skillZs
★ LIVE SKILL TAGS ★
>>> LIVE SKILLS INDEX <<<
* OPEN SOURCE *
NO LOGIN, NO TRACKING
※ REAL INSTALL DATA ※
← back to all skills
zereight/gitlab-mcp76 installs

deep-interview

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.

How do I install this agent skill?

npx skills add https://github.com/zereight/gitlab-mcp --skill deep-interview
view source ↗

Is this agent skill safe to install?

  • Gen Agent Trust Hubpass

    The skill is a requirements-gathering tool that uses Socratic questioning to clarify user ideas. It reads the local codebase to provide context and writes specification files to a project-specific directory. No malicious patterns or security risks were detected.

  • Socketpass

    No alerts

  • Snykpass

    Risk: LOW · No issues

What does this agent skill do?

Deep Interview

Ouroboros-inspired Socratic questioning with mathematical ambiguity scoring. Replaces vague ideas with crystal-clear specifications by asking targeted questions that expose hidden assumptions.

Pipeline

deep-interview → ralplan (consensus refinement) → omg-autopilot (execution)

When to Use

  • User has a vague idea and wants thorough requirements gathering
  • Task is complex enough that jumping to code would waste cycles
  • User wants mathematically-validated clarity before execution

When NOT to Use

  • Detailed specific request with file paths → execute directly
  • Quick fix → delegate to @executor or /ralph
  • User says "just do it" → respect their intent

Phases

Phase 1: Initialize

  1. Parse the user's idea
  2. Detect brownfield vs greenfield (use @explore to check codebase)
  3. For brownfield: map relevant codebase areas
  4. Initialize ambiguity score at 100%

Phase 2: Interview Loop

Repeat until ambiguity <= 20% or user exits early:

  1. Generate question targeting the WEAKEST clarity dimension
  2. Ask ONE question at a time with current ambiguity context
  3. Score ambiguity across dimensions:
    • Goal Clarity (40% weight for greenfield, 35% brownfield)
    • Constraint Clarity (30% / 25%)
    • Success Criteria (30% / 25%)
    • Context Clarity (N/A / 15% for brownfield)
  4. Report progress with dimension scores and gaps
  5. Track ontology (key entities, stability ratio)

Phase 3: Challenge Agents

  • Round 4+: Contrarian - challenge core assumptions
  • Round 6+: Simplifier - probe for complexity removal
  • Round 8+: Ontologist - find the essence (if ambiguity > 30%)

Phase 4: Crystallize Spec

When ambiguity <= threshold, generate spec to .omc/specs/deep-interview-{slug}.md:

  • Goal, Constraints, Non-Goals, Acceptance Criteria
  • Assumptions Exposed & Resolved
  • Ontology (Key Entities) with convergence tracking
  • Interview Transcript

Phase 5: Execution Bridge

Present options:

  1. Ralplan → OMG Autopilot (Recommended): consensus-refine then execute
  2. Execute with omg-autopilot (skip ralplan)
  3. Execute with ralph: persistence loop
  4. Execute with team: parallel agents
  5. Refine further: continue interviewing

Rules

  • Ask ONE question at a time
  • Target the WEAKEST clarity dimension each round
  • Gather codebase facts via @explore BEFORE asking user
  • Score ambiguity after every answer
  • Do not proceed until ambiguity <= threshold (default 20%)
  • Hard cap at 20 rounds, soft warning at 10

Add the canonical catalog link to the repository README so users can inspect current installs and available audits. The publishing guide covers the complete discovery path.

<a href="https://skillzs.dev/skills/zereight/gitlab-mcp/deep-interview">View deep-interview on skillZs</a>