← RoboflowCONTENT HISTORY
WHAT CHANGED
added
Update to Roboflow
Snapshot Oct 27, 2026 · 00:59 UTC · version 1.0.3
Package or technical metadata updated
Package or technical metadata updated
Observed in package metadata. These changes alone do not establish a new customer-facing feature.
Save Roboflow and check future changes in Following.
Up to 10 plugins free · no card required.
All fields and original values.
Is v2 template
Before
Oct 24, 2026 · 13:44 UTC
Not present
After
Oct 27, 2026 · 00:59 UTC
false
Compare saved observations
Download comparison JSONFull technical diff · 1 changed fields
added /is_v2_template
BEFORE
Field was absent
AFTER
false
Full snapshot data
{
"canonical_app_id": "asdk_app_6ac2713d52dc8191913b283379e39840",
"connector_id": "asdk_app_6ac2713d52dc8191913b283379e39840",
"created_at": "2026-10-04T16:50:47.456431Z",
"discoverability": "LISTED",
"id": "plugin_asdk_app_6ac2713d52dc8191913b283379e39840",
"is_template": false,
"is_template_instance": false,
"is_v2_template": false,
"name": "roboflow-computer-vision",
"release": {
"app_ids": [
"asdk_app_6ac2713d52dc8191913b283379e39840"
],
"app_manifest": {
"apps": {
"roboflow": {
"id": "asdk_app_6ac2713d52dc8191913b283379e39840",
"required": true
}
}
},
"app_templates": [],
"description": "Roboflow computer vision tools and workflow skills for datasets, annotation, training, inference, and deployment.",
"display_name": "Roboflow",
"id": "pluginrel_6139eb9253d88191a27ddc1005c2aa4a",
"interface": {
"brand_color": "#6706CE",
"capabilities": [],
"category": "Developer Tools",
"composer_icon_dark_url": null,
"composer_icon_url": "https://files.openai.com/content?id=file_000000006a5c820eacd093162d178a07",
"default_prompt": "Find a pretrained model to detect hard hats",
"default_prompts": [
"Find a pretrained model to detect hard hats",
"Train a model to count cars in my parking lot video",
"Show my Roboflow projects and their image counts"
],
"developer_name": "Roboflow, Inc.",
"logo_url": "https://files.openai.com/content?id=file_000000002898820eb9fdcc0fec162cdd",
"logo_url_dark": null,
"long_description": "Roboflow turns images and videos into intelligence. Go from idea to production right from the conversation: find a ready-made model or train one on your images, build vision applications, and deploy them as an API or on your own devices. Roboflow is an end-to-end platform for vision AI.\n\nRoboflow works inside the workspaces your connected account can access, with the same permissions. Training, auto labeling, and deployments use your workspace credits. A Roboflow account is required.",
"plugin_category_id": "developer tools",
"privacy_policy_url": "https://roboflow.com/privacy",
"screenshot_urls": [],
"short_description": "AI for the physical world",
"terms_of_service_url": "https://roboflow.com/terms",
"website_url": "https://roboflow.com"
},
"keywords": [],
"mcp_servers": [
{
"key": "roboflow",
"metadata": {
"headers": {},
"type": "streamable-http",
"url": "https://mcp.roboflow.com/openai/mcp"
}
}
],
"onboarding_skill_name": null,
"requires_local_executor": false,
"skills": [
{
"description": "Draw computer vision annotations, labels, and predictions over images and videos using supervision-js in JavaScript/TypeScript or Supervision in Python.",
"interface": {
"brand_color": null,
"default_prompt": null,
"display_name": "draw-vision",
"icon_large_url": null,
"icon_small_url": null,
"iconography": "code",
"short_description": "Draw computer vision annotations, labels, and predictions over images and videos using supervision-js in JavaScript/TypeScript or Supervision in Python."
