Update to Ultralytics YOLO

{
  "canonical_app_id": null,
  "connector_id": null,
  "created_at": "2026-10-06T18:12:46.756858Z",
  "discoverability": "LISTED",
  "id": "plugins_6ac51f0691748191b2d31e8c84d99c62",
  "is_template": false,
  "is_template_instance": false,
  "is_v2_template": false,
  "name": "yolo",
  "release": {
    "app_ids": [],
    "app_manifest": null,
    "app_templates": [],
    "description": "Agent skills for Ultralytics YOLO and Platform: model selection, dataset annotation, training, tuning, inference, export, and deployment through the Platform web UI, the Python package, and the yolo and ul CLIs.",
    "display_name": "Ultralytics YOLO",
    "id": "pluginrel_6c66f1188f408191a69202048614999b",
    "interface": {
      "brand_color": "#042AFF",
      "capabilities": [
        "Interactive",
        "Write"
      ],
      "category": "Developer Tools",
      "composer_icon_dark_url": "https://files.openai.com/content?id=file_00000000b6a88246b92a19542887d7af",
      "composer_icon_url": "https://files.openai.com/content?id=file_00000000007081f4a23711f5dea7403b",
      "default_prompt": "Run YOLO on a sample image and show me what it detects",
      "default_prompts": [
        "Run YOLO on a sample image and show me what it detects",
        "Turn my images into a custom YOLO model, labeled and trained in Ultralytics Platform",
        "Deploy my YOLO model as an API endpoint or export it to ONNX, TensorRT, or CoreML"
      ],
      "developer_name": "Ultralytics",
      "logo_url": "https://files.openai.com/content?id=file_0000000081e082109b8c3b5749881b11",
      "logo_url_dark": "https://files.openai.com/content?id=file_00000000397c824389495af5708620f6",
      "long_description": "Ultralytics YOLO skills help Codex build computer-vision models end to end, in Ultralytics Platform or local code. Choose the right YOLO model, upload and annotate datasets, train on cloud or local GPUs, improve accuracy, and run inference, tracking, and Solutions such as object counting, then export to ONNX, TensorRT, CoreML, Core AI, OpenVINO, or NPU formats or deploy a dedicated endpoint. The skills also script Platform with the ul CLI, and they defer to your installed ultralytics version over their own tables.",
      "plugin_category_id": "developer tools",
      "privacy_policy_url": "https://www.ultralytics.com/legal/privacy",
      "screenshot_urls": [],
      "short_description": "Train and deploy vision AI",
      "terms_of_service_url": "https://www.ultralytics.com/legal/terms-of-service",
      "website_url": "https://www.ultralytics.com"
    },
    "keywords": [
      "ultralytics",
      "yolo",
      "computer-vision",
      "object-detection",
      "segmentation",
      "pose",
      "training",
      "annotation",
      "cloud-training",
      "platform",
      "onnx",
      "tensorrt"
    ],
    "mcp_servers": [],
    "onboarding_skill_name": null,
    "requires_local_executor": false,
    "skills": [
      {
        "description": "Use when operating Ultralytics Platform from a terminal or script with the ul cloud CLI (ul cloud RESOURCE OPERATION key=value, PyPI package ultralytics-platform) — listing, creating, updating, cloning, or moving projects, datasets, and models; inspecting dataset images, statistics, metadata, duplicates, and similar images; starting and monitoring cloud training runs; per-image model validation analysis; downloading weights; exports, deployments, uploads, trash and restore, storage integrations, and account usage, storage, and billing; and building Agents (YOLO, LLM, gate, and alert workflows). For the Platform web UI or local yolo commands, see yolo; for choosing what to train and how to improve it, see yolo-training and yolo-tuning.\n",
        "interface": {
          "brand_color": null,
          "default_prompt": "Use $platform-cli to manage and inspect my Platform datasets, models, training runs, and usage with the ul cloud CLI.",
          "display_name": "Platform CLI",
          "icon_large_url": null,
          "icon_small_url": null,
          "iconography": "code",
          "short_description": "Script and inspect Platform resources with the ul cloud CLI"
        },
        "name": "platform-cli",
        "plugin_release_skill_id": "pluginrsk_6ac538e5aadc8191a37aa8953ae7bfa6"
      },
      {
        "description": "Use for ANY task involving Ultralytics Platform, the ultralytics Python package, yolo CLI, YOLO model weights (.pt), dataset annotation, training, validation, prediction, tracking, export, deployment, or the detect / segment / semantic / depth / classify / pose / OBB vision tasks.\n",
        "interface": {
          "brand_color": null,
          "default_prompt": "Use $yolo to plan and run the simplest Ultralytics workflow for my vision task.",
          "display_name": "Ultralytics YOLO",
          "icon_large_url": null,
          "icon_small_url": null,
          "iconography": "code",
          "short_description": "Use YOLO locally or through Ultralytics Platform"
        },
        "name": "yolo",
        "plugin_release_skill_id": "pluginrsk_6ac538e4b448819194ba3e5d70543ca6"
      },
      {
        "description": "Use when uploading, annotating, building, converting, analyzing, or debugging datasets in Ultralytics Platform or local YOLO — Platform dataset management and Smart Annotation, data.yaml, YOLO label .txt formats, COCO/DOTA/mask conversion, auto-labeling, splits, validation, and errors like \"no labels found\" or mAP near 0. Covers detect, segment, semantic, depth, classify, pose, and OBB data.\n",
