scienceworld-target-locator

This skill determines the most likely location for a target object based on domain knowledge and environmental clues. Use when the agent needs to find a specific item (like an animal) but it is not in the current room. It analyzes the environment description and suggests a room to teleport to for further investigation.

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

96%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A tight, highly actionable single-purpose skill with a clear sequenced workflow and an explicit verification loop. The only notable gap is that the bundled reference file is not linked from the body, slightly weakening progressive disclosure.

Suggestions

Link to references/target_location_heuristics.md from the heuristic step so the fuller mapping is discoverable and the inline table is not duplicative.

Consider noting the reference's expanded object-type list (e.g., art supplies, books, metals) so the body table signals it is a summary.

Dimension	Reasoning	Score
Conciseness	Lean and efficient with no padding or explanation of concepts Claude already knows; the heuristic table and example flow each earn their place.	5 / 5
Actionability	Provides a concrete object-type-to-room table and the exact executable commands (`teleport to <ROOM>`, `look around`), copy-paste ready for the common cases.	5 / 5
Workflow Clarity	Clear 4-step sequence with an explicit verify checkpoint ('look around to verify the target is present. If not, try the next likely room') that serves as a feedback loop for error recovery.	5 / 5
Progressive Disclosure	Well-organized sections for a simple skill, but the body inlines a heuristic table that duplicates the existing references/target_location_heuristics.md without linking to it, leaving the reference unsignaled.	4 / 5
	Total	19 / 20 Passed

Description

78%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is clear and well-structured with an explicit trigger clause, making it strong on completeness and trigger quality. Specificity is good but not exhaustive, and the framing carries minor overlap risk with broad search tasks.

Suggestions

Broaden the concrete action list to mention object-type classification and the fallback/iterate behavior, improving specificity.

Add a synonym or two for the trigger (e.g., 'locate', 'track down') to widen natural-term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain and a couple concrete actions ('analyzes the environment description and suggests a room to teleport to'), but the action set is not comprehensive — it omits the classify-and-iterate behavior described in the body.	3 / 5
Completeness	Clearly states what it does ('determines the most likely location... analyzes the environment description and suggests a room to teleport to') and an explicit 'Use when...' trigger with a concrete scenario, answering both what and when.	5 / 5
Trigger Term Quality	Includes a natural 'Use when the agent needs to find a specific item (like an animal) but it is not in the current room' trigger with a concrete example, covering common variations well but lacking synonyms or file extensions.	4 / 5
Distinctiveness Conflict Risk	The ScienceWorld-target-location niche is mostly distinct with clear triggers, though the generic 'find a specific item' framing could marginally overlap with general search skills.	4 / 5
	Total	16 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: zjunlp/SkillNet
Path: experiments/src/skills/scienceworld/scienceworld-target-locator/SKILL.md
Commit: 076c6df

Reviewed: 6 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.