Paseo任务交接技能：AI智能体无缝任务转移与上下文传递指南

paseo-handoff by getpaseo/paseo

122 周安装量

283 GitHub Stars

GitHub

安装命令

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

AI/机器学习自动化开发运维

🇨🇳中文介绍

任务交接技能

你正在将当前任务交接给另一个智能体。你的工作是编写一份全面的交接提示，并通过 Paseo CLI 启动该智能体。

用户参数： $ARGUMENTS

先决条件

首先加载 Paseo 技能 —— 它包含了所有智能体命令的 CLI 参考。

什么是任务交接

任务交接将你当前的任务——包括所有上下文、决策、失败的尝试和约束——转移给一个新的智能体，由它来完成该任务。交接提示是最重要的部分：接收任务的智能体从零上下文开始，因此它所需的一切信息都必须包含在提示中。

解析参数

解析 $ARGUMENTS 以确定：

提供方和模型 —— 交接给谁
工作树 —— 是否在独立的 git 工作树中运行
任务描述 —— 用户提供的任何额外上下文

提供方解析

用户输入	提供方	模型	模式
(无)	`codex`

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

相关 Skills

FlyClaw：零登录航班聚合查询工具，Python实现多源航班信息与价格搜索

4,000,000 周安装

find-skills 技能搜索工具 - Vercel Labs 开源智能体技能包管理器

855,400 周安装

Vercel React 最佳实践指南 | 58条Next.js性能优化规则与代码重构

281,000 周安装

agent-browser 浏览器自动化工具 - Vercel Labs 命令行网页操作与测试

155,300 周安装

如果用户提到"在工作树中"或"worktree"，则添加 --worktree 参数，并附带一个从任务描述派生的简短描述性分支名称。工作树需要一个 --base 分支 —— 使用工作目录中的当前分支（运行 git branch --show-current 来获取它）。

任务描述 —— 需要做什么，使用清晰的祈使句语言
任务限定条件 —— 保留用户请求的语义： * 如果用户要求仅调查不编辑，请说"请勿编辑任何文件" * 如果用户要求修复，请说"实施修复" * 如果用户要求重构，请说"重构"而不是"重写" * 准确传达原始意图
相关文件 —— 列出每个重要的文件路径，并简要说明每个文件的内容
当前状态 —— 到目前为止已完成的工作，哪些有效，哪些无效
已尝试的方法 —— 任何尝试过的方法以及它们失败或被放弃的原因
已做出的决策 —— 你和用户商定的任何事项（设计选择、约束、权衡）
验收标准 —— 智能体如何知道任务已完成
约束条件 —— 智能体不得做的任何事情

## 任务

[清晰、祈使句式的任务描述]

## 上下文

[此任务存在的原因，智能体需要的背景信息]

## 相关文件

- `path/to/file.ts` — [它的作用以及为何重要]
- `path/to/other.ts` — [它的作用以及为何重要]

## 当前状态

[已完成的工作，哪些有效，哪些无效]

## 已尝试的方法

- [方法 1] — [失败/被放弃的原因]
- [方法 2] — [部分成功，但是...]

## 已做出的决策

- [决策 1 — 理由]
- [决策 2 — 理由]

## 验收标准

- [ ] [标准 1]
- [ ] [标准 2]

## 约束条件

- [不要做 X]
- [必须保留 Y]

打印智能体 ID 和用于跟踪进度的命令：

已交接给 [provider] ([model])。智能体 ID: <id> 跟踪进度: paseo logs <id> -f 等待完成: paseo wait <id>
默认情况下不要等待智能体 —— 用户可以选择等待或继续其他操作。
如果用户想要等待，运行 paseo wait <id>，完成后运行 paseo logs <id>。

🇺🇸English

Handoff Skill

You are handing off the current task to another agent. Your job is to write a comprehensive handoff prompt and launch the agent via Paseo CLI.

User's arguments: $ARGUMENTS

Prerequisites

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

What Is a Handoff

A handoff transfers your current task — including all context, decisions, failed attempts, and constraints — to a fresh agent that will carry it to completion. The handoff prompt is the most important part: the receiving agent starts with zero context , so everything it needs must be in the prompt.

Parsing Arguments

Parse $ARGUMENTS to determine:

Provider and model — who to hand off to
Worktree — whether to run in an isolated git worktree
Task description — any additional context the user provided

Provider Resolution

User says	Provider	Model	Mode
(nothing)	`codex`	`gpt-5.4`	`full-access`
`codex`	`codex`	`gpt-5.4`	`full-access`
`claude`	`claude`	`opus`	`bypass`
`opus`	`claude`	`opus`	`bypass`
`sonnet`	`claude`	`sonnet`	`bypass`

Default is Codex with gpt-5.4.

Worktree Resolution

If the user says "in a worktree" or "worktree", add --worktree with a short descriptive branch name derived from the task. Worktrees require a --base branch — use the current branch in the working directory (run git branch --show-current to get it).

Writing the Handoff Prompt

This is the critical step. The receiving agent has zero context about your conversation. The handoff prompt must be a self-contained briefing document.

Must Include

Task description — What needs to be done, in clear imperative language
Task qualifiers — Preserve the semantics of what the user asked for:
- If the user asked to investigate without editing , say "DO NOT edit any files"
- If the user asked to fix , say "implement the fix"
- If the user asked to refactor , say "refactor" not "rewrite"
- Carry forward the exact intent
Relevant files — List every file path that matters, with brief descriptions of what each contains
Current state — What has been done so far, what's working, what's not
What was tried — Any approaches attempted and why they failed or were abandoned
Decisions made — Anything you and the user agreed on (design choices, constraints, trade-offs)
Acceptance criteria — How the agent knows it's done
Constraints — Anything the agent must NOT do

Template

## Task

[Clear, imperative description of what to do]

## Context

[Why this task exists, background the agent needs]

## Relevant Files

- `path/to/file.ts` — [what it does and why it matters]
- `path/to/other.ts` — [what it does and why it matters]

## Current State

[What's been done, what works, what doesn't]

## What Was Tried

- [Approach 1] — [why it failed/was abandoned]
- [Approach 2] — [partial success, but...]

## Decisions

- [Decision 1 — rationale]
- [Decision 2 — rationale]

## Acceptance Criteria

- [ ] [Criterion 1]
- [ ] [Criterion 2]

## Constraints

- [Do not do X]
- [Must preserve Y]

Launching the Agent

Default (Codex, no worktree)

paseo run -d --mode full-access --provider codex --name "[Handoff] Task description" "$prompt"

Claude (Opus, no worktree)

paseo run -d --mode bypass --model opus --name "[Handoff] Task description" "$prompt"

Codex in a worktree

base=$(git branch --show-current)
paseo run -d --mode full-access --provider codex --worktree task-branch-name --base "$base" --name "[Handoff] Task description" "$prompt"

Claude in a worktree

base=$(git branch --show-current)
paseo run -d --mode bypass --model opus --worktree task-branch-name --base "$base" --name "[Handoff] Task description" "$prompt"

After Launch

Print the agent ID and the command to follow along:

Handed off to [provider] ([model]). Agent ID: <id> Follow along: paseo logs <id> -f Wait for completion: paseo wait <id>
Do not wait for the agent by default — the user can choose to wait or move on.
If the user wants to wait, run paseo wait <id> and then paseo logs <id> when done.

Weekly Installs

122

Repository

getpaseo/paseo

GitHub Stars

283

First Seen

9 days ago

Security Audits

Gen Agent Trust HubPass SocketWarn SnykPass

Installed on

mcpjam122

antigravity122

kilo122

replit122

junie122

windsurf122