Skip to main content
Skills are the building blocks of the VLM Run platform. A skill is a modular, reusable capability that tells Orion exactly what to extract from a visual input and how to structure the output. Once created, a skill can be referenced from any endpoint (images, PDFs, video, audio, or agent workflows), producing consistent, schema-validated results every time.
Think of skills as “visual functions”: define the input type, describe the task, set the output schema, and call it from anywhere.

​
Skills Lifecycle

Create

Define a new skill through a chat conversation or by uploading a skill package. Specify the task description, output schema, and test it against sample files.

Edit

Refine the skill’s prompt, schema, or metadata from the platform. Publish new versions without breaking existing integrations. Callers on a pinned version continue working unchanged.

Use

Reference the skill in chat, the REST API, or the SDK. Combine multiple skills in a single request for complex extraction pipelines.
Skills table view
The skills table lists every skill in your workspace. Filter by name, domain, or version, and click any row to open the detail editor. From here you can see usage stats, version history, and the current schema.

​
Configuring Skills

Skill detail and editor view
The detail view shows the full skill definition: task description, JSON schema, sample inputs and outputs, and version history. Edit any field and publish a new version directly from this page.

​
Best Practices

​
Dive deeper

Create a Skill

Step-by-step guide to creating a skill on the platform.

Edit a Skill

How to update prompts, schemas, and publish new versions.

Use a Skill

Reference skills in chat, API calls, and agent workflows.

Skill Specification

The full specification format: skill.md, vlmrun.yaml, and schema.json.

Version Pinning

Control which version consumers use in production.

Skills via API

Create and manage skills programmatically with the REST API.