Skip to main content

​
Overview

Integrate skills with Upsonic’s safety engine to validate content against configured policies before it reaches the agent.

​
Usage

from upsonic import Agent
from upsonic.skills import Skills, LocalSkills

skills = Skills(
    loaders=[LocalSkills("./my-skills")],
    policy=my_safety_policy,
)

agent = Agent(
    model="anthropic/claude-sonnet-4-6",
    name="Safe Agent",
    role="Content Reviewer",
    goal="Review content safely",
    skills=skills,
)

result = agent.print_do("Process this content following safety guidelines.")

​
Multiple Policies

Pass a list of policies — all are checked: 
from upsonic.skills import Skills, LocalSkills

skills = Skills(
    loaders=[LocalSkills("./my-skills")],
    policy=[content_policy, compliance_policy, privacy_policy],
)

​
How It Works

When an agent accesses skill content (instructions or references), the content is checked against all configured policies:
  1. Each policy’s check() method receives a PolicyInput with the content
  2. If any policy returns a result with confidence > 0.7, the content is blocked
  3. The agent receives an error message instead of the skill content
{"error": "Content blocked by policy: <reason>", "skill_name": "my-skill"}
Script execution results are not policy-checked — only skill instructions and reference document content pass through the safety engine.

​
Parameters

ParameterTypeDefaultDescription
policypolicy or ListNoneSafety policy or list of policies