oracle

Identify patterns, contradictions, and missing dependencies across conflicting persona outputs.

15|2|Updated Feb 6, 2026
One-click install
npx skills add https://github.com/jdonohoo/vern-bot --skill oracle-jdonohoo
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: oracle
Source: https://github.com/jdonohoo/vern-bot/tree/main/skills/oracle
Command: npx skills add https://github.com/jdonohoo/vern-bot --skill oracle-jdonohoo

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Oracle Vern reads conflicting perspectives and noisy council outputs to surface the underlying signal: the unspoken dependencies, contradictions, and actionable tasks that teams miss during planning and review.

Core Features & Use Cases

  • Cross-perspective pattern recognition: Synthesizes multiple persona outputs to find reinforcement and tension among viewpoints.
  • Dependency & gap identification: Calls out missing tasks, hidden prerequisites, and implicit assumptions that can derail plans.
  • Actionable recommendations: Produces justified, prioritized tasks and suggestions that earn their place in a roadmap.
  • Use Case: During a multi-LLM design review, ask Oracle to reconcile conflicting recommendations, enumerate missing technical dependencies, and propose prioritized remediation steps.

Quick Start

Ask Oracle to analyze the council outputs and return the identified patterns, missing dependencies, and three prioritized action items.

Frequently Asked Questions about oracle

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

FAQPage Schema
How do I identify missing dependencies from conflicting multi-LLM council outputs?

Pattern recognition across conflicting persona outputs works by synthesizing multiple viewpoints to find reinforcement and tension. It surfaces unspoken dependencies, contradictions, and actionable tasks to reveal the underlying signal in noisy architecture reviews.

What is the best way to reconcile conflicting recommendations during an architecture review?

Reconciling conflicting recommendations during architecture reviews requires deep analytical synthesis. This approach surfaces contradictions and reinforcing signals across personas, enumerates missing technical dependencies, and provides justified, prioritized remediation steps.

How do I extract prioritized action items from noisy persona comparison reviews?

Extracting prioritized action items from noisy persona comparison reviews involves applying deep analytical synthesis to conflicting outputs. This produces justified, actionable recommendations and tasks that earn their place in a roadmap by resolving perspective gaps.

Does cross-perspective pattern recognition work for gap identification in planning outputs?

Cross-perspective pattern recognition works for gap identification in planning outputs. It synthesizes multiple persona outputs to call out missing tasks, hidden prerequisites, and implicit assumptions that can derail plans during multi-LLM reviews.

When do I need to use dependency identification for multi-LLM design reviews?

Dependency identification for multi-LLM design reviews is needed when viewpoints conflict or contain gaps. It surfaces hidden tasks and prerequisites across conflicting persona outputs, ensuring teams capture actionable tasks missed during initial planning.