},
"name": "draw-vision",
"plugin_release_skill_id": "pluginrsk_6ad156fdc1308191a60b824a2a4220f9"
},
{
"description": "Protocol-level facts for Roboflow REST and Inference APIs — URL patterns, auth, parameters, error codes, and SDK quick-start. For deployment strategy and Workflow execution patterns, see roboflow-inference.",
"interface": {
"brand_color": null,
"default_prompt": null,
"display_name": "roboflow-api-reference",
"icon_large_url": null,
"icon_small_url": null,
"iconography": "code",
"short_description": "Protocol-level facts for Roboflow REST and Inference APIs — URL patterns, auth, parameters, error codes, and SDK quick-start. For deployment strategy and Workflow execution patterns, see roboflow-inference."
},
"name": "roboflow-api-reference",
"plugin_release_skill_id": "pluginrsk_6ad156ff1084819184297ff9ac4fb06c"
},
{
"description": "Use when running a Roboflow Workflow over many images or videos with batch processing — Asset Library jobs (the platform stages workspace images for you) or staged jobs (you stage external local/cloud files with the inference-cli), plus monitoring jobs, downloading results, and routing imports to datasources (bucket mirror) instead.",
"interface": {
"brand_color": null,
"default_prompt": null,
"display_name": "roboflow-batch-processing",
"icon_large_url": null,
"icon_small_url": null,
"iconography": "bolt",
"short_description": "Use when running a Roboflow Workflow over many images or videos with batch processing — Asset Library jobs (the platform stages workspace images for you) or staged jobs (you stage external local/cloud files with the inference-cli), plus monitoring jobs, downloading results, and routing imports to datasources (bucket mirror) instead."
},
"name": "roboflow-batch-processing",
"plugin_release_skill_id": "pluginrsk_6ad156fdf92c81918c97673ef37bec06"
},
{
"description": "Use when connecting cloud storage (AWS S3 / S3-compatible or Google Cloud Storage) to Roboflow to mirror images into a workspace — creating storage credentials, defining datasources (bucket-mirror configs), selecting objects with glob rules, validating access, and running/scheduling mirror jobs.",
"interface": {
"brand_color": null,
"default_prompt": null,
"display_name": "roboflow-cloud-storage",
"icon_large_url": null,
"icon_small_url": null,
"iconography": "hierarchy",
"short_description": "Use when connecting cloud storage (AWS S3 / S3-compatible or Google Cloud Storage) to Roboflow to mirror images into a workspace — creating storage credentials, defining datasources (bucket-mirror configs), selecting objects with glob rules, validating access, and running/scheduling mirror jobs."
},
"name": "roboflow-cloud-storage",
"plugin_release_skill_id": "pluginrsk_6ad156fdc2a08191b03085b079c79811"
},
{
"description": "Use when uploading locally trained model weights (YOLO, RF-DETR, YOLO-NAS, PaliGemma, Florence-2) to Roboflow — the client-side Python SDK upload flow, safe API key handling, per-family packaging requirements, and verifying the upload.",
"interface": {
"brand_color": null,
"default_prompt": null,
"display_name": "roboflow-custom-weights-upload",
"icon_large_url": null,
"icon_small_url": null,
"iconography": "code",
"short_description": "Use when uploading locally trained model weights (YOLO, RF-DETR, YOLO-NAS, PaliGemma, Florence-2) to Roboflow — the client-side Python SDK upload flow, safe API key handling, per-family packaging requirements, and verifying the upload."
},
"name": "roboflow-custom-weights-upload",
"plugin_release_skill_id": "pluginrsk_6ad156ff4dd08191912c35fad130652b"
},
{
"description": "Use when uploading images, labeling, organizing datasets, creating Roboflow projects (detection/segmentation/keypoint/classification), tags, splits, versions, or RoboQL search.",
"interface": {
"brand_color": null,
"default_prompt": null,
"display_name": "roboflow-data-management",
"icon_large_url": null,
"icon_small_url": null,
"iconography": "hierarchy",
"short_description": "Use when uploading images, labeling, organizing datasets, creating Roboflow projects (detection/segmentation/keypoint/classification), tags, splits, versions, or RoboQL search."
