Hi everyone,

When you ask an AI assistant for advice, it can be difficult to tell whether it has examined the tradeoffs or simply followed your framing.

I’ve put together Portable LLM Council, an open-source skill that helps you explore a business or technical decision through several perspectives before receiving a recommendation.

The process has three rounds:

• Five separate advisors examine assumptions, fundamentals, overlooked opportunities, clarity, and execution.

• Five fresh reviewers evaluate the anonymized answers for strong arguments and blind spots.

• A chair weighs the reasoning and recommends a direction and one concrete first step.

The assistant saves an HTML report and a Markdown transcript so you can inspect the arguments behind the recommendation.

Useful questions include:
— Should we launch a paid pilot or build the full product?
— Should our team focus on onboarding or acquiring more customers?
— Should we migrate a system gradually or replace it in one go?

These are starting questions, not complete prompts. The decision needs relevant context.

Share your objective, constraints, options, and evidence so far—or ask the assistant to use the discussion you’ve already had. A few focused paragraphs are usually enough. The example questions above are starting points, not complete prompts.

One shared skill supports native subagents for Claude Code—including local Code sessions in Claude Desktop—Codex, Cursor, Command Code, Grok Build, OpenCode, and Factory Droid. No particular model is required.

To get started, give your assistant this instruction:

“Read the installation instructions at https://github.com/goolamabbas/portable-llm-council and install the shared skill and the agent definitions for this harness in my personal installation locations. Back up existing copies before replacing anything, then verify discovery. Do not run a council yet.”

Your assistant may request approval for file changes. You may need to start a new session before it can verify discovery. The repository also includes manual installation instructions and example prompts:

https://github.com/goolamabbas/portable-llm-council

A full council takes more time and model usage than an ordinary answer, so it’s best reserved for decisions with meaningful tradeoffs. Agreement isn’t proof of correctness. The benefit is uncovering assumptions, competing arguments, and evidence you may need before acting.

If you try it, I’d love to hear what it helped you notice—and where it fell short.

Best,
Yusuf