Help us improve
Share bugs, ideas, or general feedback.
From octo
Runs a configurable multi-LLM council with personas, budget caps, synthesis, veto gates, and optional implementation handoff for advice, decisions, plans, or reviews.
npx claudepluginhub nyldn/claude-octopus --plugin octoHow this skill is triggered — by the user, by Claude, or both
Slash command
/octo:skill-councilThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Use this skill for `/octo:council` and council-style requests.
Convenes multiple AI models to deliberate and reach consensus on plans, designs, or acceptance criteria. Supports brainstorm, debate, and verdict modes.
Spawns AI council perspectives (User Advocate, Architect, Skeptic, etc.) to analyze decisions, plans, and ideas from multiple angles, delivering synthesized reports with verdicts and tensions.
Conducts multi-persona debates for founder decisions with 4 grounded personas (Operator, Buyer, Investor, Contrarian) across structured rounds. Outputs transcript, recommendation, and decision log.
Share bugs, ideas, or general feedback.
Use this skill for /octo:council and council-style requests.
Collect or infer:
advice, decision, plan, implement, or reviewauto, architecture, product, security, business, research, or docsbalanced, adversarial, implementation, executive, or red-teamquick, standard, or deepauto, 3, 5, or 7Show the selected council, provider availability, benchmark freshness, quorum requirement, and cost estimate before provider fanout. Re-check the budget before critique, revision, synthesis, and implementation planning so the run stops before the next phase would exceed --max-cost. If the run is a dry run, stop after this preflight and write summary.json.
Never implement from council output without explicit approval. Preserve disagreement, summarize risks, and keep vetoes visible in the final answer and artifacts.