# Make Plan

For external plan request scenarios, guides the Agent to request a clear, actionable...

- Repository: https://github.com/agentscope-ai/QwenPaw (37135 stars)
- Category: AI and agents
- License: Apache-2.0
- Last updated: 2026-10-30
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add agentscope-ai/QwenPaw --skill make_plan -g -a claude-code -y`
Codex: `npx skills add agentscope-ai/QwenPaw --skill make_plan -g -a codex -y`
Cursor: `npx skills add agentscope-ai/QwenPaw --skill make_plan -g -a cursor -y`
Gemini CLI: `npx skills add agentscope-ai/QwenPaw --skill make_plan -g -a gemini-cli -y`

## Description

For external plan request scenarios, guides the Agent to request a clear, actionable, step-by-step plan from a stronger Agent via list_agents and chat_with_agent, emphasizing that the plan is executed by the requester, not by the consulted Agent.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# Make Plan

Use this Skill when you need to make an **external plan request** to a stronger Agent.

The goal of this Skill is not to outsource a task, but rather to:
- Request a plan from a stronger Agent
- The plan must consist of **clear, actionable steps**
- **You execute the plan yourself**
- Do not ask the consulted Agent to execute the task directly

How to invoke:
- Use `list_agents()` to check available Agents
- Use `chat_with_agent(...)` to request the stronger Agent to "make a plan"
- In `text`, explicitly include the prompt: **only provide a step-by-step executable plan, do not execute**
- To supplement or refine the original plan in a follow-up, pass `session_id`

Recommended invocation skeleton:

```text
list_agents()

chat_with_agent(
  to_agent="<stronger_agent>",
  text="[Agent <auto> requesting] Please help me create an execution plan for the following task. You do not need to execute the task -- just output clear, actionable steps in order.",
)
```

## Core Rules

This Skill handles one thing only:
1. Find a stronger Agent
2. Request that Agent to output an execution plan
3. Require the plan to be step-by-step, actionable, and in sequential order
4. You execute the plan yourself rather than asking the other Agent to do it for you

If what you truly need is a "plan", use this Skill.
If what you need is a final answer, architectural judgment, review conclusion, or direct execution, do not misuse this Skill.

## Applicable Scenarios

The following scenarios are suitable for making an external plan request:
- The task requires multi-step decomposition
- Steps have dependencies between them
- A clear sequence, checkpoints, or verification points are needed
- Multiple modules, files, systems, or roles are involved
- The user explicitly requests a plan before execution
- You want to obtain a more complete and reliable execution path first

## Do Not Use This Way

The rest: https://github.com/agentscope-ai/QwenPaw/blob/HEAD/src/qwenpaw/agents/skills/make_plan-en/SKILL.md