deep-dive

Trace root causes and crystallize actionable requirements through a 3-point injection workflow.

Updated Mar 31, 2026
One-click install
npx skills add https://github.com/ClementATH/oh-my-claudecode --skill deep-dive-clementath
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: deep-dive
Source: https://github.com/ClementATH/oh-my-claudecode/tree/main/skills/deep-dive
Command: npx skills add https://github.com/ClementATH/oh-my-claudecode --skill deep-dive-clementath

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Deep Dive orchestrates a 2-stage workflow that first investigates why something happened (trace) and then defines what to do about it (deep-interview), using a 3-point injection to preserve context across steps so that insights from tracing directly inform the interview.

Core Features & Use Cases

  • End-to-end orchestration of trace-driven interviews that produce a validated spec
  • 3-phase injection: injects trace findings into the interview initialization, preserving system context
  • Phase-driven execution: initializes, confirms lanes, runs parallel trace lanes, injects results, and bridges to execution
  • Works for greenfield and brownfield problems, uncertainties, and complex architectural investigations

Quick Start

Provide a problem description to kick off the trace-interview crystallization flow.

Frequently Asked Questions about deep-dive

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I trace root causes and translate findings into actionable requirements?

Root cause tracing and requirements crystallization are orchestrated by running a two-stage workflow that first investigates why something happened using parallel trace lanes, then injecting those findings into a deep-interview to define what to do next.

What is the best way to investigate ambiguous problems in brownfield projects?

Investigating ambiguous brownfield problems is handled by a phase-driven execution flow that maintains stateful persistence and context continuity, ensuring insights from tracing directly inform the final validated spec.

How does context persistence work during a trace and interview workflow?

Context persistence during a trace and interview workflow works through a 3-point injection protocol, which preserves system context by injecting trace findings directly into the interview initialization phase.

Can I bridge architectural investigations directly into execution pipelines?

You can bridge architectural investigations into execution pipelines because the workflow outputs a validated spec and connects to execution via omc-plan and autopilot, turning crystallized requirements into actionable plans.

Does this workflow support parallel trace lanes for complex bug investigations?

Parallel trace lanes are supported for complex bug investigations, allowing the workflow to run multiple investigations concurrently before consolidating results into the deep-interview phase for spec crystallization.

When do I need a trace-driven interview for feature exploration?

A trace-driven interview for feature exploration is needed when facing uncertainties in greenfield or brownfield projects, ensuring that architectural investigations and root cause analysis directly inform the validated requirements.