Fix Tests

This is a test maintenance orchestrator that spins up parallel agents to fix failing tests after you've changed business logic or refactored. It discovers your test infrastructure, identifies all failures, then launches one developer agent per broken test file with instructions to iterate until passing. The workflow is smart about complexity: simple single-file changes you handle yourself, but anything more complex gets delegated to agents who work in parallel. It includes a verification step at the end where you run the full suite again and launch new agents for any remaining failures. The constraint to fix tests rather than business logic is the right default, though it allows agents to fix obvious bugs. If you regularly break dozens of tests during refactors, this could save hours of tedious fix-and-verify cycles.

skills.sh installs: 1.2K
GitHub stars: 1.8K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add neolabhq/context-engineering-kit --skill fix-tests --agent claude-code

Installs into .claude/skills of the current project.

Files

Fix Tests

User Arguments

User can provide to focus on specific tests or modules:

$ARGUMENTS

If nothing is provided, focus on all tests.

Context

After business logic changes, refactoring, or dependency updates, tests may fail because they no longer match the current behavior or implementation. This command orchestrates automated fixing of all failing tests using specialized agents.

Goal

Fix all failing tests to match current business logic and implementation.

Important Constraints

Focus on fixing tests - avoid changing business logic unless absolutely necessary
Preserve test intent - ensure tests still validate the expected behavior
"Analyse complexity of changes" -
- if there 2 or more changed files, or one file with complex logic, then Do not write tests yourself - only orchestrate agents!
- if there is only one changed file, and it's a simple change, then you can write tests yourself.