القائمة
Spawn Claude instances into a shared conversation room where they debate, disagree, and converge. Round-robin turns with parallel execution within each round.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
| name | model-chat |
| description | Spawn Claude instances into a shared conversation room where they debate, disagree, and converge. Round-robin turns with parallel execution within each round. |
| user-invocable | true |
| allowed-tools | ["Read","Agent","Grep","Glob","Bash"] |
| effort | default |
Spawn 5 Claude Sonnet instances into a shared conversation room. They debate a problem across 5 rounds using round-robin turns (all agents respond in parallel each round, see full history). A synthesizer agent then merges the debate into a final answer.
$ARGUMENTS — the topic or problem to debate.
Optional:
agents=X — number of agents (default 5)rounds=X — number of debate rounds (default 5)Same model, slight framing variations = systematically different failure modes. Surfacing disagreements between instances is more valuable than any single instance's confident answers. Consensus across independent runs filters hallucinations, divergences reveal judgment calls.
You are Agent [N] in a debate room.
Topic: [QUESTION]
Conversation so far:
[FULL HISTORY]
Respond with your position. Agree, disagree, or build on others. Be direct.
Under 150 words.
Here is a debate between [N] agents across [R] rounds:
[FULL DEBATE]
Synthesize into a final answer. Note where they agreed, where they diverged, and your verdict.
Report directly:
Multi-agent primitives for Claude Code: consensus, debate, fanout research, skill building, and measured optimization.
TRIGGER when user explicitly invokes optimization with a numeric automatable metric — "optimize the lighthouse score", "shrink the bundle", "reduce build time", "cut p99 latency", "hill climb the eval accuracy", "/autoresearch", "make X faster" where X is measurable. Drops a working hill-climb harness into the project, generates project-specific mutations by reading the codebase, runs the loop. SKIP when there's no numeric metric, when changes need design/UX/copy judgment, or for one-off manual tuning. SKIP requests like "make this cleaner/better/smaller" that have no measurement command.
Fan-out/fan-in research. Spawns N researchers (Sonnet) in parallel to explore a question from different angles, then synthesizes findings with Opus.
Build flawless Claude Code skills. Studies existing skills as reference, ensures correct format, and pushes for genuine intelligence — skills that exploit something specific about how Claude works. SKIP for one-off scripts, prompts, or task helpers.
Stochastic multi-agent consensus. Spawns N agents with identical prompts to independently analyze a problem. Aggregates by consensus (mode), divergences (splits), and outliers (unique ideas).