Skip to main content
POST
/
v1
/
skills
/
create
!pip install vlmrun

from vlmrun.client import VLMRun

client = VLMRun(base_url="https://agent.vlm.run/v1", api_key="<VLMRUN_API_KEY>")

# Create a skill from a prompt
skill = client.skills.create(
    prompt="Extract invoice_id, date, and total_amount from invoices.",
    json_schema={
        "type": "object",
        "properties": {
            "invoice_id": {"type": "string"},
            "invoice_date": {"type": "string", "format": "date"},
            "total_amount": {"type": "number"}
        },
        "required": ["invoice_id", "invoice_date", "total_amount"]
    }
)
print(f"Created skill: {skill.id} ({skill.name})")

# Create a skill from a pre-uploaded file
skill = client.skills.create(
    name="invoice-extraction",
    description="Extract structured data from invoices",
    file_id="<file-id>"  # Uploaded skill zip containing SKILL.md
)

# Create a skill from a chat session
skill = client.skills.create(
    session_id="<session-id>"
)

{
  "id": "<string>",
  "name": "<string>",
  "description": "<string>",
  "created_at": "2023-11-07T05:31:56Z",
  "updated_at": "2023-11-07T05:31:56Z",
  "status": "completed"
}
!pip install vlmrun

from vlmrun.client import VLMRun

client = VLMRun(base_url="https://agent.vlm.run/v1", api_key="<VLMRUN_API_KEY>")

# Create a skill from a prompt
skill = client.skills.create(
    prompt="Extract invoice_id, date, and total_amount from invoices.",
    json_schema={
        "type": "object",
        "properties": {
            "invoice_id": {"type": "string"},
            "invoice_date": {"type": "string", "format": "date"},
            "total_amount": {"type": "number"}
        },
        "required": ["invoice_id", "invoice_date", "total_amount"]
    }
)
print(f"Created skill: {skill.id} ({skill.name})")

# Create a skill from a pre-uploaded file
skill = client.skills.create(
    name="invoice-extraction",
    description="Extract structured data from invoices",
    file_id="<file-id>"  # Uploaded skill zip containing SKILL.md
)

# Create a skill from a chat session
skill = client.skills.create(
    session_id="<session-id>"
)

Authorizations

​
Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

application/json

Request to create a skill.

Three creation modes (provide exactly one): A. file_id: Create from a pre-built skill zip uploaded via POST /v1/files. B. prompt (+ optional json_schema): Auto-generate SKILL.md and schema.json. C. session_id: Retrieve chat history and auto-generate SKILL.md from messages.

For mode A (file_id), name and description are required. For modes B (prompt) and C (session_id), name and description are optional — if omitted, they are auto-generated by the LLM from the content.

​
name
string | null

Name of the skill (required for file_id, auto-generated for prompt/session_id)

Maximum string length: 255
​
description
string | null

Description of the skill (required for file_id, auto-generated for prompt/session_id)

​
file_id
string | null

File ID from file upload API (the uploaded skill zip)

​
prompt
string | null

Prompt text that becomes the SKILL.md body (auto-generates skill zip)

​
json_schema
Json Schema · object

JSON schema that becomes schema.json in the skill zip

​
session_id
string | null

Chat session ID to retrieve chat history as the prompt

​
is_public
boolean
default:false

Whether the skill is publicly accessible

Response

Successful Response

Response for skill creation.

​
id
string
required

ID of the created skill

​
name
string
required

Name of the skill (may differ from request if LLM-generated)

​
description
string
required

Description of the skill (may differ from request if LLM-generated)

​
created_at
string<date-time>
required

Date and time when the skill was created

​
updated_at
string<date-time>
required

Date and time when the skill was updated

​
status
string
default:completed

Status of the skill creation