Create Skills - VLM Run

Mode	Source	Description
Skill Folder	Local directory or zip	Upload a pre-built skill folder containing SKILL.md
Prompt	`prompt` (+ optional `json_schema`)	Auto-generate SKILL.md and schema.json from a text prompt
Session	`session_id`	Auto-generate SKILL.md from a chat session’s history

From Skill Folder

The folder must contain a SKILL.md file. The skill name and description are parsed from its YAML frontmatter.

# Upload a local skill folder directly (zips and creates in one step)
vlmrun skills upload ./my-skill

# Override name/description from SKILL.md frontmatter
vlmrun skills upload ./my-skill --name "invoice-extraction" --description "Extract structured data from invoices"

from vlmrun.client import VLMRun
from pathlib import Path

client = VLMRun(api_key="<VLMRUN_API_KEY>")

# One-step: zip, upload, and create a skill from a local directory
skill = client.skills.create_from_directory(
    directory=Path("./my-skill"),
)
print(f"Created skill: {skill.skill_name} (type={skill.type})")

# Override name/description from SKILL.md frontmatter
skill = client.skills.create_from_directory(
    directory=Path("./my-skill"),
    name="invoice-extraction",
    description="Extract structured data from invoices",
)

create_from_directory zips the folder, uploads the archive via the Files API, and creates the skill in one call. It returns an AgentSkill with type="skill_reference". Pass it directly to any endpoint that accepts skills. The folder should follow the skill directory structure:

my-skill/
├── SKILL.md
├── schema.json
├── vlmrun.yaml
└── resources/  (optional)

Use a skill folder for full control of instructions, schema, and execution configuration. Use a prompt to prototype.

From Prompt

# From a text prompt
vlmrun skills create --prompt "Extract invoice_id, date, and total_amount from invoices."

# With a JSON schema file
vlmrun skills create --prompt "Extract invoice data" --schema schema.json

from vlmrun.client import VLMRun

client = VLMRun(api_key="<VLMRUN_API_KEY>")

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})")

The platform generates a SKILL.md from the prompt. It generates schema.json from the provided JSON schema.

From Chat Session

vlmrun skills create --session-id "<session-id>"

from vlmrun.client import VLMRun

client = VLMRun(api_key="<VLMRUN_API_KEY>")

skill = client.skills.create(session_id="<session-id>")
print(f"Created skill: {skill.id} ({skill.name})")

The platform analyzes the conversation. It extracts the task instructions and the expected output format.