Test Fixing

When your test suite breaks after a refactor or code change, this gives Claude a methodical framework to fix everything systematically. It runs the full suite first, groups failures by error type and root cause (ImportErrors, AttributeErrors, etc.), then tackles them in priority order rather than randomly. The workflow is smart: fix infrastructure issues like imports before logic bugs, verify each group passes before moving on, use focused test runs to avoid waiting for the full suite every time. It's basically a checklist that prevents the common mistake of fixing tests randomly and creating whack-a-mole situations where fixing one thing breaks another.

skills.sh installs: 661
GitHub stars: 43.1K
last updated: Jul 14, 2026

View on GitHub

Install

$ npx -y skills add sickn33/antigravity-awesome-skills --skill test-fixing --agent claude-code

Installs into .claude/skills of the current project.

Files

Test Fixing

Systematically identify and fix all failing tests using smart grouping strategies.

When to Use

Explicitly asks to fix tests ("fix these tests", "make tests pass")
Reports test failures ("tests are failing", "test suite is broken")
Completes implementation and wants tests passing
Mentions CI/CD failures due to tests

Systematic Approach

1. Initial Test Run

Read project instructions, dependency manifests and CI configuration to identify the existing test command. Use make test only if that target exists and is the project contract. Inspect fixture/service requirements before running it; do not invoke production operations to obtain a baseline. Preserve pre-existing changes.

Analyze output for: