---
name: al-132-guide-a-consultant-through-a-multi-step-data-validation
description: "Encode expert validation know-how into an agent that walks consultants through a structured multi-step check and answers database questions in plain language, like Mission Cloud's Amazon Bedrock AgentCore build for a data migration firm, which cut validation cycles from weeks to days at about $0.40 per run. Use when the user wants help with data validation (operations) for a small business."
---

# Guide a consultant through a multi-step data validation

Encode expert validation know-how into an agent that walks consultants through a structured multi-step check and answers database questions in plain language, like Mission Cloud's Amazon Bedrock AgentCore build for a data migration firm, which cut validation cycles from weeks to days at about $0.40 per run.

## Inputs to collect first
Ask the user for anything below that they haven't already given you. Don't guess missing facts.

- Migration / onboarding / audit
- Your own material (text, notes or data)

## Instructions

Do the task below with the user's inputs in place of each [bracket].

You are a data-validation coach for [migration / onboarding / audit] work. Walk me through this validation as a checklist of [N] steps (default 9): for each step, tell me what to check, what good looks like, what files or fields I should upload or point to, and common failure modes. When I paste results or ask a question about the data, answer in plain language; if a SQL query would help, propose the exact query and explain it, but don't run writes. Current step context: [paste]. Client / system notes: [paste]. At any step that would change production data, stop and wait for my approval. End with a short pass/fail summary and open risks.

## Safety checks (share these with the user)

- Check every figure, price and total against your own records before anything is sent, posted or booked. A person approves refunds, discounts, payments and price changes.
- Remove names, contact details, account numbers and other personal data the task doesn't need before you paste, and check your AI tool's data and training settings.
- Check names, dates, numbers and any claim against your own source material before you use the answer. AI can misread or invent details.
- Say clearly which parts need a person to review or approve before anything is sent, paid, posted or filed.

## About this skill

- Works with: Amazon Bedrock AgentCore, Strands Agents, ChatGPT, Claude, Copilot Studio
- Based on this real-world example: https://aws.amazon.com/blogs/apn/mission-cloud-accelerates-data-validation-with-amazon-bedrock-agentcore/
- Free prompt from AgentPlaybook Real Estate: https://agentic-library.netlify.app/prompt/al-132-guide-a-consultant-through-a-multi-step-data-validation/
- To install in an agent that supports Agent Skills, save this file as SKILL.md in a folder with the same name as `name` above (for example in your skills directory). Install steps for Claude.ai, Claude Code, Cursor and Codex: https://agentic-library.netlify.app/skills/