u002Fbucket\u002Fdata\u002Fwds\"\nS3_EVAL = \"s3:\u002F\u002Fbucket\u002Fdata\u002Feval\"\nS3_INFER = \"s3:\u002F\u002Fbucket\u002Fdata\u002Finfer\"\n```\n\n**train, custom dataset:**\n```python\n{\n    \"train.num_epochs\": 10,\n    \"dataset.train.type\": \"custom\",\n    \"dataset.train.datasets\": [{\"image_dir\": f\"{S3_TRAIN}\u002Fimages.tar.gz\", \"image_list_file\": f\"{S3_TRAIN}\u002Fimage_list.txt\", \"caption_dir\": f\"{S3_TRAIN}\u002Fcaptions.tar.gz\"}],\n    \"dataset.val.datasets\": [{\"image_dir\": f\"{S3_EVAL}\u002Fimages.tar.gz\", \"image_list_file\": f\"{S3_EVAL}\u002Fimage_list.txt\", \"caption_dir\": f\"{S3_EVAL}\u002Fcaptions.tar.gz\"}],\n}\n```\n\n**train, WDS dataset:**\n```python\n{\n    \"train.num_epochs\": 10,\n    \"dataset.train.type\": \"wds\",\n    \"dataset.train.wds.root_dir\": f\"{S3_WDS}\",\n    \"dataset.train.wds.shard_list_file\": f\"{S3_WDS}\u002Fshards.txt\",\n    \"dataset.train.wds.samples_per_shard\": 10000,\n    \"dataset.val.datasets\": [{\"image_dir\": f\"{S3_EVAL}\u002Fimages.tar.gz\", \"image_list_file\": f\"{S3_EVAL}\u002Fimage_list.txt\", \"caption_dir\": f\"{S3_EVAL}\u002Fcaptions.tar.gz\"}],\n}\n```\n\n**evaluate:**\n```python\n{\n    \"dataset.val.datasets\": [{\"image_dir\": f\"{S3_EVAL}\u002Fimages.tar.gz\", \"image_list_file\": f\"{S3_EVAL}\u002Fimage_list.txt\", \"caption_dir\": f\"{S3_EVAL}\u002Fcaptions.tar.gz\"}],\n}\n```\n\nLeave `evaluate.checkpoint` unset for zero-shot evaluation with pretrained weights. Set `evaluate.trt_engine` instead of `evaluate.checkpoint` for TensorRT evaluation.\n\n**inference:**\n```python\n{\n    \"inference.datasets\": [{\"image_dir\": f\"{S3_INFER}\u002Fimages.tar.gz\"}],\n    \"inference.text_file\": f\"{S3_INFER}\u002Fprompts.txt\",\n}\n```\n\nInference writes `image_embeddings.h5` and\u002For `text_embeddings.h5` under `results_dir`. The saved embeddings are L2-normalized.\n\n**export:**\n```python\n{\n    \"export.onnx_file\": \"${results_dir}\u002Fexport\u002Fclip_model.onnx\",\n    \"export.encoder_type\": \"combined\",\n    \"export.batch_size\": -1,\n}\n```\n\nSet `export.encoder_type: separate` when deployment should use independent vision and text encoders. Separate export writes `_vision.onnx` and `_text.onnx` variants derived from the base `export.onnx_file`.\n\n**gen_trt_engine:**\n```python\n{\n    \"gen_trt_engine.onnx_file\": \"${results_dir}\u002Fexport\u002Fclip_model.onnx\",\n    \"gen_trt_engine.trt_engine\": \"${results_dir}\u002Fdeploy\u002Fclip_model.engine\",\n    \"gen_trt_engine.batch_size\": -1,\n    \"gen_trt_engine.tensorrt.data_type\": \"fp16\",\n    \"gen_trt_engine.tensorrt.min_batch_size\": 1,\n    \"gen_trt_engine.tensorrt.opt_batch_size\": 1,\n    \"gen_trt_engine.tensorrt.max_batch_size\": 16,\n}\n```\n\n## Eval Dataset\n\nOptional for training. If provided, validation metrics are computed at validation intervals. Required for `evaluate`.\n\n## Deploy Workflow\n\nThe skill exposes `gen_trt_engine` as the deploy action. In generated SDK runners, use `model_info[\"actions\"][\"gen_trt_engine\"]` and run it in the TAO Deploy image, not the PyTorch training image. The in-container command is `clip gen_trt_engine -e {config_path}`; direct TAO Launcher usage spells the same action as `tao deploy clip gen_trt_engine -e \u002Fpath\u002Fto\u002Fspec.yaml`.\n\nTAO Deploy supports both combined and separate encoder formats. For separate encoders, pass the base path without `_vision` or `_text` to `gen_trt_engine.onnx_file` and `gen_trt_engine.trt_engine`; TAO detects or writes the suffixed vision\u002Ftext files.\n\nUse `evaluate.trt_engine` for TensorRT evaluation and `inference.trt_engine` for TensorRT embedding extraction. These TensorRT paths also run in the TAO Deploy image. Direct TAO Launcher usage spells these as `tao deploy clip evaluate` and `tao deploy clip inference`.\n\nFull TAO Deploy reference: [tao-deploy-clip](references\u002Ftao-deploy-clip.md).\n\n## Important Parameters\n\n- **model.type**: Backbone family and resolution. Use fixed-resolution SigLIP2\u002FOpenCLIP variants for deployment.\n- **model.adaptor_name**: Required for Radio-CLIP. Set to `siglip` or `clip`.