MCPInstall

brains-trust

by jezwebAI & Agents

Get a second opinion from leading AI models on code, architecture, strategy, prompting, or anything. Queries models via OpenRouter, Gemini, or OpenAI APIs. Supports single opinion, multi-model consensus, and devil's advocate patterns. Trigger with 'brains trust', 'second opinion', 'ask gemini', 'ask gpt', 'peer review', 'consult', 'challenge this', or 'devil's advocate'.

Installs
535
Last 24h
—
Trending rank
—
Security
Not audited

Install

Works with every agent the skills CLI supports.

npx skills add https://github.com/jezweb/claude-skills --skill brains-trust
  1. 01

    Install

    Run the command in your project. The CLI asks which agents to install for.

  2. 02

    Describe the task

    Ask your agent for something this skill covers. It loads brains-trust automatically when relevant.

  3. 03

    Review the result

    The agent follows the SKILL.md steps, scripts and references bundled with the skill.

SKILL.md

The instructions your agent reads when the skill is triggered.

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

TriggerDefault patternDefault 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:

# 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

PatternDefault forWhat 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 models from different providers (e.g. one Google + one Qwen) for maximum diversity of perspective.

Modes

ModeWhenModel tier
Code ReviewReview files for bugs, patterns, securityFlash
ArchitectureDesign decisions, trade-offsPro
DebugStuck after 2+ failed attemptsFlash
SecurityVulnerability scanPro
StrategyBusiness, product, approach decisionsPro
PromptingImprove prompts, system prompts, KB filesFlash
GeneralAny question, brainstorm, challengeFlash

Pro tier: The most capable model from the chosen provider (e.g. google/gemini-3.1-pro-preview, openai/gpt-5.4). Flash tier: Fast, cheaper models for straightforward analysis (e.g. google/gemini-3-flash-preview, qwen/qwen3.5-flash-02-23).

Workflow

  1. Detect available keys — check OPENROUTER_API_KEY, GEMINI_API_KEY, OPENAI_API_KEY in environment. If none found, show setup instructions and stop.

  2. Fetch current models — WebFetch https://models.flared.au/llms.txt and pick appropriate models based on mode (pro vs flash) and consultation pattern (single vs consensus). If user requested a specific provider ("ask gemini"), use that.

  3. Read target files into context (if code-related). For non-code questions (strategy, prompting, general), skip file reading.

  4. Build prompt using the AI-to-AI template from references/prompt-templates.md. Include file contents inline with --- filename --- separators. Do not set output token limits — let models reason fully.

  5. Create consultation directory at .jez/artifacts/brains-trust/{timestamp}-{topic}/ (e.g. 2026-03-10-1423-auth-architecture/). Write the prompt to prompt.txt inside it — never pass code inline via bash arguments (shell escaping breaks it).

  6. Generate and run Python script at .jez/scripts/brains-trust.py using patterns from references/provider-api-patterns.md:

    • Reads prompt from the consultation directory's prompt.txt
    • Calls the selected API(s)
    • For consensus mode: calls multiple APIs in parallel using concurrent.futures
    • Saves each response to {model}.md in the consultation directory
    • Prints results to stdout

  7. Synthesise — read the responses, present findings to the user. Note where models agree and disagree. Add your own perspective (agree/disagree with reasoning). Let the user decide what to act on.

When to Use

Good use cases:

  • Before committing major architectural changes
  • When stuck debugging after multiple attempts
  • Architecture decisions with multiple valid options
  • Reviewing security-sensitive code
  • Challenging your own assumptions on strategy or approach
  • Improving system prompts or KB files
  • Any time you want a fresh perspective

Avoid using for:

  • Simple syntax checks (Claude handles these)
  • Every single edit (too slow, costs money)
  • Questions with obvious, well-known answers

Critical Rules

  1. Never hardcode model IDs — always fetch from models.flared.au first
  2. Never cap output tokens — don't set max_tokens or maxOutputTokens
  3. Always write prompts to file — never pass via bash arguments
  4. Include file contents inline — attach code context directly in the prompt
  5. Use AI-to-AI framing — the model is advising Claude, not talking to the human
  6. Print progress to stderr — the Python script must print status updates (Calling gemini-2.5-pro..., Received response from qwen3.5-plus.) so the user knows it's working during the 30-90 second wait

Reference Files

WhenRead
Building prompts for any modereferences/prompt-templates.md
Generating the Python API call scriptreferences/provider-api-patterns.md

FAQ

What does the brains-trust skill do?

Get a second opinion from leading AI models on code, architecture, strategy, prompting, or anything. Queries models via OpenRouter, Gemini, or OpenAI APIs. Supports single opinion, multi-model consensus, and devil's advocate patterns. Trigger with 'brains trust', 'second opinion', 'ask gemini', 'ask gpt', 'peer review', 'consult', 'challenge this', or 'devil's advocate'.

How do I install brains-trust?

Run npx skills add https://github.com/jezweb/claude-skills --skill brains-trust in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/brains-trust/ (personal) or .claude/skills/brains-trust/ (project).

Which AI agents can use brains-trust?

Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.

Is brains-trust safe to install?

No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.

Who maintains brains-trust?

It is published by jezweb in jezweb/claude-skills. It has 535 recorded installs.

More from jezweb/claude-skills

View all →

shadcn-ui

jezweb/claude-skills

Install and configure shadcn/ui components for React projects. Guides component selection, installation order, dependency management, customisation with semantic tokens, and common UI recipes (forms, data tables, navigation, modals). Use after tailwind-theme-builder has set up the theme infrastructure, when adding components, building forms, creating data tables, or setting up navigation.

