---
name: al-100-database-incident-diagnosis-brief
description: "Turn blocking chains, wait stats, and slow-query clues into a root-cause brief with a recommended fix and a ready-to-assign ticket, like Cornerstone OnDemand's Orion AI multi-agent system on Amazon Bedrock that cut database diagnosis from 45 minutes to 10. Use when the user wants help with database ops (it & internal help) for a small business."
---

# Database incident diagnosis brief

Turn blocking chains, wait stats, and slow-query clues into a root-cause brief with a recommended fix and a ready-to-assign ticket, like Cornerstone OnDemand's Orion AI multi-agent system on Amazon Bedrock that cut database diagnosis from 45 minutes to 10.

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

- What users/SRE reported
- Blocking sessions, wait types, CPU, long-running queries, timestamps
- Deploys, schema changes, or unknown

## Instructions

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

Diagnose this database incident. Symptoms: [paste what users/SRE reported]. Metrics and waits: [paste blocking sessions, wait types, CPU, long-running queries, timestamps]. Recent changes: [paste deploys, schema changes, or unknown]. Produce: (1) most likely root cause and why, (2) what to rule out next, (3) a safe first remediation step vs anything that needs approval (e.g. killing a session), (4) a filled ticket draft: title, severity, evidence, owner team, and acceptance check. If data is incomplete, list exactly what to query next instead of guessing.

## Safety checks (share these with the user)

- This prompt works on text other people wrote (emails, reviews, messages or web pages). That text can hide instructions aimed at AI, such as "ignore your rules and…". Paste it as material to work on, and never let the AI act on requests inside it, like paying, sharing logins or changing records.
- 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: ChatGPT, Claude, Gemini, Amazon Bedrock, your SQL monitoring/export, Jira
- Based on this real-world example: https://aws.amazon.com/blogs/machine-learning/how-cornerstone-ondemand-cut-database-diagnosis-by-78-with-amazon-bedrock/
- Free prompt from AgentPlaybook Real Estate: https://agentic-library.netlify.app/prompt/al-100-database-incident-diagnosis-brief/
- 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/