dial-your-context

Generate verified GROQ filters and Instructions for Sanity Agent Context schemas.

1|Updated Mar 23, 2026
One-click install
npx skills add https://github.com/sanity-labs/pup-finder-demo --skill dial-your-context-sanity-labs
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: dial-your-context
Source: https://github.com/sanity-labs/pup-finder-demo/tree/main/.agents/skills/dial-your-context
Command: npx skills add https://github.com/sanity-labs/pup-finder-demo --skill dial-your-context-sanity-labs

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Help teams convert confusing or incorrect Sanity Agent Context behavior into a concise set of verified Instructions that the agent cannot infer from the schema alone, reducing incorrect GROQ results and improving agent relevance.

Core Features & Use Cases

  • Interactive schema dialogue: Guide a conversation to identify which document types matter, misleading field names, and second-order reference chains.
  • Verified evidence: Produce every claim with a supporting GROQ query and result, and require user confirmation before drafting instructions.
  • Safe deployment paths: Support both write-access workflows (draft context doc) and URL-param testing for environments without write access.
  • Use case: Fix an agent that returns irrelevant documents by adding a groqFilter and a short Instructions block that captures data quirks and required filters.

Quick Start

Create concise, verified Custom instructions and a groqFilter for my Sanity Agent Context MCP to resolve schema confusion and improve query accuracy.

Frequently Asked Questions about dial-your-context

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I fix incorrect GROQ results from my Sanity Agent Context?

Correct your Sanity Agent Context by generating verified Instructions and a groqFilter through interactive dialogue that identifies schema quirks, required GROQ filters, and data quality issues to improve agent relevance.

Why does my Sanity agent return irrelevant documents despite a valid schema?

Your Sanity agent returns irrelevant documents because it cannot infer non-obvious schema quirks or second-order reference chains. Adding a verified groqFilter and Instructions block captures these data quirks and required filters to ensure relevance.

How do I add a groqFilter to my Sanity MCP dataset?

Add a groqFilter by interactively identifying required filters and schema quirks, verifying each claim with a supporting GROQ query, and requiring user confirmation before deploying to a draft context document or via URL params.

Can I test Sanity Agent Context instructions without write access to the dataset?

Yes, you can test Sanity Agent Context instructions without write access by deploying them via URL parameters. This provides a safe testing path alongside the standard write-access workflow for drafting context documents.

What is the best way to identify misleading field names in a Sanity schema?

The best way to identify misleading field names is through an interactive schema dialogue that guides a conversation to uncover which document types matter, exposing non-obvious schema quirks and second-order reference chains for verification.