- Home
- Skills
- Prompt & Skill Engineering
- loop enginering
Works with the AI Agents you already use
loop enginering
Automated database migrations, security audits, flaky test detection, and PR preparation for professional dev teams.
$3
loop enginering
Example session with this skill installed
Add a new column 'user_bio' to the 'users' table. It should be nullable for now. Use Flyway.
- Read your context and instructions
- Compiled the loop enginering
I have scanned the project and identified the Flyway migration path at src/main/resources/db/migration. The latest migration is V12__add_index_on_email.sql.
DB Migration: Add user_bio to users
-- V13__add_user_bio_to_users.sql
-- Migration: Add nullable user_bio column to users table
-- Risk: Low (Nullable column addition in PostgreSQL 11+)
ALTER TABLE users ADD COLUMN user_bio TEXT;
-- Rollback:
-- ALTER TABLE users DROP COLUMN user_bio;
I checked the UserEntity.java and updated the fields to ensure compatibility with ddl-auto=validate.
Next steps
- Review the generated SQL in
src/main/resources/db/migration/V13__add_user_bio_to_users.sql. - Run
./gradlew testor use theverifyskill to ensure the JPA entity mapping matches the new schema. - Apply the migration to your local database using
flyway migrate.
Connects securely to your tools. The creator never sees your data.
About this skill
Ship high-quality database changes and maintain repository health with this suite of six essential engineering skills. This package automates the repetitive, error-prone tasks that delay PRs, from writing safe database migrations to hunting down flaky tests.
What it does
- Database Migrations Writes Flyway, Liquibase, or Prisma scripts following existing naming conventions and versioning.
- Dependency Auditing Scans for security vulnerabilities and outdated versions across npm, pnpm, Gradle, Maven, and Python.
- Automated Debugging Loops Iteratively diagnoses, fixes, and verifies code until specific goals like "zero type errors" are met.
- PR Preparation Performs self-reviews for debug code, runs verification suites, and drafts PR descriptions.
- Test Health Monitoring Detects flaky, slow, or skipped tests by running suites multiple times and analyzing XML/JSON reports.
- Project Verification Detects build tools and runs relevant lints, type checks, and tests to ensure zero regressions.
How it works
- Context Discovery The agent identifies your build tools, migration paths, and lockfiles.
- Analysis It executes specialized commands like
pnpm auditorgradlew checkto gather status. - Execution For migrations or fixes, it applies changes to specific files while adhering to local
rules/*.md. - Validation It runs verification loops, ensuring fixes work and don't break existing tests.
Frameworks & tools
Supports PostgreSQL, Flyway, Liquibase, Alembic, Prisma, Spring Boot (Gradle/Maven), Node.js (npm/pnpm/yarn/Vitest/Jest), Python (uv/ruff/pytest), and GitHub PR workflows.
Why this beats prompting it yourself
Generic prompts often miss safe migration patterns like CREATE INDEX CONCURRENTLY or fail to detect intermittent flaky tests. These skills encode specific engineering best practices for dependency prioritization and non-breaking database changes that LLMs usually overlook.
Use cases
- Generating a safe migration script to add a NOT NULL column to a high-traffic table.
- Running an overnight loop to resolve 50+ lingering TypeScript errors.
- Auditing a legacy project for critical security vulnerabilities before a release.
- Cleaning up a PR by removing debug logs and verifying all tests pass.
Known limitations
Does not execute migrations against live databases. Requires manual setup of Docker/Testcontainers if tests depend on them. Major framework upgrades require manual oversight.
Does not execute DB migrations. Requires existing test/audit plugins for Gradle/Maven. Major version upgrades require manual approval. Docker-dependent tests may fail if no daemon is available.
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 days ago
Requires