skills.rest
sannidhyas
sannidhyasCOMMUNITY
Explore all skills by this author →
GitHub

council

Aggregate responses from Claude, Codex, and Ollama into a single judged answer.

1|Updated Apr 21, 2026
Search Tags:#design#architecture#decision making#multi-model#cross-model
One-click install
npx skills add https://github.com/sannidhyas/howl-pa --skill council-sannidhyas
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: council
Source: https://github.com/sannidhyas/howl-pa/tree/main/claude-plugin/skills/council
Command: npx skills add https://github.com/sannidhyas/howl-pa --skill council-sannidhyas

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires claude, codex, ollama, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill helps you make well-informed decisions by providing a multi-model council, combining insights from Claude, Codex, and Ollama for a well-rounded perspective.

Core Features & Use Cases

  • Multi-Model Deliberation: Aggregates responses from Claude, Codex, and local Ollama for comprehensive decision-making.
  • Decision Gates: Use it at key decision points to ensure no critical issues are overlooked.
  • Use Case: When you need to decide on a complex design issue, such as choosing a cache strategy or authentication flow, the council can provide a diverse set of insights to help guide your decision.

Quick Start

To get a multi-model deliberation on a design decision, type /howl-council best-of-n Which cache strategy fits our read pattern — LRU on Redis vs. TTL-only on node-cache?

Frequently Asked Questions about council

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

FAQPage Schema
How do I get multiple perspectives on a complex architectural decision?▼

Multi-model architectural decision making aggregates responses from Claude, Codex, and Ollama, then applies a merge, best-of-n, or vote judge to return a single, well-rounded answer for complex trade-offs.

What is the best way to choose between framework options like Redis and node-cache?▼

Use a multi-model council to evaluate framework selection trade-offs by querying Claude, Codex, and Ollama together, allowing a vote judge or best-of-n mechanism to identify the strongest recommendation.

Do I need local Ollama running to use cross-model design decisions?▼

Yes, cross-model design decisions require integration with Claude, Codex, and local Ollama. You must have these dependencies configured and accessible to fan out prompts and aggregate the responses.

When should I use a multi-model council instead of a single LLM for design decisions?▼

Use a multi-model council for non-obvious design decisions and architectural trade-offs where a single model might miss critical issues, ensuring diverse insights are aggregated through a vote or merge judge.

Can I use a merge or vote judge to combine responses from Claude and Codex?▼

Yes, you can apply a merge, best-of-n, or vote judge to combine responses from Claude, Codex, and Ollama, returning a single synthesized answer optimized for the specific design or architectural question.

Related Skills

Explore More Software Engineering Skills→
rawvegrawveg
40

ollama

Run and interact with local AI models via the Ollama API.

Community
Advanced
avivsinaiavivsinai
6

yoetz

Coordinate multi-model LLM tasks for code review and bundling workflows.

Community
Advanced
ntaksh42ntaksh42
1

prompt-engineering-helper

Analyze LLM prompts for clarity, specificity, and structure with improvement suggestions.

Community
Intermediate
timharris707timharris707

advisory-board

Convene multiple AI models to review, debate, and reach consensus on decisions.

Community
Advanced