write-quality-contract

Community

Define robust guardrails for your agent OS.

AuthorSujinHwang27
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Defines a non-negotiable rule, verification checks, anti-patterns, banned vocabulary, and tone to govern an agent OS, ensuring consistent behavior, safer outputs, and auditable governance across all skills.

Core Features & Use Cases

  • Non-negotiable Rule: A single, testable rule that the system must never violate, with a clear verification path.
  • Verification & Guardrails: A structured set of checks (source verification, freshness, specificity, audience alignment) to ensure outputs meet the defined quality standards.
  • Anti-Patterns & Tone: A catalog of common failure patterns with concrete fixes and a defined voice to enforce consistent style and safety.
  • Empty Context & Data Trust: Guidelines for handling missing context and external data sources with explicit trust and verification rules.

Quick Start

Define the domain-input/quality-contract.md with the full quality contract to bootstrap OS governance.

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: write-quality-contract
Download link: https://github.com/SujinHwang27/agent-os-lab/archive/main.zip#write-quality-contract

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.