artifact-contract

Community

Normalize and govern all AgentHub outputs.

Authorzxc1a1a1
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill standardizes how AgentHub defines, validates, versions, previews, and securely stores artifacts so multi-agent outputs remain consistent, traceable, and safe across the platform.

Core Features & Use Cases

  • Artifact standard contract: Defines the Core Artifact model, required identity links (conversation/message/run), and the content vs contentRef boundary.
  • ArtifactDraft → Core normalization rules: Enforces that child agents emit ArtifactDraft while Orchestrator/ArtifactRegistry produces Core Artifacts with generated fields.
  • Artifact type registry and preview mapping: Provides a controlled mapping from artifact.type to previewType (and ultimately frontend runtime toolName) with safe defaults.
  • Schema, lifecycle, and versioning governance: Specifies validation expectations, lifecycle states, and how versions/supersession must be handled without breaking history.
  • Security and review checklist: Prevents leakage of secrets and unsafe references, and provides a systematic review rubric for changes.

Quick Start

Use the artifact-contract skill to define or review the platform rules for new artifact outputs so your agents produce normalized, previewable, and secure artifacts.

Dependency Matrix

Required Modules

None required

Components

references

💻 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: artifact-contract
Download link: https://github.com/zxc1a1a1/Multi_Agent-AgentHub/archive/main.zip#artifact-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.