Custom Vision Training Client Skill
microsoft-com-cognitiveservices-training
Endpoints
| Method | Path | Description |
|---|---|---|
GET | /domains | |
GET | /domains/{domainId} | Get a list of the available domains. |
GET | /projects | Get information about a specific domain. |
POST | /projects | Get your projects. |
GET | /projects/{projectId} | Create a project. |
DELETE | /projects/{projectId} | Get a specific project. |
PATCH | /projects/{projectId} | Delete a specific project. |
GET | /projects/{projectId}/export | Update a specific project. |
POST | /projects/{projectId}/images | Exports a project. |
DELETE | /projects/{projectId}/images | This API accepts body content as multipart/form-data and application/octet-stream. When using multipart |
POST | /projects/{projectId}/images/{imageId}/regionproposals | Delete images from the set of training images. |
POST | /projects/{projectId}/images/files | This API will get region proposals for an image along with confidences for the region. It returns an empty array if no proposals are found. |
GET | /projects/{projectId}/images/id | This API accepts a batch of files, and optionally tags, to create images. There is a limit of 64 images and 20 tags. |
POST | /projects/{projectId}/images/predictions | This API will return a set of Images for the specified tags and optionally iteration. If no iteration is specified the |
POST | /projects/{projectId}/images/regions | This API creates a batch of images from predicted images specified. There is a limit of 64 images and 20 tags. |
DELETE | /projects/{projectId}/images/regions | This API accepts a batch of image regions, and optionally tags, to update existing images with region information. |
POST | /projects/{projectId}/images/suggested | Delete a set of image regions. |
POST | /projects/{projectId}/images/suggested/count | This API will fetch untagged images filtered by suggested tags Ids. It returns an empty array if no images are found. |
GET | /projects/{projectId}/images/tagged | This API takes in tagIds to get count of untagged images per suggested tags for a given threshold. |
GET | /projects/{projectId}/images/tagged/count | This API supports batching and range selection. By default it will only return first 50 images matching images. |
POST | /projects/{projectId}/images/tags | The filtering is on an and/or relationship. For example, if the provided tag ids are for the "Dog" and |
DELETE | /projects/{projectId}/images/tags | Associate a set of images with a set of tags. |
GET | /projects/{projectId}/images/untagged | Remove a set of tags from a set of images. |
GET | /projects/{projectId}/images/untagged/count | This API supports batching and range selection. By default it will only return first 50 images matching images. |
POST | /projects/{projectId}/images/urls | This API returns the images which have no tags for a given project and optionally an iteration. If no iteration is specified the |
GET | /projects/{projectId}/iterations | This API accepts a batch of urls, and optionally tags, to create images. There is a limit of 64 images and 20 tags. |
GET | /projects/{projectId}/iterations/{iterationId} | Get iterations for the project. |
DELETE | /projects/{projectId}/iterations/{iterationId} | Get a specific iteration. |
PATCH | /projects/{projectId}/iterations/{iterationId} | Delete a specific iteration of a project. |
GET | /projects/{projectId}/iterations/{iterationId}/export | Update a specific iteration. |
Install as Skill
Use this API as a Claude Code skill for instant agent access.
CLI Install
lapsh skill-install microsoft-com-cognitiveservices-training
Downloads and installs to ~/.claude/skills/microsoft-com-cognitiveservices-training/
Recent Versions (1)
3.2(2026-02-13)