Agent Skills
› zjunlp/SkillNet
› scienceworld-material-classifier
scienceworld-material-classifier
GitHub当直接测试材料属性失败或不可用时，通过逻辑推理和常识判断材料性质（如导电性），完成分类任务。
Trigger Scenarios
直接实验测试无效
测试设备不可用
需要基于环境线索进行材料分类
Install
npx skills add zjunlp/SkillNet --skill scienceworld-material-classifier -g -y
SKILL.md
Frontmatter
{
"name": "scienceworld-material-classifier",
"description": "This skill makes a determination about a material's property (e.g., conductivity) based on environmental cues or domain knowledge when direct testing fails. Trigger it when experimental actions are invalid or unavailable, requiring a logical inference. It uses observed object properties and common-sense reasoning to classify the material and decide its final disposition."
}
Material Classification Skill
When to Use
Activate when direct experimental testing of a material property (conductivity, magnetism, etc.) fails or equipment is unavailable, and you need to classify the material by inference to complete a sorting task.
Procedure
focus on <OBJECT>— identify the target and note its material composition.- Attempt direct testing if equipment exists (e.g.,
connect <OBJECT> terminal 1 to <WIRE> terminal 2). - If testing fails, infer the property from the object's material. Consult
references/material_properties.mdfor lookup. move <OBJECT> to <CONTAINER>— place in the appropriate classification container.look at <CONTAINER>— verify the object was placed correctly.
Example
Task: Classify a glass jar for electrical conductivity when the circuit test is unavailable.
focus on glass jarconnect glass jar terminal 1 to yellow wire terminal 2— action fails (invalid connection).- Inference: glass is an electrical insulator → non-conductive.
move glass jar to orange boxlook at orange box— observation: "containing a glass jar" — classification complete.
Version History
- 7bb9a48 Current 2026-07-25 11:53
