Shape Your Agent

A conversational workflow for writing system prompts for AI agents that use Sanity's Agent Context MCP. This is specifically for teams who control the system prompt and need to define agent personality, tone, refusal behaviors, and communication boundaries. The skill walks you through use case definition, behavior rules, and boundary setting with the core philosophy that less is more. Every rule needs a concrete trigger scenario or it gets cut. It's opinionated about separation of concerns: the system prompt handles behavior and personality (200-400 words), while the Instructions field and MCP handle all the data schema and query stuff. Includes an example e-commerce support agent and a testing checklist. Skip this entirely if you don't have system prompt access.

skills.sh installs: 381
GitHub stars: 4
last updated: Jun 3, 2026

View on GitHub

Install

$ npx -y skills add sanity-io/agent-context --skill shape-your-agent --agent claude-code

Installs into .claude/skills of the current project.

Files

Shape Your Agent

An optional, conversational workflow for creating a system prompt for an AI agent that uses the Sanity Context MCP server. This is for users who control the system prompt in their agent setup.

Don't have access to the system prompt? Skip this skill entirely. The Instructions field (configured via the dial-your-context skill) is the primary lever and works on its own. A minimal system prompt like "You are a helpful agent." combined with good Instructions field content scores 80%+ in our evaluations.

Before You Start

What the system prompt is for

The system prompt defines agent behavior — who it is, how it talks, what it refuses to do. Think of it as the agent's personality and policy manual.