skills.rest
zxc1a1a1
zxc1a1a1COMMUNITY
Explore all skills by this author →
GitHub

artifact-contract

Defines the standard contract for multi-agent platform artifact outputs.

Updated May 19, 2026
Search Tags:#schema-validation#artifact-contract#artifact-versioning#contentRef-security#preview-mapping#multi-agent-orchestration#type-registry
One-click install
npx skills add https://github.com/zxc1a1a1/Multi_Agent-AgentHub --skill artifact-contract
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: artifact-contract
Source: https://github.com/zxc1a1a1/Multi_Agent-AgentHub/tree/main/.agents/skills/artifact-contract
Command: npx skills add https://github.com/zxc1a1a1/Multi_Agent-AgentHub --skill artifact-contract

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

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.

Frequently Asked Questions about artifact-contract

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I normalize multi-agent outputs into a traceable artifact contract?▼

To normalize multi-agent outputs, define a standard artifact contract enforcing stable identity links like conversationId, messageId, and runId, alongside strict content and contentRef boundaries for traceable artifacts.

What is the difference between ArtifactDraft and Core Artifact in multi-agent orchestration?▼

In multi-agent orchestration, ArtifactDraft is the raw emission produced by child agents, while Core Artifacts are the normalized, versioned outputs generated by the Orchestrator or ArtifactRegistry with assigned lifecycle states and preview mappings.

How do I implement schema validation and artifact versioning for agent-generated outputs?▼

Implement schema validation and artifact versioning by enforcing a controlled type registry for artifact.type enums and applying lifecycle governance rules that handle supersession without breaking historical artifact traceability.

How does preview mapping work for normalized artifacts in a multi-agent platform?▼

Preview mapping translates controlled artifact.type enums into a specific previewType, which the frontend runtime then maps to the appropriate toolName, ensuring safe and consistent rendering defaults across all agent outputs.

How do I prevent secret leakage when persisting agent artifacts with contentRef references?▼

Prevent secret leakage by enforcing strict content vs contentRef boundaries and applying security review guardrails that systematically check for unsafe references and sensitive data before persisting Core Artifacts.

Can I use artifact-contract to govern lifecycle states for agent outputs without breaking history?▼

Yes, artifact-contract governs lifecycle states by specifying validation expectations and versioning rules that handle supersession safely, ensuring historical artifact traceability remains intact without breaking previous records.

Related Skills

Explore More Software Engineering Skills→
OutlineDrivenOutlineDriven
5

to-prd

Synthesize a PRD from conversation context and architectural decisions.

Official
Advanced
mahmoud20138mahmoud20138
10

agentic-storage

Provide persistent MCP-based storage with immutable versioning and audit trails.

Community
Advanced
sgpropertyanalyticssgpropertyanalytics
2

data-standards

Enforce canonical enums and classifications across backend and frontend data displays.

Official
Advanced
yuhle-qugyuhle-qug

rest-api-expert

Design REST APIs with HTTP semantics and OpenAPI documentation.

Community
Intermediate