This skill scans the current environment observation to identify the presence and location of a target object needed for a task. It should be triggered when the agent's goal requires an object that is not currently in the agent's inventory, and the observation does not explicitly state where the object is. The skill analyzes the textual observation to find receptacles that likely contain the target, based on common sense or domain knowledge (e.g., a 'dishsponge' might be on a 'cart'), and output
SkillScore100Maintained
Automatic
◆AI Engineer pack
Last verified 8/18/2026
What it changes
Passed 22 of 22 test cases with the skill, and 21 of 22 without it.
Without skill95%
With skill100%
Checks it passed that the model alone missed
Outputs the action command go to towelbar 1
1 fixed21 passed either way0 still failing0 broke
Pass-rate lift
+5 pp
Tokens
+43%
Agent turns
0%
Response time
-16%
Model gemini-3.6-flashMeasured 8/18/2026v122 of 22 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
A test case the skill fixed. Same model, same prompt, with and without the skill.
Prompt
Goal: find a cloth. Inventory: empty. Observation: You see towelbar 1, cabinet 1, countertop 1. You decide to inspect towelbar 1 first. What exact ALFWorld command should be issued?
What was checked, without and with the skill
Checked
Without skill
With skill
Outputs the action command go to towelbar 1
Missed
Passed
case-09 · gemini-3.6-flash · 8/18/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md18 linessingle file
Skill: Object Locator for ALFWorld
When to Use
Trigger this skill when:
Your goal requires a specific object
The object is not in your inventory
The current observation does not explicitly state the object's location
Core Logic
Parse Observation: Extract all mentioned receptacles from the environment description
Analyze Likelihood: Use common-sense reasoning to rank receptacles where the target object is most likely to be found
Output Action: Generate a navigation action to the most promising receptacle
Quick Reference
For detailed object-receptacle mappings, see references/object_mappings.md
For the core location algorithm, see scripts/locate_object.py