},
"name": "roboflow-data-management",
"plugin_release_skill_id": "pluginrsk_6ad157009a84819184bf39ccf0443ae9"
},
{
"description": "Deployment option comparison (serverless, dedicated, self-hosted, batch) and Workflow execution patterns. For raw API URL patterns, auth, and request/response formats, see roboflow-api-reference.",
"interface": {
"brand_color": null,
"default_prompt": null,
"display_name": "roboflow-inference",
"icon_large_url": null,
"icon_small_url": null,
"iconography": "code",
"short_description": "Deployment option comparison (serverless, dedicated, self-hosted, batch) and Workflow execution patterns. For raw API URL patterns, auth, and request/response formats, see roboflow-api-reference."
},
"name": "roboflow-inference",
"plugin_release_skill_id": "pluginrsk_6ad157002ffc8191b76a2bd323083835"
},
{
"description": "Use when answering questions about Roboflow plans, credit usage, or cost estimation; directs users to roboflow.com/pricing for current dollar amounts.",
"interface": {
"brand_color": null,
"default_prompt": null,
"display_name": "roboflow-plans-and-pricing",
"icon_large_url": null,
"icon_small_url": null,
"iconography": "chart",
"short_description": "Use when answering questions about Roboflow plans, credit usage, or cost estimation; directs users to roboflow.com/pricing for current dollar amounts."
},
"name": "roboflow-plans-and-pricing",
"plugin_release_skill_id": "pluginrsk_6ad156ff463c81919235028a8b765378"
},
{
"description": "Use when explaining where Roboflow features live in the app.roboflow.com web app, mapping intents like upload, annotate, train, deploy to specific page URLs.",
"interface": {
"brand_color": null,
"default_prompt": null,
"display_name": "roboflow-product-navigation",
"icon_large_url": null,
"icon_small_url": null,
"iconography": "cursor",
"short_description": "Use when explaining where Roboflow features live in the app.roboflow.com web app, mapping intents like upload, annotate, train, deploy to specific page URLs."
},
"name": "roboflow-product-navigation",
"plugin_release_skill_id": "pluginrsk_6ad156fef12c8191b6fe67c73b61cca3"
},
{
"description": "Use when training Roboflow models, diagnosing why a model underperforms, improving accuracy, or setting up a production feedback loop — covers architecture selection, model IDs, checkpoints, Model Evaluation (confusion matrix, per-class metrics, MCP eval tools), the diagnosis-first improvement playbook, and Active Learning through the Project Model Workflow block.",
"interface": {
"brand_color": null,
"default_prompt": null,
"display_name": "roboflow-training-and-evaluation",
"icon_large_url": null,
"icon_small_url": null,
"iconography": "chart",
"short_description": "Use when training Roboflow models, diagnosing why a model underperforms, improving accuracy, or setting up a production feedback loop — covers architecture selection, model IDs, checkpoints, Model Evaluation (confusion matrix, per-class metrics, MCP eval tools), the diagnosis-first improvement playbook, and Active Learning through the Project Model Workflow block."
},
"name": "roboflow-training-and-evaluation",
"plugin_release_skill_id": "pluginrsk_6ad157001acc8191823359ddaadd02e4"
},
{
"description": "Use when searching for or using public datasets/models on Roboflow Universe (universe.roboflow.com), the open repository of 1M+ computer vision datasets and 50K+ pre-trained models.",
"interface": {
"brand_color": null,
"default_prompt": null,
"display_name": "roboflow-universe",
"icon_large_url": null,
"icon_small_url": null,
"iconography": "search",
"short_description": "Use when searching for or using public datasets/models on Roboflow Universe (universe.roboflow.com), the open repository of 1M+ computer vision datasets and 50K+ pre-trained models."
},
"name": "roboflow-universe",
"plugin_release_skill_id": "pluginrsk_6ad156fdd2dc81918406c2f4d089bab8"
}
],
"version": "1.0.3"
},
"scope": "GLOBAL",
"share_url": "https://chatgpt.com/plugins/plugin_asdk_app_6ac2713d52dc8191913b283379e39840?open_in_app",
"status": "ENABLED"
}SHA-256 of public snapshot: bcc061d7968d74e99fe52c58e7d3a6c62a9e1a72cef36275525ea2fb92d3f677