agent:design
Design AI Agent
The main orchestrator skill for designing AI agent systems. Gathers requirements, launches parallel research sub-agents to investigate each area (prompts, tools, memory, workflows, RAG, multi-agent, context engineering), and compiles findings into a unified design document.
Based on "Patterns for Building AI Agents" and "Principles of Building AI Agents" (Bhagwat & Gienow, 2025).
When to use
Use this skill when the user needs to:
- Design a new AI agent or multi-agent system from scratch
- Create a comprehensive design covering all aspects of an agent system
- Get a structured design document for implementation planning
For focused work on a single area, use the standalone skills directly:
agent:prompt, agent:tools, agent:memory, agent:workflow, agent:rag, agent:multi, agent:context
Instructions
Step 1: Understand the Domain
More from ikatsuba/skills
spec:design
Technical Design - generates architecture diagrams, interfaces, and data flow based on requirements and chosen research solutions. Use when designing how a feature will be built.
18git:amend
Amend Commit - modifies the last commit with staged changes or new message
15spec:tasks
Task Breakdown - generates an implementation plan with tracked tasks based on requirements and design documents. Use when breaking down a design into actionable work items.
14spec:requirements
Requirements Analysis - gathers requirements through structured questions and produces a requirements document with testable acceptance criteria. Use when starting a new feature spec or documenting requirements.
14git:commit
Smart Commit - stages all changes and creates a conventional commit
13spec:do-next
Execute Next Task - runs the next pending task from the tasks document
9