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.

Install to Claude Code

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