Skills

Alfworld Object Locator

Use when the agent needs to find a specific object in ALFWorld that is not currently in...

Install

npx skills add zjunlp/SkillNet --skill alfworld-object-locator -g -a claude-code -y
Repository
zjunlp/SkillNet1.4k
Category
AI and agents
Updated
22d ago
License
MIT
Context cost
Lightabout 792 tokens
Runs scripts
No, instructions only

What it does

Use when the agent needs to find a specific object in ALFWorld that is not currently in inventory and whose location is unknown. This skill parses the environment observation, ranks receptacles by likelihood of containing the target object using common-sense reasoning, and outputs a navigation action to the most promising location.

Skill: Object Locator for ALFWorld

When to Use

Trigger this skill when:

  1. Your goal requires a specific object (e.g., knife, cellphone, apple)
  2. The object is not in your inventory
  3. The current observation does not explicitly state the object's location

Core Workflow

1. Parse the Environment

Extract all visible receptacles from the observation text. Typical ALFWorld receptacles include:

  • Surfaces: countertop, desk, dresser, bed, shelf, sidetable, coffeetable, diningtable
  • Containers: drawer, cabinet, safe, fridge, microwave, garbagecan
  • Appliances: sinkbasin, bathtub, stoveburner, toaster

2. Rank by Likelihood

Use common-sense reasoning to prioritize where the target object is most likely found:

Object TypeHigh-Probability Receptacles
Kitchen items (knife, spatula, pan)countertop, drawer, diningtable, stoveburner
Food (apple, potato, tomato, bread)fridge, countertop, diningtable, microwave
Bathroom items (sponge, cloth, soap)sinkbasin, bathtub, cart, shelf
Electronics (cellphone, laptop, remote)desk, sidetable, dresser, bed, coffeetable
Stationery (pen, pencil, book)desk, shelf, drawer, sidetable
Lighting (candle, desklamp)sidetable, shelf, desk, dresser

3. Navigate and Search

For each candidate receptacle (in priority order):

  1. go to {receptacle}
  2. Read the observation, does it mention the target object?
    • YES: take {object} from {receptacle}, object found
    • NO: If the receptacle is closed, open {receptacle} and re-check
    • Still NO: Move to the next candidate receptacle

4. Track Searched Locations

Maintain a list of already-searched receptacles to avoid revisiting them. If all high-probability locations are exhausted, expand the search to remaining receptacles.

Example

Read the whole SKILL.md on GitHub

More in AI and agents