Multi-agent collaborative debate producing visible round-by-round transcripts with real intellectual friction — members are topic-briefed custom agents, run as a 3-round DEBATE or a 1-round QUICK check, to find the best path
Asking an AI to give you multiple perspectives usually produces a single voice wearing different hats. The "devil's advocate" agrees with the main position at the end. The "skeptic" shares no domain expertise with the topic at hand. You get the appearance of debate without the actual friction that makes it useful.
Council composes 4-6 custom agents via ComposeAgent with domain expertise and personality traits tailored to the specific question — never generic types. Those agents run in parallel within each round, read each other's actual arguments, and respond to them directly. Three sequential rounds let positions evolve through genuine friction. The DEBATE workflow produces a full round-by-round transcript plus synthesis; QUICK produces first-round positions for a fast sanity check. The collaborative-adversarial framing keeps it aimed at finding the best path rather than just attacking, which separates it from RedTeam.
What you say to your DA, and what the Council skill actually does.
The thinking, frameworks, and architecture that distinguish this skill from a generic version of the same task.
Runs a multi-agent debate. Custom-composed agents discuss a topic over rounds, respond to each other's actual points, and surface insights through real intellectual friction. You get a visible round-by-round transcript plus a synthesis. DEBATE runs three rounds; QUICK runs one for a fast perspective check.
When you ask one model for an opinion, you get one frame and one set of blind spots. Asking for "pros and cons" gives you a flat list with no one actually pushing back. Real deliberation needs distinct experts who disagree on the merits and argue it out, so the weak parts of an idea get exposed before you commit. Generic built-in agents all sound the same and produce bland agreement; this skill composes topic-specific agents that create genuine friction.
Custom-composed agents discuss topics in rounds, respond to each other's points, and surface insights through intellectual friction.
Write each council member inline as a short brief — a name, a role, a stance, and what they'll push on — then launch it with subagent_type: "general-purpose". A bare built-in type with no persona is topic-ignorant and produces bland agreement. The friction comes from four different briefs, each with real domain expertise and a distinct analytical angle.
See CouncilMembers.md for the slot guidance and an example brief.
Key Differentiator from RedTeam: Council is collaborative-adversarial (debate to find best path), while RedTeam is purely adversarial (attack the idea). Council produces visible conversation transcripts; RedTeam produces steelman + counter-argument.
| Workflow | Purpose | Rounds | Output |
|---|---|---|---|
| DEBATE | Full structured discussion | 3 | Complete transcript + synthesis |
| QUICK | Fast perspective check | 1 | Initial positions only |
| File | Content |
|---|---|
CouncilMembers.md |
How to write council member briefs inline |
RoundStructure.md |
Three-round debate structure and timing |
OutputFormat.md |
Transcript format templates |
Origin: Best decisions emerge from diverse perspectives challenging each other. Not just collecting opinions - genuine intellectual friction where domain-specific experts respond to each other's actual points.
Agents: Every council member is a custom brief you write for the topic, launched with general-purpose. This gives each member a distinct role, stance, and domain expertise. Generic agents produce generic debate; topic-specific briefs produce sharp, informed debate.
Speed: Parallel execution within rounds, sequential between rounds. A 3-round debate of 4 agents = 12 agent calls but only 3 sequential waits. Complete in 40-90 seconds.
"Council: Should we use WebSockets or SSE?"
-> Write 4 member briefs (real-time architect, frontend-DX, ops skeptic, researcher)
-> DEBATE workflow -> 3-round transcript
"Quick council check: Is this API design reasonable?"
-> Write 4 member briefs with API-relevant roles
-> QUICK workflow -> Fast perspectives
"Council: Is AI overhyped?"
-> Write briefs: AI builder, security skeptic, pragmatic engineer, evidence analyst
-> DEBATE workflow -> 3-round transcript
Works well with:
Last Updated: 2026-03-18
general-purpose — there is no composition tool. Write four different topic-specific briefs; don't launch bare built-in types with no persona.Each workflow is one job the skill runs. The trigger phrases route your request to the right one — this is the skill's routing table.
Workflows/`Workflows/Debate.md`.md Full structured debate (3 rounds, visible transcript)
Workflows/`Workflows/Quick.md`.md Quick consensus check (1 round, fast)
Say any of these to your DA and LifeOS activates the Council skill automatically:
Or invoke explicitly:
Skill("Council")Auxiliary files the skill loads at runtime — frameworks, guides, configs.
The thinkers, books, frameworks, and research this skill is built on. The ideas belong to them — the integration belongs to LifeOS.
Install LifeOS on your machine — your DA gets the Council skill plus 46 others, all hooked into one Life OS.