\n- **model.image_size**: Training transform image resolution. Keep it aligned with the selected fixed-resolution backbone.\n- **train.num_epochs**: CLIP fine-tuning often converges quickly. Start with 10-20 epochs for domain adaptation, then increase only if validation loss is still improving.\n- **train.optim.vision_lr \u002F train.optim.text_lr**: Learning rates for the two encoders. CLIP is sensitive to high learning rates; reduce both if loss is unstable.\n- **model.freeze_vision_encoder \u002F model.freeze_text_encoder**: Defaults are false. Freezing one encoder can help when the dataset is small or only one modality needs adaptation.\n- **train.loss_type**: `siglip` is recommended for SigLIP2 and Radio-CLIP. Use `clip` for CLIP-style softmax loss.\n- **export.encoder_type**: `combined` exports one ONNX graph. `separate` exports independent vision and text graphs.\n- **gen_trt_engine.tensorrt.data_type**: TensorRT deployment supports `fp16` and `fp32`.\n\n## Hardware\n\nSingle-GPU training works for small datasets. Use 4+ GPUs for datasets with more than 100k images or large backbones. Use 16GB+ VRAM per GPU for small\u002Ffixed-resolution runs and larger GPUs for Radio-CLIP or high-resolution OpenCLIP variants.\n\n## Error Patterns\n\n**CUDA out of memory**: Reduce `dataset.train.batch_size`, `dataset.val.batch_size`, or the TensorRT opt\u002Fmax batch sizes. For export\u002Fdeploy, check `export.input_height` and `export.input_width` against the selected fixed-resolution backbone.\n\n**NaN loss**: Learning rate is too high for fine-tuning. Reduce `train.optim.vision_lr` and `train.optim.text_lr`, increase `train.optim.warmup_steps`, and verify that captions are valid non-empty text.\n\n**Zero retrieval or classification quality**: Check that captions and prompts match the target label vocabulary. CLIP compares image and text embeddings, so prompt wording matters.\n\n**Dataset size smaller than total batch size**: The total batch size is `batch_size * num_gpus`. If the dataset, especially validation, has fewer samples than this, reduce `dataset.val.batch_size` or `dataset.train.batch_size`.\n\n**Radio-CLIP config validation error**: Set `model.adaptor_name` explicitly to `siglip` or `clip`.\n\n**Naflex export failure**: `siglip2-so400m-patch16-naflex` is training-only in the current TAO docs and cannot be exported to ONNX or TensorRT. Use a fixed-resolution variant such as `siglip2-so400m-patch16-384`.\n\n**ONNX external data missing**: Models larger than 2 GB export an ONNX file plus an external data file. Keep both files in the same directory and do not rename the external data file before `gen_trt_engine`.\n\n**TensorRT shape mismatch**: When using dynamic batch export, provide min\u002Fopt\u002Fmax shape profiles for every input. Text sequence length must match the tokenizer length, commonly 77 for CLIP tokenizers and 64 for SigLIP2 tokenizers.\n\n**attention_mask warning**: `attention_mask` is currently accepted by exported graphs for compatibility, but TAO ignores its values and may remove it in a future release. Do not build new direct-ONNX inference code that depends on mask values.\n\n**Error merging spec.yaml with schema**: A Hydra\u002FOmegaConf config validation error. Common causes are putting `num_epochs` or `num_gpus` at the spec root instead of under `train.*`, or mixing up training image size (`model.image_size`) with export dimensions (`export.input_height` and `export.input_width`).\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 `clip.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 | `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.