paseo-committee
此技能通过组建由两个高推理能力智能体组成的委员会,专门用于进行根本原因分析并制定详细计划。当用户在复杂问题中陷入困境、循环往复、视野受限或面临艰难的规划挑战时,该 Skill 能提供全新的视角和解决方案,有效打破僵局,确保问题得到彻底解决。
npx skills add https://github.com/getpaseo/paseo --skill paseo-committeeBefore / After 效果对比
1 组用户在复杂问题中陷入困境,难以找到根本原因,规划过程反复受阻,团队成员可能陷入思维定势,导致效率低下和决策失误。
此技能通过引入两个高推理智能体进行独立分析和协作,能快速识别根本原因,提供多角度解决方案,显著提升决策质量和问题解决效率。
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.
用户评价 (0)
发表评价
暂无评价
统计数据
用户评分
为此 Skill 评分