P

paseo-handoff

by @getpaseov
4.4(120)

This skill enables the seamless transfer of the current task and its full context to a new AI agent. It generates a structured, self-contained briefing, ensuring the receiving agent can quickly grasp the task background, attempted approaches, decisions, and constraints, even when starting from scratch. This prevents information loss and enhances multi-agent collaboration efficiency, making it particularly useful for complex workflows requiring task handoffs between different agents.

multi-agent-systemsagent-orchestrationworkflow-automationtask-managementGitHub
Installation
npx skills add https://github.com/getpaseo/paseo --skill paseo-handoff
compare_arrows

Before / After Comparison

1 组
Before

Before this skill, users manually organized and transferred extensive context when switching or introducing new agents, often missing critical details. This led to redundant work or misunderstandings by the new agent, requiring significant time for communication and correction.

After

This Skill automatically generates a structured briefing with all necessary information, allowing the new agent to immediately start work. It significantly reduces manual organization and communication time, improving the accuracy and efficiency of task handoffs.

SKILL.md

Handoff Skill

Transfer the current task — context, decisions, failed attempts, constraints — to a fresh agent. The receiving agent starts with zero context, so the handoff prompt must be a self-contained briefing.

User's arguments: $ARGUMENTS

Prerequisites

Read the paseo skill. Before choosing a provider, read ~/.paseo/orchestration-preferences.json unless the user explicitly named a provider in this request. Do not create the receiving agent until you have read it.

Parsing arguments

  1. Provider — explicit user request first; otherwise resolve from impl preference (or ui if the task is styling-only).
  2. Worktree — "in a worktree" / "worktree" → create a worktree via Paseo with a short branch name derived from the task, based on the current branch.
  3. Task description — anything else the user said.

The handoff prompt

The receiving agent has zero context. Include:

## Task
[Imperative description.]

## Context
[Why this task exists, required context.]

## Relevant files
- `path/to/file.ts` — [what it is and why it matters]

## Current state
[What's done, what works, what doesn't.]

## What was tried
- [Approach] — [why it failed or was abandoned]

## Decisions
- [Decision — rationale]

## Acceptance criteria
- [ ] [Criterion]

## Constraints
- [Must-not / must-preserve]

Preserve task semantics. Investigate-only → "DO NOT edit files." Fix → "implement the fix." Refactor → "refactor, not rewrite." Carry the user's exact intent.

Launch

Create the agent via Paseo with a [Handoff] <task> title, the briefing as initial prompt, detached: true, and cwd set to the worktree path if --worktree. Leave notifyOnFinish omitted unless the user explicitly wants no callback.

Handoff agents are siblings/root agents, not your subagents. They must survive you being archived and must not appear in your subagent track.

Don't wait by default — the user decides whether to follow along or move on. Tell them the agent ID and how to follow along (the paseo skill explains).

User Reviews (0)

Write a Review

Effect
Usability
Docs
Compatibility

No reviews yet

Statistics

Installs4.8K
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