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| train | `encryption_key` | `key` | encryption key |\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":49,"license":15,"metadata":52,"description":7,"allowed-tools":55,"compatibility":56},[50,36,32,51,40],"vision-language","zero-shot",{"author":53,"version":54},"NVIDIA Corporation","1.0.0","Read Bash","Requires docker + nvidia-container-toolkit.","main","7a940b8e5af16c95e5c190a524421d32fc7445a9",".claude\u002Fskills\u002Ftao-finetune-clip","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":65,"prompt":75,"zipAvailable":76},[66,69,72],{"tool":67,"command":68},"npx","npx skills add headmktlucca-ui\u002Fneuroads-lp --skill tao-finetune-clip",{"tool":70,"command":71},"bunx","bunx skills add headmktlucca-ui\u002Fneuroads-lp --skill tao-finetune-clip",{"tool":73,"command":74},"pnpm","pnpm dlx skills add headmktlucca-ui\u002Fneuroads-lp --skill tao-finetune-clip","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-finetune-clip\u002FSKILL.md",true,[78,84,88,92,96,100,104,108,112,116,120,124,128,132,136,140],{"path":79,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":82,"sourceHtmlUrl":83},"BENCHMARK.md","REFERENCE","参考文档",4226,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-finetune-clip\u002FBENCHMARK.md",{"path":85,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":86,"sourceHtmlUrl":87},"evals\u002Fevals.json",764,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-finetune-clip\u002Fevals\u002Fevals.json",{"path":89,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":90,"sourceHtmlUrl":91},"references\u002Fskill_info.yaml",4567,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-finetune-clip\u002Freferences\u002Fskill_info.yaml",{"path":93,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":94,"sourceHtmlUrl":95},"references\u002Fspec_template_deploy.yaml",606,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-finetune-clip\u002Freferences\u002Fspec_template_deploy.yaml",{"path":97,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":98,"sourceHtmlUrl":99},"references\u002Fspec_template_evaluate.yaml",1412,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-finetune-clip\u002Freferences\u002Fspec_template_evaluate.yaml",{"path":101,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":102,"sourceHtmlUrl":103},"references\u002Fspec_template_export.yaml",1495,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-finetune-clip\u002Freferences\u002Fspec_template_export.yaml",{"path":105,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":106,"sourceHtmlUrl":107},"references\u002Fspec_template_train.yaml",1322,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-finetune-clip\u002Freferences\u002Fspec_template_train.yaml",{"path":109,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":110,"sourceHtmlUrl":111},"references\u002Fspec_template.yaml",2079,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-finetune-clip\u002Freferences\u002Fspec_template.yaml",{"path":113,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":114,"sourceHtmlUrl":115},"references\u002Ftao-deploy-clip.md",4848,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-finetune-clip\u002Freferences\u002Ftao-deploy-clip.md",{"path":117,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":118,"sourceHtmlUrl":119},"references\u002Ftao-deploy-clip.skill_info.yaml",1990,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-finetune-clip\u002Freferences\u002Ftao-deploy-clip.skill_info.yaml",{"path":121,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":122,"sourceHtmlUrl":123},"schemas\u002Fevaluate.schema.json",27238,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-finetune-clip\u002Fschemas\u002Fevaluate.schema.json",{"path":125,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":126,"sourceHtmlUrl":127},"schemas\u002Fexport.schema.json",28063,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-finetune-clip\u002Fschemas\u002Fexport.schema.json",{"path":129,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":130,"sourceHtmlUrl":131},"schemas\u002Fmanifest.json",4626,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-finetune-clip\u002Fschemas\u002Fmanifest.json",{"path":133,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":134,"sourceHtmlUrl":135},"schemas\u002Ftrain.schema.json",24839,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-finetune-clip\u002Fschemas\u002Ftrain.schema.json",{"path":137,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":138,"sourceHtmlUrl":139},"skill-card.md",3794,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