P

paseo-committee

by @getpaseov
4.4(120)

This skill forms a committee of two high-reasoning AI agents specifically designed for root cause analysis and detailed plan generation. It is invaluable when users are stuck in complex problems, experiencing repetitive loops, tunnel-visioning, or confronting difficult planning challenges. By providing fresh perspectives and alternative solutions, this skill effectively breaks impasses and ensures that problems are thoroughly addressed, leading to more robust and innovative outcomes.

multi-agentroot-cause-analysisplanningcollaborationproblem-solvingGitHub
Installation
npx skills add https://github.com/getpaseo/paseo --skill paseo-committee
compare_arrows

Before / After Comparison

1 组
Before

Users often get stuck in complex problems, struggling to identify root causes, and planning processes are repeatedly hindered. Teams may fall into fixed mindsets, leading to low efficiency and poor decision-making.

After

This skill, by introducing two high-reasoning agents for independent analysis and collaboration, can quickly identify root causes and provide multi-faceted solutions, significantly improving decision quality and problem-solving efficiency.

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.

User Reviews (0)

Write a Review

Effect
Usability
Docs
Compatibility

No reviews yet

Statistics

Installs4.7K
Rating4.4 / 5.0
Version
Updated2026年10月23日
Comparisons1

User Rating

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

Rate this Skill

0.0

Compatible Platforms

🤖claude-code

Timeline

Created2026年6月13日
Last Updated2026年10月23日
🎁 Agent Knowledge Cards
Survey