ralph-loop-light

Repair small code defects with a test-first fix loop validated by ruff and pytest.

1|Updated Jan 13, 2026
One-click install
npx skills add https://github.com/jongensutrecht/demo-ai-stack --skill ralph-loop-light
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ralph-loop-light
Source: https://github.com/jongensutrecht/demo-ai-stack/tree/main/.claude/skills/quick-fix
Command: npx skills add https://github.com/jongensutrecht/demo-ai-stack --skill ralph-loop-light

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill helps you repair small, well-scoped code issues quickly while keeping tests mandatory and the workflow lightweight.

Core Features & Use Cases

  • Test-first micro fixes: Handles small bugs, UI glitches, config changes, and dependency updates without the overhead of a full planning process.
  • Built-in validation loop: Enforces a short fix cycle that starts with a failing test, applies the change, and verifies the result with full test runs.
  • Scope safeguards: Stops the quick path when the change grows beyond the intended size or fails repeatedly, so larger work can move to a fuller process.

Quick Start

Ask the skill to fix a small bug, write the missing test, and validate the repair with the built-in workflow.

Frequently Asked Questions about ralph-loop-light

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

FAQPage Schema
How do I fix small pytest failures with a test-first workflow?

To fix small pytest failures with a test-first workflow, you need a constrained loop that starts with a failing test, applies the code change, and verifies the result with a passing test.

What is a test-first fix loop for minor bugs?

A test-first fix loop for minor bugs is a lightweight workflow that enforces writing a failing test before applying a small code repair, then validating the fix with ruff and pytest.

Can I use a quick fix loop for UI regressions and dependency updates?

Yes, you can use a quick fix loop for UI regressions, configuration tweaks, and dependency updates, provided the change scope remains very small and lightweight.

What is the best way to validate a quick code fix with ruff and pytest?

The best way to validate a quick code fix with ruff and pytest is to enforce a short cycle that requires a clean git state and a failing test before the fix, then a passing test after.

When should I avoid using a test-first quick fix workflow?

You should avoid using a test-first quick fix workflow when the change scope grows beyond a very small size or fails repeatedly, stopping the quick path so larger work uses a fuller process.

Does the test-first fix loop stop after a certain number of iterations?

Yes, the test-first fix loop stops after a three-iteration limit to prevent endless cycles, ensuring bug repair stays constrained and moves to a fuller process if it fails repeatedly.