1. Discover test infrastructure by reading project configuration files.
2. Run all tests to identify failing test files.
3. Verify single test execution to ensure agents can run tests in isolation.
4. Launch developer agents in parallel, one per failing test file, with specific instructions.
5. Verify all fixes by running the full test suite again.
6. Iterate if needed, launching new agents for remaining failures.
7. Ensure all tests pass and test coverage is maintained.
SynapticSkills