Skills
.Work. You
Rest

hitl-safety

Official

Implement human-in-the-loop safety controls for actions that require approval.

#human-in-the-loop#guardrails#approval process#safety controls#LLM judging
Authorframerslab
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill provides safety controls for actions that could be destructive, irreversible, expensive, sensitive, or external, ensuring they go through a human or LLM judge approval process before execution.

Core Features & Use Cases

  • HITL Approval Process: Ensures critical actions are reviewed by a human or an LLM judge for safety.
  • Guardrail Checks: Includes post-approval checks for code safety and PII redaction.
  • Use Case: Before sending a mass email or deploying changes to production, this Skill can be used to trigger an approval step that involves a human review or an LLM decision.

Quick Start

Set up the Skill with the appropriate handler (e.g., hitl.cli()) and configure it in your agent settings or code.

Dependency Matrix

Required Modules

None required

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: hitl-safety
Download link: https://github.com/framerslab/agentos-skills/archive/main.zip#hitl-safety

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 620,000+ vetted skills library on demand.