scienceworld-target-identifier
Analyzes room observations to identify objects matching a given target description (e.g., 'living thing'). Triggered after exploring a room when the…
它会碰到什么
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: Target Object Identifier
Purpose
This skill enables you to systematically locate objects in the ScienceWorld environment that match a specific target description (e.g., "living thing", "container", "electrical device"). It transforms the raw observation text from look around into a structured list of candidate objects for your current task.
When to Use
- Trigger Condition: Immediately after executing
look aroundin any room. - Input Required: The full observation text from
look aroundAND the target description from your task. - Output: A prioritized list of matching objects with their locations and properties.
Execution Workflow
Step 1: Parse Observation
Extract all observable items from the room description. Pay special attention to:
- Objects listed after "Here you see:"
- Objects in containers (marked with "containing" or "On the X is:")
- Substances (marked as "a substance called")
- Living vs. non-living distinctions
Step 2: Apply Target Filter
Use the bundled classification script to filter objects based on the target description:
- For "living thing": Include animals, plants, eggs, and biological organisms
- For specific categories: Match against known object taxonomies
- For generic descriptions: Use semantic similarity matching
Step 3: Prioritize Candidates
Rank candidates by:
- Accessibility: Objects not in closed containers first
- Proximity: Objects in current room before other locations
- Task Relevance: Objects matching secondary task criteria (e.g., "easy to transport")
Step 4: Generate Action Plan
For each high-priority candidate:
- Note its exact name as it appears in observations
- Determine if
pick up,focus on, or other preliminary action is needed - Plan path to target location if specified in task
Key Considerations
- Exact Object Names: Use the exact phrasing from observations (e.g., "turtle egg" not "egg turtle")
- Container States: All containers are open per environment rules
- Teleportation: You can instantly move between rooms when searching
- Multiple Matches: If multiple objects match, select based on task context (e.g., choose less mobile items for transport tasks)
Error Handling
- If no matches found: Teleport to another room and repeat
- If ambiguous matches: Use
examine OBJfor clarification - If classification uncertain: Check reference taxonomy in bundled resources
Example Application
Task: "Find a living thing and move it to the blue box in bathroom"
look aroundin current room- Run this skill with target="living thing"
- Receive list: ["baby wolf", "turtle egg", "crocodile egg"]
- Select "turtle egg" (easier to transport)
focus on turtle egg→pick up turtle egg→teleport to bathroom→move turtle egg to blue box
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。
它属于哪个仓库
experiments/src/skills/scienceworld/scienceworld-target-identifier/SKILL.md同一个仓库里的其他技能
- alfworld-appliance-navigator
- alfworld-appliance-preparer
- alfworld-clean-object
- alfworld-device-operator
- alfworld-environment-scanner
- alfworld-goal-interpreter
- alfworld-heat-object-with-appliance
- alfworld-inventory-management
- alfworld-locate-target-object
- alfworld-location-navigator
- alfworld-navigation-planner
- alfworld-object-cooler