Check if a change breaks replay or affects recording determinism. Use when reviewing replay-sensitive edits touching proxy boundary logic, stream or protocol semantics, replay message handling, Go replay/control behavior, thread/fork behavior, weakref or finalizer timing, module interception coverage, or similar control flow. Also use for determinism review, replay safety check, or verifying a diff won't cause replay divergence. Do not use for general code review, trivial cleanup, or ordinary non-replay changes.
Debug Retrace itself when record/replay diverges. Use for replay crashes, bind marker mismatches, checkpoint/SYNC differences, wrong replayed object types, stale extraction suspicion, pytest/DAP replay desyncs, subprocess/fork/thread replay issues, pathpredicate/fd provenance problems, or any bug where Retrace replay fails before the expected user application failure. This skill is for finding the first record/replay mismatch, not for debugging the user's application.
investigate flaky, intermittent, non-reproducible, or ci-only python pytest failures by leading with retrace capture and deterministic replay. use when a user reports flaky pytest tests, random failures, tests that pass locally but fail in ci, async/threading/timing flakes, pytest-xdist issues, fixture leakage, monkeypatch leakage, test isolation failures, dependency/environment-sensitive failures, pytest timeouts, or ai-generated code that breaks tests intermittently. guide the agent to preserve the failed execution as a retrace trace, replay it, inspect runtime state, and use ordinary pytest/source/log checks only as supporting triage.