Paseo委员会技能：AI代理协作解决复杂技术问题的根本原因分析与规划

paseo-committee by getpaseo/paseo

212 周安装量

645 GitHub Stars

GitHub

安装命令

npx skills add https://github.com/getpaseo/paseo --skill paseo-committee

AI/机器学习软件工程自动化

🇨🇳中文介绍

委员会技能

你正在组建一个委员会，以跳出当前问题并获得新的视角。

用户的附加上下文： $ARGUMENTS

先决条件

首先加载 Paseo 技能 —— 它包含了所有代理命令的 CLI 参考和等待指南。

什么是委员会

两个代理 —— Opus 4.6 (--thinking on) 和 GPT 5.4 (--thinking medium) —— 并行启动以规划解决方案。全新的上下文，没有实现包袱，进行正确的根本原因分析。

它们在规划完成后会保持活动状态，以便进行第 3 阶段的审查 —— 它们只掌握计划，因此能发现实施过程中的偏差。

目的是退一步思考，而不是固执己见。 委员会可能会提出完全不同的方法。

你的角色

你驱动整个生命周期：规划 → 实施 → 审查。你是用户和委员会之间的中间人。在循环完成之前，不要将控制权交还给用户。如果用户需要对分歧进行权衡，请询问他们 —— 但不要停止流程。

无需焦虑

一旦你调用 paseo wait，就信任等待。 不要轮询日志、过早读取输出、发送催促消息、打断深度分析，或者因为耗时过长而放弃。

GPT 5.4 可以推理 15–30 分钟。Opus 会进行扩展思考。长时间的等待意味着代理发现了值得思考的问题。让它完成。

如果 CLI 有错误，用户会告诉你。

禁止编辑后缀

发送给委员会成员的每个提示 —— 初始、后续或审查 —— 必须以此后缀结尾。如果你不这样做，它们将开始编辑代码。

广告位招租

在这里展示您的产品或服务

触达数万 AI 开发者，精准高效

联系我们

第 1 阶段：获取计划

描述 整体问题 ，而不仅仅是直接症状：

高层目标和验收标准
约束条件
症状（如果是错误）
你尝试过什么以及失败的原因
明确要求进行根本原因分析

prompt="我们正在尝试 [高层目标]。约束条件：[X, Y, Z]。验收标准：[A, B, C]。

我们一直卡在这里。以下是我们尝试过的方法以及失败的原因：
- [方法 1] —— 失败，因为 [原因]
- [方法 2] —— 部分有效，但 [问题]
请跳出这些尝试。进行根本原因分析 —— 解决方案可能根本不是针对 [直接症状]，可能是结构性的。

使用深入思考的方法：陈述你的假设，对每个假设至少问 3 个层次的“为什么”，并检查你是在修补症状还是在消除问题。正确的方法是什么？

$NO_EDITS"

向两者发送相同的提示，使用 [Committee] 前缀进行标识：

opus_id=$(paseo run -d --mode bypass --model opus --thinking on --name "[Committee] Task description" "$prompt" -q)
gpt_id=$(paseo run -d --mode full-access --provider codex --model gpt-5.4 --thinking medium --name "[Committee] Task description" "$prompt" -q)

等待两个代理 —— 不仅仅是第一个完成的。

paseo wait "$opus_id"
paseo wait "$gpt_id"

paseo logs "$opus_id"
paseo logs "$gpt_id"

不要轻易接受输出。 使用 深入思考 框架来挑战他们的输出。在综合之前：

问 2-3 个层次的“为什么”。 “修复 X 因为 Y 坏了” —— 为什么 Y 坏了？Y 是根本原因还是后果？
挑战假设。 如果计划对代码做出了某些假设，让代理验证它。
症状与原因。 “我们是在修复后果还是原因？”
探讨替代方案。 “你考虑并拒绝了哪些方案？”

paseo send "$opus_id" "你说 [X]。为什么 [底层问题] 会首先发生？我们是在修补症状吗？ $NO_EDITS"

paseo wait "$opus_id"
paseo logs "$opus_id"

不断推进，直到计划解决了根本原因。

意见一致 → 合并成统一计划。
存在重大分歧 → 让用户参与进来。

将合并后的计划发回以进行确认。如果需要，可以进行多轮对话 —— 继续直到达成共识。

paseo send "$opus_id" "合并计划：[plan]。有什么顾虑吗？ $NO_EDITS"
paseo send "$gpt_id" "合并计划：[plan]。有什么顾虑吗？ $NO_EDITS"

第 2 阶段：实施

你自己实施计划 —— 除非用户明确说 “委托” ，在这种情况下，启动一个实施者：

impl_id=$(paseo run -d --mode full-access --provider codex --name "[Impl] Task description" "端到端地实施以下计划。[plan]" -q)
paseo wait "$impl_id"

委员会代理保持“干净”状态 —— 不参与实施。

第 3 阶段：审查

将变更发送给委员会进行审查。他们以计划为基准，捕捉偏差。

review_prompt="实施已完成。根据计划审查变更。标记偏差或缺失的部分。 $NO_EDITS"

paseo send "$opus_id" "$review_prompt"
paseo send "$gpt_id" "$review_prompt"

paseo wait "$opus_id"
paseo wait "$gpt_id"

paseo logs "$opus_id"
paseo logs "$gpt_id"

将委员会的反馈发送给实施者（或自行应用）。重复第 2 阶段 → 第 3 阶段，直到委员会确认实施符合计划。

在大约 10 次迭代后仍未达成一致，则启动一个新的委员会，并提供所有尝试过的完整上下文 —— 当前委员会的上下文可能已经偏离太远。

🇺🇸English

Committee Skill

You are forming a committee to step back from the current problem and get fresh perspective.

