skills.rest
oneforce
oneforceCOMMUNITY
Explore all skills by this author →
GitHub

deep-dive

Orchestrate trace analysis with structured interviews to generate deep-interview specs.

1|Updated Mar 27, 2026
Search Tags:#planning#requirements#orchestration#interview#trace#spec#deep-interview
One-click install
npx skills add https://github.com/oneforce/oh-my-gemini-cli --skill deep-dive-oneforce
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: deep-dive
Source: https://github.com/oneforce/oh-my-gemini-cli/tree/main/skills/deep-dive
Command: npx skills add https://github.com/oneforce/oh-my-gemini-cli --skill deep-dive-oneforce

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Deep Dive solves the challenge of turning ambiguous problems into concrete, testable specs by orchestrating trace-based investigation with a structured interview to crystallize requirements.

Core Features & Use Cases

  • Trace-driven interview: Runs three parallel trace lanes to surface root causes and critical unknowns, then injects findings into the interview.
  • 3-point injection: Transfers trace findings to initialize the interview with targeted questions, preserving context.
  • Spec generation: Produces a standard deep-interview style spec at .omg/specs/deep-dive-{slug}.md for downstream planning and execution.
  • Brownfield and Greenfield support: Works with existing codebases or entirely new ideas, adapting the trace lanes accordingly.
  • Safety & resilience: Wraps untrusted trace data in delimiters and persists state for resume.

Quick Start

Run /deep-dive with your problem to begin a trace-to-interview workflow and produce a ready-to-execute spec.

Frequently Asked Questions about deep-dive

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

FAQPage Schema
How do I turn ambiguous project requirements into a testable spec?▼

A trace-driven interview process surfaces root causes and critical unknowns by running parallel trace lanes, then uses a 3-point injection to transfer those findings into structured interview questions, preserving full context throughout the workflow.

Does structured requirement gathering work for existing codebases?▼

To start a trace-driven interview, run the workflow command with your problem statement to initiate the 2-stage process, which automatically orchestrates trace analysis, conducts the structured interview, and exports the final spec to the .omg/specs directory for planning.

Can I resume requirement gathering if the workflow is interrupted?▼

The trace-to-interview approach differs from standard requirement gathering by actively running parallel trace lanes to investigate root causes before initializing a structured interview, ensuring the final spec is grounded in surfaced evidence rather than assumptions.

What's the best way to generate specs for downstream autopilot execution?▼

The trace-to-interview workflow exports a standard deep-interview style spec file to the .omg/specs directory, providing a ready-to-execute document that serves as the single source of truth for downstream planning and autopilot execution.

Related Skills

Explore More Product & Management Skills→
MohammedSaudAlsahliMohammedSaudAlsahli

deep-dive

Trace and interview to investigate root causes and crystallize requirements.

Community
Advanced
ChegginCheggin
1

deep-dive

Run a two-stage trace and interview workflow to produce a testable specification.

Community
Advanced
connor-git-yamlconnor-git-yaml
15

speckit-feature

Coordinate ten-phase Spec-Driven Development workflows with Claude Code Task tools.

Community
Advanced
r3dlexr3dlex
2

deep-dive

Analyze complex technical issues through root cause investigation and requirement capture.

Community
Advanced