ALWAYS activate before fixing ANY bug, error, test failure, CI/CD issue, type error, lint, log error, UI issue.
Unified skill for fixing issues of any complexity with intelligent routing.
| Flag | When | Behavior |
|---|---|---|
--auto | Simple/moderate issues (default) | Auto-approve if score ≥ 9.5 |
--review | Critical/production code | Pause for approval each step |
--quick | Type errors, lint, trivial bugs | Fast debug → fix → review |
--parallel | 2+ independent issues | Parallel agents per issue |
If no --auto flag present, ask user to select mode.
@[skills/debug]| Level | Indicators | Workflow |
|---|---|---|
| Simple | Single file, clear error, type/lint | references/workflow-quick.md |
| Moderate | Multi-file, root cause unclear | references/workflow-standard.md |
| Complex | System-wide, architecture impact | references/workflow-deep.md |
| Parallel | 2+ independent issues | Parallel agents per issue |
./docs if changes warrant@[skills/debug]@[skills/problem-solving], @[skills/sequential-thinking]@[skills/brainstorm]Step 0: [Mode] selected — [Complexity] detected
Step 1: Root cause identified — [summary]
Step 2: Fix implemented — [N] files changed
Step 3: Tests [X/X passed]
Step 4: Review [score]/10 — [status]
Step 5: Complete
references/complexity-assessment.md — Classification criteriareferences/workflow-quick.md / workflow-standard.md / workflow-deep.mdreferences/workflow-ci.md — GitHub Actions failuresreferences/workflow-test.md — Test suite failuresreferences/workflow-types.md — TypeScript type errors