User's additional context: $ARGUMENTS

Prerequisites

Load the Paseo skill first — it contains the CLI reference for all agent commands and waiting guidelines.

What Is a Committee

Two agents — Opus 4.6 (--thinking on) and GPT 5.4 (--thinking medium) — launched in parallel to plan a solution. Fresh context, no implementation baggage, proper root cause analysis.

They stay alive after planning for Phase 3 review — they hold only the plan, so they catch implementation drift.

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

Your Role

You drive the full lifecycle: plan → implement → review. You are a middleman between the user and the committee. Do not yield back to the user until the cycle is complete. If the user needs to weigh in on a divergence, ask them — but don't stop the process.

No Anxiety

Once you callpaseo wait, trust the wait. Do not poll logs, read output early, send hurry-up messages, interrupt deep analysis, or give up because it's taking long.

GPT 5.4 can reason for 15–30 minutes. Opus does extended thinking. Long waits mean the agent found something worth thinking about. Let it finish.

If the CLI has a bug, the user will tell you.

No-Edits Suffix

Every prompt to a committee member — initial, follow-up, or review — must end with this suffix. They will start editing code if you don't.

NO_EDITS="This is analysis only. Do NOT edit, create, or delete any files. Do NOT write code."

All example prompts below include $NO_EDITS — always expand it.

Phase 1: Get a Plan

Write the prompt

Describe the overall problem , not just the immediate symptom:

High-level goal and acceptance criteria
Constraints
Symptoms (if a bug)
What you've tried and why it failed
Explicitly ask for root cause analysis

prompt="We're trying to [high-level goal]. Constraints: [X, Y, Z]. Acceptance criteria: [A, B, C].

We've been stuck on this. Here's what we've tried and why it didn't work:
- [approach 1] — failed because [reason]
- [approach 2] — partially worked but [issue]
Step back from these attempts. Do root cause analysis — the fix might not be for [immediate symptom] at all, it might be structural.

Use the think-harder approach: state your assumptions, ask why at least 3 levels deep for each, and check whether you're patching a symptom or removing the problem. What's the right approach?

$NO_EDITS"

Launch both members

Same prompt to both, [Committee] prefix for identification:

opus_id=$(paseo run -d --mode bypass --model opus --thinking on --name "[Committee] Task description" "$prompt" -q)
gpt_id=$(paseo run -d --mode full-access --provider codex --model gpt-5.4 --thinking medium --name "[Committee] Task description" "$prompt" -q)

Wait for both

Wait for both agents — not just the first one that finishes.

paseo wait "$opus_id"
paseo wait "$gpt_id"

Read and challenge

paseo logs "$opus_id"
paseo logs "$gpt_id"

Do not accept output at face value. Use the think-harder framework to challenge their output. Before synthesizing:

Ask "why" 2–3 levels deep. "Fix X because Y is broken" — why is Y broken? Is Y a root cause or a consequence?
Challenge assumptions. If the plan assumes something about the code, make the agent verify it.
Symptom vs cause. "Are we fixing the consequence or the cause?"
Probe alternatives. "What did you consider and reject?"

paseo send "$opus_id" "You said [X]. Why does [underlying thing] happen in the first place? Are we patching a symptom? $NO_EDITS"

paseo wait "$opus_id"
paseo logs "$opus_id"

Keep pushing until the plan addresses the root cause.

Synthesize and confirm

Convergence → merge into unified plan.
Significant divergence → involve the user.

Send the merged plan back for confirmation. Multi-turn if needed — keep going until consensus.

paseo send "$opus_id" "Merged plan: [plan]. Concerns? $NO_EDITS"
paseo send "$gpt_id" "Merged plan: [plan]. Concerns? $NO_EDITS"

Phase 2: Implement

Implement the plan yourself — unless the user said "delegate" , in which case launch an implementer:

impl_id=$(paseo run -d --mode full-access --provider codex --name "[Impl] Task description" "Implement the following plan end-to-end. [plan]" -q)
paseo wait "$impl_id"

Committee agents stay clean — not involved in implementation.

Phase 3: Review

Send the committee the changes for review. They anchor against the plan and catch drift.

review_prompt="Implementation is done. Review changes against the plan. Flag drift or missing pieces. $NO_EDITS"

paseo send "$opus_id" "$review_prompt"
paseo send "$gpt_id" "$review_prompt"

paseo wait "$opus_id"
paseo wait "$gpt_id"

paseo logs "$opus_id"
paseo logs "$gpt_id"

Iterate

Send committee feedback to the implementer (or apply yourself). Repeat Phase 2 → 3 until the committee confirms the implementation matches the plan.

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

Weekly Installs

126

Repository

getpaseo/paseo

GitHub Stars

283

First Seen

9 days ago

Security Audits

Gen Agent Trust HubPass SocketWarn SnykPass

Installed on

openclaw126

claude-code126

github-copilot126

codex126

kimi-cli126

gemini-cli126

AI Elements：基于shadcn/ui的AI原生应用组件库，快速构建对话界面

67,500 周安装