القائمة
2-stage pipeline: trace (causal investigation) then deep-interview (requirements). Activate when user says: deep dive, deep-dive, investigate deeply, trace and interview.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Use this skill when working with the GitLab MCP server tools for merge requests, issues, repositories, pipelines, work items, variables, dependency proxy, webhooks, search, CI catalog, and related GitLab workflows.
Clean AI-generated code slop with regression-safe workflow. Activate when user says: deslop, anti-slop, AI slop, cleanup slop, clean up this code, remove bloat.
Cancel any active OMG mode and clean up state. Activate when user says: cancel, stop, cancelomg, stopomg, abort, kill it, stop everything.
Claude-Codex-Gemini tri-model orchestration for multi-perspective analysis. Activate when user says: ccg, tri-model, three models, multi-model, cross-validate, get multiple opinions, compare models.
Canonical cross-language coding standards reference. Shared rules embedded by reviewer agents. Activate when: viewing coding standards, checking naming rules, reviewing style baseline, consulting style guide, what are the rules.
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.
| 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.