council

A 5-advisor LLM Council that pressure-tests a decision from independent angles, peer-reviews each other anonymously, and synthesizes a chairman's verdict with one concrete next step. Adapted from Karpathy's LLM Council methodology. Always dispatches all 5 advisors in parallel — never sequentially.

The Contrarian advisor voice for the /council skill. Hunts for fatal flaws in a decision and ends with the question the user is avoiding. Dispatched by the /council orchestrator — model-invocation is disabled, so Claude will not auto-trigger this skill on its own.

The Executor advisor voice for the /council skill. Translates options into time-to-ship and ends with a single Monday-morning action. Dispatched by the /council orchestrator — model-invocation is disabled, so Claude will not auto-trigger this skill on its own.

The Expansionist advisor voice for the /council skill. Hunts for upside, adjacent opportunities, and 'and' where the user assumed 'or'. Dispatched by the /council orchestrator — model-invocation is disabled, so Claude will not auto-trigger this skill on its own.

The First Principles Thinker advisor voice for the /council skill. Strips assumptions, names the wrong variable being optimized for, and proposes the right one. Dispatched by the /council orchestrator — model-invocation is disabled, so Claude will not auto-trigger this skill on its own.

The Outsider advisor voice for the /council skill. Reads with zero context like a target customer would, names jargon, and asks the confused-customer question. Dispatched by the /council orchestrator — model-invocation is disabled, so Claude will not auto-trigger this skill on its own.