agent-creator_skill

Overview

This skill automates the design and creation of AI Agents for conversational, task-driven, research, and multi-agent workflows. It guides you through defining identity, writing system prompts, planning tools and memory, orchestrating workflows, and adding safety and testing. The output is a ready-to-run agent configuration and best-practice templates.

How this skill works

The skill inspects your requirements and walks through a phased workflow: requirements, role design, tool planning, prompt engineering, safety design, and testing. It generates structured artifacts—identity template, system prompt scaffold, tool schemas, workflow patterns, and verification checklists—so you can instantiate agents quickly. It also recommends architecture patterns (ReAct, Plan-and-Execute, Router, Reflection) based on task needs.

When to use it

• You need to create a new AI Agent (assistant, automation, or researcher).
• You must design a clear System Prompt and role identity before development.
• You want to define or standardize tool schemas and tool-calling logic.
• You are planning multi-agent coordination or role-based collaboration.
• You need a repeatable testing and safety checklist for deployment.

Best practices

• Start with a crisp problem statement and measurable success criteria.
• Define identity with explicit capabilities and hard boundaries to prevent scope creep.
• Structure the System Prompt: Identity, Context, Instructions, Constraints, Output Format, Examples.
• Design tools with formal schemas and decision logic for when to call them.
• Implement input validation, output filtering, and manual-intervention triggers for safety.
• Test across normal, edge, adversarial, and load scenarios before production.

Example use cases

• Customer support assistant with tool access to ticketing and knowledge base.
• Automated data-processing agent that executes ETL tasks and reports results.
• Research agent that collects, synthesizes, and drafts a literature summary.
• Multi-agent simulation where planner, executor, and auditor roles coordinate a complex workflow.
• Code-review assistant that enforces security and performance guidelines using few-shot examples.