From octo
Frames a technical decision as a multi-model debate, assigns sides to AI providers, and launches /octo:debate. Useful for getting adversarial perspectives on two-or-more-sided decisions.
How this skill is triggered — by the user, by Claude, or both
Slash command
/octo:debate-kickoffThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Turn a loosely stated decision ("Redis or Memcached?", "monorepo vs polyrepo") into a well-formed multi-model debate.
Turn a loosely stated decision ("Redis or Memcached?", "monorepo vs polyrepo") into a well-formed multi-model debate.
The user has a two-or-more-sided technical decision and wants adversarial perspectives from different model families rather than one model's opinion.
${CLAUDE_PLUGIN_ROOT}/scripts/helpers/check-providers.sh and note which providers are available. A debate needs at least two seatable non-Claude providers for cross-lab disagreement; if only Claude is available, say so and offer a single-model pro/con instead./octo:debate with the motion and the side assignments. Display the standard Octopus banner with provider indicators before dispatch.npx claudepluginhub nyldn/claude-octopus --plugin octoFacilitates structured multi-provider AI debates between Claude and available advisors for critical decisions. Dispatches real providers via orchestrate.sh for diverse perspectives.
Debates design decisions using cross-model AI discussions. Supports Agent Teams, Codex CLI, and self-debate modes for multi-perspective validation of architectures and design choices.
Spawns multiple expert agents to debate or poll a high-stakes decision with no clear winner. Surfaces tradeoffs, genuine disagreements, and suggests a path with reversibility cost. Standalone or sub-routine.