Guides systematic root-cause debugging. Use when tests fail, builds break, behavior does not match expectations, or any unexpected error appears.
npx claudepluginhub v1truv1us/ai-eng-system --plugin ai-eng-learningThis skill uses the workspace's default tool permissions.
Adapted from `addyosmani/agent-skills` (MIT), commit `82ceff41ed4d3c644e3dcca8a0514390b2911223`.
Creates isolated Git worktrees for feature branches with prioritized directory selection, gitignore safety checks, auto project setup for Node/Python/Rust/Go, and baseline verification.
Executes implementation plans in current session by dispatching fresh subagents per independent task, with two-stage reviews: spec compliance then code quality.
Dispatches parallel agents to independently tackle 2+ tasks like separate test failures or subsystems without shared state or dependencies.
Adapted from addyosmani/agent-skills (MIT), commit 82ceff41ed4d3c644e3dcca8a0514390b2911223.
Debugging should be systematic. Preserve evidence, reproduce the failure, localize the cause, fix the root cause, and add a guard against recurrence.
When something unexpected happens:
Make the failure happen reliably. If you cannot reproduce it, capture the conditions under which it appears and instrument the system carefully.
Determine which layer is actually failing:
Create the smallest failing example. Strip unrelated code and data until only the bug remains.
Do not patch the symptom if the failure originates elsewhere.
Add a regression test, alert, or verification step that would catch the same failure next time.
Run the relevant targeted checks, then the broader checks needed to prove the system is healthy again.
| Rationalization | Reality |
|---|---|
| "I already know the fix" | Maybe, but reproducing first prevents wasted iterations. |
| "It is flaky, just rerun it" | Flakiness is a real failure mode that should be understood. |
| "It works on my machine" | Environment differences are often the bug. |