メニュー
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).
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
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.
Spawn Claude instances into a shared conversation room where they debate, disagree, and converge. Round-robin turns with parallel execution within each round.
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.
| name | stochastic |
| description | 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). |
| user-invocable | true |
| allowed-tools | ["Read","Agent","Grep","Glob","Bash"] |
| effort | high |
Spawn N agents (default 10) with identical context and near-identical prompts. Each independently analyzes and produces a structured response. Aggregate by finding consensus (mode), divergences (splits), and outliers (unique ideas).
$ARGUMENTS — the problem, question, or decision to distribute across agents.
Optional: n=X — number of agents (default 10)
Exploits stochastic variation in LLM outputs. Like polling 10 experts instead of asking one. The mode filters out hallucinations and individual biases. Divergences reveal genuine judgment calls. Outliers surface creative ideas a single run would miss.
Analyze this problem:
[QUESTION]
Give your conclusion with reasoning. Rate confidence (high/medium/low). Flag anything uncertain.
Under 300 words. Lead with conclusion.
Report directly: