output_agent

Community

Preflight all human-visible responses.

Authordewitt
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Vetting all human-visible outputs for safety, clarity, and relevance to prevent harmful or confusing responses from being shown.

Core Features & Use Cases

  • Deterministic validation of outputs against safety and quality criteria before delivery.
  • Seamless integration with chat workflows to preflight replies in customer support, knowledge bases, and QA reviews.
  • Provides actionable feedback via FIX: [reason] when a violation is detected, or OK when the reply passes.

Quick Start

Validate a candidate reply by asking the Output Agent to return OK if it passes or FIX with a reason if it does not.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 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: output_agent
Download link: https://github.com/dewitt/swarm/archive/main.zip#output-agent

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 471,000+ vetted skills library on demand.