Frontend & Design3.6K installs

color-palette

jezweb/claude-skills

Generate complete, accessible colour palettes from a single brand hex. Produces 11-shade scale (50-950), semantic tokens, dark mode variants, Tailwind v4 CSS output, WCAG contrast checks. Use whenever the user supplies a brand hex and asks for a palette, mentions setting up a design system, wants Tailwind theme colours from a brand colour, or asks to check colour accessibility / contrast.

Frontend & Design3.2K installs

tailwind-theme-builder

jezweb/claude-skills

Set up Tailwind v4 + shadcn/ui themed UI with dark mode. Install deps, configure CSS variables via @theme inline, wire dark mode toggle, verify. Use whenever the user mentions Tailwind v4, setting up Tailwind theming, shadcn/ui colours, dark mode, or troubleshooting colours not working, tw-animate-css errors, @theme inline conflicts, @apply breaking after upgrade, or v3 → v4 migration issues.

Frontend & Design3.2K installs

wordpress-elementor

jezweb/claude-skills

Edit Elementor pages and manage templates on WordPress sites via browser automation (for visual / structural changes) or WP-CLI (for safe text replacements). Use whenever the user wants to edit an Elementor page, update text in Elementor widgets, apply or manage Elementor templates, or make content changes to pages built with the Elementor page builder.

Productivity & Automation2.9K installs

ux-audit

jezweb/claude-skills

Walk through a live web app AS a real user to find usability + behavioural bugs that static reviews miss. REQUIRES proof of interaction (typing, clicking, sending, observing) before any verdict — a sweep that didn't interact terminates with verdict 'Incomplete'. Walks threads, exercises every element, runs the multi-pane stress matrix, visual polish sweep, component perfection checklist, automated a11y (axe-core), pragmatic performance budget (LCP/CLS/INP), scenario battery (11 scenarios), and stress recipes including the real-flavour data battery. Hard gates: console errors/warnings = 0, network 5xx = 0, layout collapse = 0, axe Critical/Serious = 0, perf budget green. Audit-the-audit meta-check rejects rushed reports. Each finding has reproduction steps, evidence path, and suspected code location. Trigger with 'ux audit', 'walkthrough', 'qa sweep', 'audit the app', 'dogfood this', 'check all pages', 'find what's broken', 'stress the UI'.

Frontend & Design2.8K installs

tailwind-v4-shadcn

jezweb/claude-skills

Set up Tailwind v4 with shadcn/ui using @theme inline pattern and CSS variable architecture. Four-step pattern: CSS variables, Tailwind mapping, base styles, automatic dark mode. Prevents 8 documented errors. Use when initializing React projects with Tailwind v4, or fixing colors not working, tw-animate-css errors, @theme inline dark mode conflicts, @apply breaking, v3 migration issues.

Frontend & Design2.6K installs

Popular ai & agents skills

View category →

google-agents-cli-publish

google/agents-cli

This skill should be used when the user wants to "publish an agent", "publish my ADK agent", "register an agent with Gemini", "publish to Gemini" (formerly Gemini Enterprise), or needs guidance on the agents-cli publish gemini command. Also use when the user wants to "manage agents in Agent Registry", "list/update/delete registered agents", or "register an MCP server". Covers ADK vs A2A registration modes, programmatic and interactive usage, flag reference, auto-detection from deployment metadata, Agent Registry fleet management, and troubleshooting. Part of the agents-cli skills suite. Do NOT use for deployment (use google-agents-cli-deploy).

AI & Agents513.9K installs

google-agents-cli-eval

google/agents-cli

This skill should be used when the user wants to "run an evaluation", "evaluate my agent", "evaluate my ADK agent", "write an eval dataset", "analyze eval failures", "compare eval results", "optimize agent", or needs guidance on the Gemini platform eval methodology and the Quality Flywheel. Covers eval metrics, dataset schema, LLM-as-judge scoring, and common failure causes. Applies to any agents-cli project, whatever framework the agent is written in. Do NOT use for agent API code patterns (ADK: use google-agents-cli-adk-code), deployment (use google-agents-cli-deploy), or project scaffolding (use google-agents-cli-scaffold).

AI & Agents513.5K installs

skill-creator

anthropics/skills

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

OfficialAI & Agents416.4K installs

codex-pet

prime-skills/runcomfy-agent-skills

Codex Pet generator on RunComfy. Build a Codex-compatible Codex Pet spritesheet.webp + pet.json from a single reference image, drop it into ${CODEXHOME:-$HOME/.codex}/pets/ / and Codex picks it up as a custom Codex Pet next to the 8 built-ins. This skill produces the exact Codex Pet atlas Codex expects (1536x1872 PNG/WebP, 8 cols x 9 rows, 192x208 cells, 9 animation states — idle, running-right, running-left, waving, jumping, failed, waiting, running, review). Calls OpenAI GPT Image 2 edit ONCE via the local RunComfy CLI as runcomfy run openai/gpt-image-2/edit to produce a canonical Codex Pet pose, then assembles all 9 animation rows programmatically with ImageMagick micro-transforms — no Codex Pro, no $imagegen, no OPENAIAPIKEY required, only RUNCOMFYTOKEN. Triggers on "codex pet", "create codex pet", "make codex pet", "hatch codex pet", "/hatch image", "desktop pet codex", "codex pets", "spritesheet.webp", or any explicit ask to build a custom pet for OpenAI Codex.

AI & Agents402.1K installs

full-output-enforcement

leonxlnx/taste-skill

Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.

AI & Agents401K installs

executing-plans

obra/superpowers

Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available

AI & Agents245.7K installs