More screenshots
Works with the AI Agents you already use
Claude Code
Cursor
Codex CLI
Muse
Dots+20 moreClaude CodeCursorCodex CLIMuseDots
Manus
Grok
Grok Bot+17 agents🗄️ SQL Migration Safety Doctor
The SQL Migration Safety Doctor is a specialized security and stability auditor for database migrations.
$12
🗄️ SQL Migration Safety Doctor
Example session with this skill installed
Check the new migration in migrations/20231024_add_user_index.sql for any safety issues.
- Read your context and instructions
- Compiled the sql migration safety
⚠️ High Risk: Non-Concurrent Index
- File:
migrations/20231024_add_user_index.sql - Line: 4
- Evidence:
CREATE INDEX idx_user_email ON users(email); - Impact: Will lock the
userstable for writes. - Remediation: Use
CREATE INDEX CONCURRENTLYin a separate transaction.
Connects securely to your tools. The creator never sees your data.
About this skill
What it does
The SQL Migration Safety Doctor is a specialized security and stability auditor for database migrations. It scans SQL files for destructive operations, heavy lock risks, and data integrity gaps before they ever hit your production environment. By identifying risky patterns like WHERE-less updates, lossy column changes, and non-concurrent index creation, it acts as a gatekeeper for your data layer.
Why use this skill
Prompting a generic AI for SQL reviews often misses subtle database-specific locking behaviors or platform-specific risks (like Postgres table locks). This skill uses a dedicated Python-based heuristic scanner combined with a rigorous audit checklist to provide evidence-based findings. It categorizes risks by severity—Critical to Info—and provides battle-tested remediation snippets to fix issues immediately.
Supported tools and workflows
- SQL Dialects: Optimized for Postgres, MySQL, and standard SQL patterns.
- Framework Agnostic: Works with migrations from Rails, Django, Prisma, Flyway, Liquibase, or raw SQL files.
- DevOps Integration: Ideal for pre-commit hooks or CI/CD pipeline simulations.
Output format
You receive a structured report detailing confirmed findings with file/line citations, a manual review checklist for complex logic, and specific SQL snippets to remediate the identified risks safely.
,sample_input:How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 4 months ago