P

paseo-committee

by @getpaseov
4.4(120)

この Skill は、2つの高推論能力を持つAIエージェントからなる委員会を編成し、根本原因分析と詳細な計画策定に特化しています。ユーザーが複雑な問題で行き詰まったり、堂々巡りになったり、視野が狭まったり、困難な計画課題に直面している場合に非常に役立ちます。この Skill は、新たな視点と代替ソリューションを提供することで、膠着状態を効果的に打破し、問題が徹底的に解決されることを保証します。

multi-agentroot-cause-analysisplanningcollaborationproblem-solvingGitHub
インストール方法
npx skills add https://github.com/getpaseo/paseo --skill paseo-committee
compare_arrows

Before / After 効果比較

1 组
使用前

ユーザーは複雑な問題で行き詰まり、根本原因の特定に苦労し、計画プロセスが繰り返し妨げられます。チームは固定観念に陥り、効率の低下や誤った意思決定につながることがあります。

使用後

この Skill は、2つの高推論エージェントを導入して独立した分析と協調を行うことで、根本原因を迅速に特定し、多角的なソリューションを提供し、意思決定の質と問題解決の効率を大幅に向上させます。

SKILL.md

Committee Skill

Two agents from contrasting providers, fresh context, planning a solution in parallel. They stay alive for review after implementation.

The purpose is to step back, not double down. The committee may propose a completely different approach.

User's additional context: $ARGUMENTS

Prerequisites

Read the paseo skill. Before choosing committee members, read ~/.paseo/orchestration-preferences.json unless the user explicitly named providers in this request. Do not create committee agents until you have read it.

Contrast is the point of a committee, so pick across providers deliberately using the configured preferences rather than hardcoded defaults.

Composition

Two members with different reasoning styles, selected from orchestration preferences:

  • one planning/research-strength provider
  • one contrasting high-reasoning provider

Override only when the user explicitly asks for different members.

Hard rules

  • No edits. Every prompt to a committee member ends with the no-edits suffix:

    This is analysis only. Do NOT edit, create, or delete any files. Do NOT write code.
    
  • Trust the wait. Do not poll, send hurry-ups, or interrupt. GPT-5.4 can reason 15–30 minutes; Opus does extended thinking. Long waits mean it found something worth thinking about.

  • You are the middleman. Drive plan → implement → review without yielding to the user, except for divergences that need their call.

Phase 1: Plan

Write a problem-level prompt:

  • High-level goal and acceptance criteria
  • Constraints
  • Symptoms (if a bug)
  • What you tried and why it failed
  • Explicit: "do root cause analysis"
  • Explicit: "state assumptions, ask why three levels deep, check whether you're patching a symptom or removing the problem"

Create both agents in parallel via Paseo with [Committee] <task> titles and the same prompt. Wait for both — not just whichever finishes first.

Read both responses. Challenge them — do not accept at face value:

  • "Why does happen? Symptom or cause?"
  • Verify any assumption the plan makes about the code.
  • "What did you considered and reject?"

Send follow-ups until the plan addresses root cause.

Synthesize:

  • Convergence → unified plan.
  • Significant divergence → involve the user.

Confirm the merged plan with both members. Multi-turn until consensus.

Phase 2: Implement

Default: implement yourself. If the user said "delegate", launch one impl agent and pass the merged plan.

The committee stays clean — not involved in implementation.

Phase 3: Review

Send the diff to the committee:

Implementation is done. Review changes against the plan. Flag drift or missing pieces.

Apply feedback yourself, or send to the impl agent. Repeat 2 → 3 until consensus.

After ~10 iterations without convergence, start a fresh committee with the full history of what was tried — the current committee's context may have drifted too far.

ユーザーレビュー (0)

レビューを書く

効果
使いやすさ
ドキュメント
互換性

レビューなし

統計データ

インストール数4.7K
評価4.4 / 5.0
バージョン
更新日2026年10月23日
比較事例1 件

ユーザー評価

4.4(120)
5
37%
4
43%
3
13%
2
5%
1
2%

この Skill を評価

0.0

対応プラットフォーム

🤖claude-code

タイムライン

作成2026年6月13日
最終更新2026年10月23日
🎁 Agent 知識カード
アンケート