// 2-stage pipeline: trace (causal investigation) then deep-interview (requirements). Activate when user says: deep dive, deep-dive, investigate deeply, trace and interview.
| name | deep-dive |
| description | 2-stage pipeline: trace (causal investigation) then deep-interview (requirements). Activate when user says: deep dive, deep-dive, investigate deeply, trace and interview. |
| argument-hint | <problem or exploration target> |
Orchestrates a 2-stage pipeline: first investigate WHY something happened (trace), then define WHAT to do about it (deep-interview). Trace findings feed into the interview via 3-point injection.
deep-dive → ralplan (consensus refinement) → omg-autopilot (execution)
/deep-interview/tracePresent hypotheses to user for confirmation (1 round).
Run 3 parallel tracer lanes using @tracer agents:
.omc/specs/deep-dive-trace-{slug}.mdFollow deep-interview protocol with 3 overrides:
Low-confidence trace: don't inject uncertain conclusion, use ALL unknowns as questions.
Same options as deep-interview: ralplan → omg-autopilot (recommended), omg-autopilot, ralph, team, or refine further.
Spec saved to .omc/specs/deep-dive-{slug}.md with additional "Trace Findings" section.
Use this skill when working with the GitLab MCP server tools for merge requests, issues, repositories, pipelines, work items, webhooks, search, and related GitLab workflows.
Cancel any active OMG mode and clean up state. Activate when user says: cancel, stop, cancelomg, stopomg, abort, kill it, stop everything.
Socratic deep interview with mathematical ambiguity gating. Activate when user says: deep interview, interview me, ask me everything, don't assume, make sure you understand, ouroboros, socratic, I have a vague idea, not sure exactly what I want.
Full autonomous execution from idea to working code. Activate when user says: autopilot, auto-pilot, autonomous, build me, create me, make me, full auto, handle it all, or "I want a/an..."
Strategic planning with optional interview workflow. Activate when user says: plan this, plan the, let's plan, make a plan, how should we approach.
PRD-driven persistence loop until task completion with verification. Activate when user says: ralph, don't stop, must complete, finish this, keep going until done.