agno-guardrails
CommunitySecure your AI with input/output checks.
Authorajshedivy
Version1.0.0
Installs0
System Documentation
What problem does it solve?
This Skill enhances the safety and reliability of AI agents by implementing robust input and output validation, preventing harmful or unintended interactions.
Core Features & Use Cases
- Input Validation: Use
pre_hooksto check user inputs for spam, policy violations, or PII before agent processing. - Output Validation: Employ
post_hooksto validate agent responses for PII, format correctness, or adherence to content policies. - Built-in Checks: Leverage pre-built guardrails for PII and prompt injection detection.
- Use Case: Protect your customer-facing chatbot by ensuring user inputs don't contain offensive language and that the agent's responses do not accidentally reveal sensitive customer data.
Quick Start
Add a guardrail to your agent to block messages containing more than 10 exclamation marks.
Dependency Matrix
Required Modules
agno[openai]
Components
scriptsreferences
💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: agno-guardrails Download link: https://github.com/ajshedivy/agno-cookbook/archive/main.zip#agno-guardrails Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.