        "interface": {
          "brand_color": null,
          "default_prompt": "Use $yolo-datasets to prepare and validate my dataset in Platform or local YOLO.",
          "display_name": "YOLO Datasets",
          "icon_large_url": null,
          "icon_small_url": null,
          "iconography": "chart",
          "short_description": "Prepare, annotate, and validate YOLO datasets"
        },
        "name": "yolo-datasets",
        "plugin_release_skill_id": "pluginrsk_6ac538e65edc8191b32465b0d55d75bf"
      },
      {
        "description": "Use when exporting or deploying Ultralytics YOLO models in Platform or code — the Platform Export tab and yolo export/model.export() for ONNX, TensorRT, CoreML, Core AI, OpenVINO, LiteRT, NCNN, ExecuTorch, and NPUs (RKNN, QNN, Hailo, Ascend, IMX, Axelera, DeepX, Xilinx), FP16/INT8 quantization, benchmarking, and non-Python runtimes. For inference with .pt weights or Platform endpoints, see yolo-inference.\n",
        "interface": {
          "brand_color": null,
          "default_prompt": "Use $yolo-export to export my model for my target hardware and verify its accuracy.",
          "display_name": "YOLO Export",
          "icon_large_url": null,
          "icon_small_url": null,
          "iconography": "code",
          "short_description": "Export YOLO models for production deployment"
        },
        "name": "yolo-export",
        "plugin_release_skill_id": "pluginrsk_6ac538e5cf488191b2dabafb7851b9e4"
      },
      {
        "description": "Use when testing, running, or deploying Ultralytics YOLO inference in Platform or code on images, video, webcams, or streams — Platform Predict and dedicated endpoints, model.predict()/yolo predict, Results API boxes/masks/keypoints, persistent tracking, annotated video, and Solutions such as counting, heatmaps, speed, queues, and parking. For optimized runtime exports, see yolo-export.\n",
        "interface": {
          "brand_color": null,
          "default_prompt": "Use $yolo-inference to run or deploy inference through Platform or local YOLO.",
          "display_name": "YOLO Inference",
          "icon_large_url": null,
          "icon_small_url": null,
          "iconography": "code",
          "short_description": "Run, track, and deploy YOLO model inference"
        },
        "name": "yolo-inference",
        "plugin_release_skill_id": "pluginrsk_6ac538e5c20c8191adab6d31dc37fc8f"
      },
      {
        "description": "Use when choosing or comparing Ultralytics models in Platform or code — picking a model family (YOLO26/YOLO11/YOLOv8, YOLO-World, YOLOE, SAM/SAM2/FastSAM, RT-DETR, YOLO-NAS), size (n/s/m/l/x), task variant (-seg, -sem, -cls, -pose, -obb, -depth), pretrained checkpoint, open-vocabulary or promptable detection/segmentation, custom architecture, Platform Explore, or exact weight names and availability.\n",
        "interface": {
          "brand_color": null,
          "default_prompt": "Use $yolo-models to pick the right YOLO model and size for my task and hardware.",
          "display_name": "YOLO Models",
          "icon_large_url": null,
          "icon_small_url": null,
          "iconography": "code",
          "short_description": "Choose and compare Ultralytics YOLO models"
        },
        "name": "yolo-models",
        "plugin_release_skill_id": "pluginrsk_6ac538e5320c8191a10956fb2c737bbf"
      },
      {
        "description": "Use when training, fine-tuning, or validating Ultralytics YOLO models in Platform, cloud GPUs, or local code — model.train(), yolo train/val, remote metric streaming, epochs, batch, imgsz, devices, augmentation, multi-GPU, resumes, results, and fixing OOM, NaN loss, low mAP, or overfitting. For hyperparameter search and systematic improvement loops, see yolo-tuning.\n",
        "interface": {
          "brand_color": null,
          "default_prompt": "Use $yolo-training to train and validate my model with Platform or local compute.",
          "display_name": "YOLO Training",
          "icon_large_url": null,
          "icon_small_url": null,
          "iconography": "code",
          "short_description": "Train YOLO models locally or on cloud GPUs"
        },
        "name": "yolo-training",
        "plugin_release_skill_id": "pluginrsk_6ac538e4b5a081918f7253dea6c5c8de"
      },
      {
        "description": "Use when improving or comparing Ultralytics YOLO models in Platform or code, or running hyperparameter search/autotraining — Platform experiment comparison, the systematic improvement playbook, model.tune() genetic evolution, Ray Tune, search spaces, and deciding whether tuning is worthwhile. For one training run and its arguments, see yolo-training.\n",
        "interface": {
          "brand_color": null,
          "default_prompt": "Use $yolo-tuning to diagnose and improve my model with evidence-backed experiments.",
          "display_name": "YOLO Tuning",
          "icon_large_url": null,
          "icon_small_url": null,
          "iconography": "chart",
          "short_description": "Improve YOLO accuracy and tune hyperparameters"
        },
        "name": "yolo-tuning",
        "plugin_release_skill_id": "pluginrsk_6ac538e4bf6881918547f095449bd92a"
      }
    ],
    "version": "0.5.0"
  },
  "scope": "GLOBAL",
  "share_url": "https://chatgpt.com/plugins/plugins_6ac51f0691748191b2d31e8c84d99c62?open_in_app",
  "status": "ENABLED"
}