Agent Skills
› zjunlp/SkillNet
› alfworld-navigation-planner
alfworld-navigation-planner
GitHub用于在家庭环境中规划智能体在不同容器间的移动路径，以系统性搜索目标对象。输入当前位置和目标容器，输出下一步移动指令，支持自适应路径调整。
触发场景
需要在环境中移动以寻找特定物品
需要规划从一个位置到另一个容器的导航路径
安装
npx skills add zjunlp/SkillNet --skill alfworld-navigation-planner -g -y
SKILL.md
Frontmatter
{
"name": "alfworld-navigation-planner",
"description": "Plans a path to move the agent between receptacles to search for target objects. Use this when you need to traverse the environment to reach a specific location or systematically explore multiple areas. It takes the current location and destination receptacle as input, and outputs the next 'go to' action to approach the target."
}
Instructions
Use this skill to navigate between receptacles (e.g., bed, desk, drawer) in a household environment to locate objects. The core logic is handled by the bundled script.
Input/Output Format
- Input: Provide the agent's current location and the target receptacle.
- Output: The skill will return the next
go to {recep}action to execute.
How to Use
- Identify your goal. Determine which receptacle you need to search (e.g.,
desk 1to find adesklamp). - Call the skill. Pass your current location and the target receptacle.
- Execute the action. Perform the
go toaction returned by the skill. - Observe and repeat. After moving, observe the new location. If the target object is not found, use this skill again to plan movement to the next most promising receptacle.
Key Principles
- Systematic Search: Move efficiently between likely receptacles instead of random exploration.
- Adaptive Planning: If an action fails ("Nothing happened"), the script's logic helps choose an alternative path.
- Context Preservation: Always note your current location after each move for the next planning step.
Example Thought Process:
Thought: I need to find a desklamp. The
desk 1is a likely location. I am currently atbed 1. Action: Usealfworld-navigation-plannerwith current locationbed 1and targetdesk 1. Result:go to desk 1
版本历史
- 7bb9a48 当前 2026-07-25 11:51
