Revert "feat(cloud-storage): add cloud storage skill + fix MCP resource links"

README.md

@@ -126,7 +126,6 @@ The `npx skills` CLI works with any agent that reads `SKILL.md` files from `.cla
 ## Available skills
 
 - **api-reference**: REST API and inference API references
-- **cloud-storage**: connecting S3/GCS buckets to mirror images into a workspace
 - **data-management**: uploading images, labeling, dataset organization
 - **inference**: running inference, workflows, workflow templates
 - **plans-and-pricing**: Roboflow plans and credit usage

skills/data-management/SKILL.md

@@ -28,7 +28,6 @@ Project type is set at creation and **cannot be changed later**.
 |--------|----------|---------|
 | Web UI drag-and-drop | < 1,000 images | JPG, PNG, WEBP, AVIF, BMP, MOV, MP4, PDF + 40+ annotation formats |
 | CLI (`roboflow import`) | > 1,000 images (images only) | Same image formats, no video |
-| Cloud storage bucket mirror | Extensive or continuously-growing data already in S3 / GCS | See `roboflow://skills/cloud-storage/SKILL` |
 | Dataset Upload Workflow Block | Collecting from production Workflows | Programmatic |
 | Universe fork | Starting from a public dataset | Any Universe dataset |
 
@@ -213,5 +212,4 @@ Prefab MCP apps (`create_project_app`) exist when parameters are unclear, you ne
 
 ## Related Pages
 
-- `roboflow://skills/data-management/labeling` — annotation tools, AI labeling, Label Assist, Smart Polygon, Auto Label, annotation jobs
-- `roboflow://skills/cloud-storage/SKILL` — mirror an S3/GCS bucket into the workspace (credentials, datasources, glob rules, scheduled sync)
+- `roboflow://skills/roboflow-labeling/SKILL` — annotation tools, AI labeling, Label Assist, Smart Polygon, Auto Label, annotation jobs

skills/product-navigation/features-by-page.md

@@ -10,9 +10,8 @@ Base URL: `https://app.roboflow.com`
 
 | Intent | Web URL | Alternatives |
 |--------|---------|-------------|
-| Upload images/videos from your computer (local files) | `/{ws}/{proj}/upload` | Python SDK: `project.upload(path)`, MCP: `image_upload` + `image_upload_status` |
+| Upload images/videos | `/{ws}/{proj}/upload` | Python SDK: `project.upload(path)`, MCP: `image_upload` + `image_upload_status` |
 | Import from S3/GCS/Azure | `/{ws}/{proj}/upload` -> Cloud Import tab | Python SDK with cloud URLs |
-| Import images from cloud storage (S3 / GCS bucket mirror) | `/{ws}/settings/datasources` | MCP: `connect_cloud_storage`; see `roboflow://skills/cloud-storage/SKILL` |
 | Import from Universe | `/{ws}/{proj}/upload` -> Universe tab | MCP: `universe_search` then fork |
 | Upload pre-annotated data | `/{ws}/{proj}/upload` (drag folder with annotations) | Python SDK: `project.upload(path)` auto-detects annotations |
 

skills/training-and-evaluation/SKILL.md

@@ -279,5 +279,5 @@ Auto-runs after training. Access: Models > click model version > View Evaluation
 
 ## Related Pages
 
-- `roboflow://skills/training-and-evaluation/improvement-playbook` — diagnostic decision tree, confusion matrix guide, per-class metrics, architecture switching, iterative improvement checklist
+- `roboflow://skills/roboflow-model-improvement/SKILL` — diagnostic decision tree, confusion matrix guide, per-class metrics, architecture switching, iterative improvement checklist
 - `roboflow://skills/training-and-evaluation/active-learning` — production feedback loop: Dataset Upload workflow block, confidence-based sampling, review and retrain cycle

skills/training-and-evaluation/active-learning.md

@@ -59,7 +59,7 @@ Active learning is most effective when it's targeted, not random. Use the model
 | Small objects missed | High-resolution images with small instances |
 | Dataset distribution mismatch (new environment) | Random sample from the new deployment context |
 
-See `roboflow://skills/training-and-evaluation/improvement-playbook` for the full diagnostic decision tree.
+See `roboflow://skills/roboflow-model-improvement/SKILL` for the full diagnostic decision tree.
 
 ## Common Mistakes