跳到主要内容
知仓学习社ZHICANG

alfworld-locate-target-object

Navigates to a suspected location and identifies a target object. Use when your goal requires finding a specific object (e.g., "potato", "plate") an…

不碰外部(只输出文字)无严重或高危命中zjunlp/SkillNet

它会碰到什么

扫了多少2 个文本文件,4 KB
它会碰到什么不碰外部(只输出文字)
命中总数0 处
命中统计严重 0 · 高 0 · 中 0 · 低 0

这一栏是扫描器报的事实,不是结论。命中多不等于有毒(安全工具、规则库、示例脚本本来就会包含危险写法),命中少也不等于干净。它和你手上的凭据、文件、网络有什么关系,需要你自己看。

技能内容

Skill: Locate Target Object

Purpose

Use this skill when your goal requires a specific object and you need to find it. The skill directs you to a likely receptacle, inspects it, and confirms if the target is present.

Core Workflow

  1. Identify Target & Suspected Location: Determine the object you need and the most logical place to find it (e.g., food in the fridge, utensils in a drawer).
  2. Navigate: Go to the suspected receptacle.
  3. Inspect: If the receptacle is closed, open it.
  4. Locate: Visually scan the contents for the target object.
  5. Report: Output the object's location if found, or note its absence.

Instructions

Follow this sequence of actions and reasoning.

Thought: I need to find a <target_object>. The most likely place for it is the <suspected_receptacle>.

Action: go to <suspected_receptacle>

Observation: [You arrive at the receptacle. It may be open or closed.]

Thought: I am at the <suspected_receptacle>. To see inside, I must open it.

Action: open <suspected_receptacle>

Observation: [The receptacle opens, revealing its contents.]

Thought: The <suspected_receptacle> is open. I will now look for the <target_object> among its contents.

  • If the object is visible: I have located the <target_object> in the <suspected_receptacle>. My location task is complete.
  • If the object is not visible: The <target_object> is not in the <suspected_receptacle>. I must consider the next most likely location.

Key Principles

  • Contextual Guessing: Use common sense to guess the initial search location (e.g., fridge for perishables, cabinet for dry goods).
  • Sequential Access: You must go to a location before you can open it.
  • Visual Confirmation: Only trust the Observation after opening a receptacle to confirm an object's presence or absence.

Example

Scenario: You need to find a potato for a heating task.

Thought: I need to find a potato. Potatoes are commonly stored in the fridge.
Action: go to fridge 1
Observation: The fridge 1 is closed.
Action: open fridge 1
Observation: You open the fridge 1. The fridge 1 is open. In it, you see a potato 1, a lettuce 2.

Result: The potato has been located in fridge 1. You can now take potato 1 from fridge 1 and proceed.

Next Steps

After successfully locating the object, you will typically need to take it or interact with it, which is outside the scope of this skill. If the object is not found, trigger this skill again with a new suspected location.

想直接用这个技能?

本站把开放许可(MIT / Apache 等)的技能按仓库打包整理到网盘,点一下转存到你自己的网盘,不用一个个从 GitHub 拉。许可未声明的技能只给原始仓库链接,不打包。