sj-agent-dev
CommunityBuild reliable, production-ready business AI agents.
Software Engineering#multi-agent#orchestration#ai-agent#agent-architecture#business-automation#agent-guardrails#agent-observability
Authors0613
Version1.0.0
Installs0
System Documentation
What problem does it solve?
Most business AI agent projects fail because they prioritize model intelligence over structural reliability, leading to fragile systems that break in real-world workflows with no guardrails, poor observability, or unsafe tool access.
Core Features & Use Cases
- 10-Axis Design Framework: Covers runtime loops, orchestration, role separation, tool hierarchy, context management, guardrails, observability, memory layers, evaluation, and graph topology for end-to-end agent architecture.
- Production-Grade Implementation Guidance: Includes pattern catalogs, tool risk tiering standards, and pre-deployment checklists to ensure agents meet operational safety and reliability requirements.
- Use Cases: Design new multi-agent business systems, optimize existing agent performance, build domain-specific automation (e.g., customer support, order processing), strengthen operational safety, and reduce context waste in agent workflows.
Quick Start
Use the sj-agent-dev skill to design an order processing agent with parallel inventory and payment specialists, approval gates for refunds, and structured logging for all actions.
Dependency Matrix
Required Modules
None requiredComponents
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: sj-agent-dev Download link: https://github.com/s0613/S-skills/archive/main.zip#sj-agent-dev Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 537,000+ vetted skills library on demand.