-finetune-clip\u002Fskill-card.md",{"path":141,"resourceType":142,"resourceTypeDesc":143,"sizeBytes":144,"sourceHtmlUrl":145},"skill.oms.sig","OTHER","其他",7529,"https:\u002F\u002Fgithub.com\u002Fheadmktlucca-ui\u002Fneuroads-lp\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftao-finetune-clip\u002Fskill.oms.sig",[147,171,195,221,239,274],{"skillNo":148,"name":149,"nameZh":6,"description":150,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":151,"licenseFileUrl":6,"sourceHtmlUrl":152,"categories":153,"keywords":160,"publishedAt":44},"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",[154,157],{"categoryNo":155,"categoryName":156,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":158,"categoryName":159,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[161,162,163,164,165,28,166,167,168,169,170],"xunit","xunit skill","testing","injection","user","tests","triggers","unit","unit-testing","C#",{"skillNo":172,"name":173,"nameZh":6,"description":174,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":151,"licenseFileUrl":6,"sourceHtmlUrl":175,"categories":176,"keywords":179,"publishedAt":44},"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",[177,178],{"categoryNo":155,"categoryName":156,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":158,"categoryName":159,"taxonomyType":21,"taxonomyTypeDesc":22},[180,181,163,182,183,184,185,186,28,187,188,189,190,191,166,167,192,193,29,194],"xcuitest","xcuitest skill","automation","test","testing framework","ios","devices","mobile","mobile-testing","ui test","local","apple","apps","native","objective",{"skillNo":196,"name":197,"nameZh":6,"description":198,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":151,"licenseFileUrl":6,"sourceHtmlUrl":199,"categories":200,"keywords":205,"publishedAt":44},"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",[201,204],{"categoryNo":202,"categoryName":203,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":158,"categoryName":159,"taxonomyType":21,"taxonomyTypeDesc":22},[206,207,208,209,210,211,212,213,28,214,215,216,217,218,219,29,220],"builder","world","world builder","MCP","create","mcp tools","Tools","game","pokemon","manage","style","via","theme","zone","generative",{"skillNo":222,"name":223,"nameZh":6,"description":224,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":151,"licenseFileUrl":6,"sourceHtmlUrl":225,"categories":226,"keywords":229,"publishedAt":44},"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",[227,228],{"categoryNo":155,"categoryName":156,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":158,"categoryName":159,"taxonomyType":21,"taxonomyTypeDesc":22},[230,163,231,182,232,233,234,235,165,28,236,190,166,167,237,238],"webdriverio skill","typescript","javascript","browser","cloud","e2e","e2e-testing","URL","conf",{"skillNo":240,"name":241,"nameZh":6,"description":242,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":151,"licenseFileUrl":6,"sourceHtmlUrl":243,"categories":244,"keywords":254,"publishedAt":44},"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",[245,248,249],{"categoryNo":246,"categoryName":247,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000009","前端开发",{"categoryNo":202,"categoryName":203,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":250,"categoryName":251,"taxonomyType":252,"taxonomyTypeDesc":253},"01JBSEEDCAT000000000000032","设计师","PROFESSION","适用职业",[255,256,257,258,259,260,261,262,263,264,265,266,267,268,269,270,271,272,167,273],"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":275,"name":276,"nameZh":6,"description":277,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":151,"licenseFileUrl":6,"sourceHtmlUrl":278,"categories":279,"keywords":282,"publishedAt":44},"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",[280,281],{"categoryNo":202,"categoryName":203,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":250,"categoryName":251,"taxonomyType":252,"taxonomyTypeDesc":253},[255,257,283,264,267,28,284,285,191,272,286,167,192,287,29,288,289],"watchos design guidelines","workout","human","watch","interface","platform-design","features"]