How do I install the Custom Vision Prediction Client skill?

Run npx skillmds@latest add lap-platform/custom-vision-prediction-client in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Custom Vision Prediction Client safe to use?

This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. Capability flags: makes network calls, reads secrets. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Custom Vision Prediction Client?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Custom Vision Prediction Client free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Custom Vision Prediction Client?

Lap-Platform (@lap-platform) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Custom Vision Prediction Client by lap-platform

Name: Custom Vision Prediction Client
Rating: 4.2 (5 reviews)
Author: Lap-Platform

File contents

Custom Vision Prediction Client

API version: 3.0

Auth

ApiKey Prediction-Key in header

Base URL

https://southcentralus.api.cognitive.microsoft.com/customvision/v3.0/prediction

Setup

Set your API key in the appropriate header
POST /{projectId}/classify/iterations/{publishedName}/url -- create first url

Endpoints

8 endpoints across 1 groups. See references/api-spec.lap for full details.

{projectId}

Method	Path	Description
POST	/{projectId}/classify/iterations/{publishedName}/url	Classify an image url and saves the result.
POST	/{projectId}/classify/iterations/{publishedName}/image	Classify an image and saves the result.
POST	/{projectId}/classify/iterations/{publishedName}/url/nostore	Classify an image url without saving the result.
POST	/{projectId}/classify/iterations/{publishedName}/image/nostore	Classify an image without saving the result.
POST	/{projectId}/detect/iterations/{publishedName}/url	Detect objects in an image url and saves the result.
POST	/{projectId}/detect/iterations/{publishedName}/image	Detect objects in an image and saves the result.
POST	/{projectId}/detect/iterations/{publishedName}/url/nostore	Detect objects in an image url without saving the result.
POST	/{projectId}/detect/iterations/{publishedName}/image/nostore	Detect objects in an image without saving the result.

Common Questions

Match user requests to endpoints in references/api-spec.lap. Key patterns:

"Create a url?" -> POST /{projectId}/classify/iterations/{publishedName}/url
"Create a image?" -> POST /{projectId}/classify/iterations/{publishedName}/image
"Create a nostore?" -> POST /{projectId}/classify/iterations/{publishedName}/url/nostore
"Create a nostore?" -> POST /{projectId}/classify/iterations/{publishedName}/image/nostore
"Create a url?" -> POST /{projectId}/detect/iterations/{publishedName}/url
"Create a image?" -> POST /{projectId}/detect/iterations/{publishedName}/image
"Create a nostore?" -> POST /{projectId}/detect/iterations/{publishedName}/url/nostore
"Create a nostore?" -> POST /{projectId}/detect/iterations/{publishedName}/image/nostore
"How to authenticate?" -> See Auth section

Response Tips

Check response schemas in references/api-spec.lap for field details
Create/update endpoints typically return the created/updated object

References

Full spec: See references/api-spec.lap for complete endpoint details, parameter tables, and response schemas

Generated from the official API spec by LAP

---name: custom-vision-prediction-clientdescription: Custom Vision Prediction Client API skill. Use when working with Custom Vision Prediction Client for {projectId}. Covers 8 endpoints.--- # Custom Vision Prediction Client API version: 3.0 ## Auth ApiKey Prediction-Key in header ## Base URL https://southcentralus.api.cognitive.microsoft.com/customvision/v3.0/prediction ## Setup 1. Set your API key in the appropriate header 3. POST /{projectId}/classify/iterations/{publishedName}/url -- create first url ## Endpoints 8 endpoints across 1 groups. See references/api-spec.lap for full details. ### {projectId} | Method | Path | Description | |--------|------|-------------| | POST | /{projectId}/classify/iterations/{publishedName}/url | Classify an image url and saves the result. | | POST | /{projectId}/classify/iterations/{publishedName}/image | Classify an image and saves the result. | | POST | /{projectId}/classify/iterations/{publishedName}/url/nostore | Classify an image url without saving the result. | | POST | /{projectId}/classify/iterations/{publishedName}/image/nostore | Classify an image without saving the result. | | POST | /{projectId}/detect/iterations/{publishedName}/url | Detect objects in an image url and saves the result. | | POST | /{projectId}/detect/iterations/{publishedName}/image | Detect objects in an image and saves the result. | | POST | /{projectId}/detect/iterations/{publishedName}/url/nostore | Detect objects in an image url without saving the result. | | POST | /{projectId}/detect/iterations/{publishedName}/image/nostore | Detect objects in an image without saving the result. | ## Common Questions Match user requests to endpoints in references/api-spec.lap. Key patterns: - "Create a url?" -> POST /{projectId}/classify/iterations/{publishedName}/url - "Create a image?" -> POST /{projectId}/classify/iterations/{publishedName}/image - "Create a nostore?" -> POST /{projectId}/classify/iterations/{publishedName}/url/nostore - "Create a nostore?" -> POST /{projectId}/classify/iterations/{publishedName}/image/nostore - "Create a url?" -> POST /{projectId}/detect/iterations/{publishedName}/url - "Create a image?" -> POST /{projectId}/detect/iterations/{publishedName}/image - "Create a nostore?" -> POST /{projectId}/detect/iterations/{publishedName}/url/nostore - "Create a nostore?" -> POST /{projectId}/detect/iterations/{publishedName}/image/nostore - "How to authenticate?" -> See Auth section ## Response Tips - Check response schemas in references/api-spec.lap for field details - Create/update endpoints typically return the created/updated object ## References - Full spec: See references/api-spec.lap for complete endpoint details, parameter tables, and response schemas > Generated from the official API spec by [LAP](https://lap.sh)

Frequently asked questions

Custom Vision Prediction Client

File contents

Custom Vision Prediction Client

Auth

Base URL

Setup

Endpoints

{projectId}

Common Questions

Response Tips

References

Related skills

Frequently asked questions

How do I install the Custom Vision Prediction Client skill?

What does the Custom Vision Prediction Client skill do?

Is Custom Vision Prediction Client safe to use?

Which AI agents work with Custom Vision Prediction Client?

Is Custom Vision Prediction Client free to use?

Who published Custom Vision Prediction Client?