Brains Trust

# Brains Trust

Consult other leading AI models for a second opinion. Not limited to code — works for architecture, strategy, prompting, debugging, writing, or any question where a fresh perspective helps.

## Defaults (When User Just Says "Brains Trust")

If the user triggers this skill without specifying what to consult about, apply these defaults:

1. **Pattern**: Consensus (2 models from different providers) — it's called "brains trust", not "single opinion"
2. **Scope**: Whatever Claude has been working on in the current session. Look at recent context: files edited, decisions made, architecture discussed, problems being solved.
3. **Mode**: Infer from context:
   - Recently wrote/edited code → **Code Review**
   - In a planning or design discussion → **Architecture**
   - Debugging something → **Debug**
   - Building prompts or skills → **Prompting**
   - No clear signal → **General** (ask: "what are we missing? what are our blind spots?")
4. **Models**: Pick the newest pro-tier model from 2 different providers (check `models.flared.au`). Prefer diversity: e.g. one Google + one OpenAI, or one Qwen + one Google. Never two from the same provider.
5. **Prompt focus**: "Review what we've been working on. What are we missing? What could be improved? What blind spots might we have? Are there simpler approaches we haven't considered?"

### Trigger → Default Mapping

| Trigger | Default pattern | Default scope |
|---------|----------------|---------------|
| "brains trust" | Consensus (2 models) | Current session work |
| "second opinion" | Single (1 model) | Current session work |
| "ask gemini" / "ask gpt" | Single (specified provider) | Current session work |
| "peer review" | Consensus (2 models) | Recently changed files |
| "challenge this" / "devil's advocate" | Devil's advocate (1 model) | Claude's current position |

The user can always override by being specific: "brains trust this config file", "ask gemini about the auth approach", etc.

## Setup

Set at least one API key as an environment variable:

```bash
# Recommended — one key covers all providers
export OPENROUTER_API_KEY="your-key"

# Optional — direct access (often faster/cheaper)
export GEMINI_API_KEY="your-key"
export OPENAI_API_KEY="your-key"
```

OpenRouter is the universal path — one key gives access to Gemini, GPT, Qwen, DeepSeek, Llama, Mistral, and more.

## Current Models

**Do not use hardcoded model IDs.** Before every consultation, fetch the current leading models:

```
https://models.flared.au/llms.txt
```

This is a live-updated, curated list of ~40 leading models from 11 providers, filtered from OpenRouter's full catalogue. Use it to pick the right model for the task.

For programmatic use in the generated Python script: `https://models.flared.au/json`

## Consultation Patterns

| Pattern | Default for | What happens |
|---------|------------|-------------|
| **Consensus** | "brains trust", "peer review" | Ask 2 models from different providers in parallel, compare where they agree/disagree |
| **Single** | "second opinion", "ask gemini", "ask gpt" | Ask one model, synthesise with your own view |
| **Devil's advocate** | "challenge this", "devil's advocate" | Ask a model to explicitly argue against your current position |

For consensus, always pick mode