scienceworld-object-selector

Use when the agent needs to choose a specific object from multiple candidates in the environment based on task criteria such as object type (non-living thing, electrical component, container), properties, or category. This skill surveys visible objects with "look around", evaluates each against the task requirements, selects the most suitable candidate, and signals intent with "focus on [OBJECT]".

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

88%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 well-structured, actionable skill body with concrete commands and complete worked examples. The main gap is the unreferenced object_properties.md bundle file, which should be linked from the body for clear navigation.

Suggestions

Link references/object_properties.md from the body (e.g., in Key Principles or a References section) so the classification reference is discoverable from SKILL.md.

Tighten the "When to Use" bullets to avoid restating the frontmatter description's trigger phrasing.

Consider noting in the workflow when to consult object_properties.md during the evaluate step.

Dimension	Reasoning	Score
Conciseness	Largely lean and efficient with no padding about what ScienceWorld is, but the "When to Use" bullets mildly restate the frontmatter trigger and could be trimmed; fits 'minor instances of over-explanation'.	4 / 5
Actionability	Provides fully executable, copy-ready commands (`look around`, `focus on [OBJECT]`, `move ... to ...`, `examine [OBJECT]`) and two complete worked input/output examples covering common cases.	5 / 5
Workflow Clarity	A clear five-step sequence (survey, evaluate, select, signal, execute) with a verification checkpoint ("Verify if uncertain -- Use examine [OBJECT]"); appropriate for a simple, non-destructive selection skill.	5 / 5
Progressive Disclosure	Well-organized sections (Purpose, When to Use, Workflow, Examples, Key Principles), but the bundled references/object_properties.md is never linked from the body, leaving a one-level-deep reference unsignaled.	4 / 5
	Total	18 / 20 Passed

Description

92%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.

A strong, third-person description that concretely states what the skill does and when to use it with ScienceWorld-specific trigger phrases. Minor room to broaden trigger-term synonyms, but otherwise highly specific and distinctive.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "surveys visible objects with \"look around\"", "evaluates each against the task requirements", "selects the most suitable candidate", "signals intent with \"focus on [OBJECT]\"" — giving comprehensive coverage of what the skill does.	5 / 5
Completeness	Explicitly answers both what (surveys, evaluates, selects, signals) and when ("Use when the agent needs to choose a specific object from multiple candidates in the environment based on task criteria such as...") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural task phrases like "choose a specific object from multiple candidates" and the criteria types ("non-living thing", "electrical component", "container") plus "focus on", but a few common variations or synonyms are absent.	4 / 5
Distinctiveness Conflict Risk	Targets a clear niche (ScienceWorld object selection) with distinct triggers ("look around", "focus on [OBJECT]", object-type criteria), making conflict with other skills minimal.	5 / 5
	Total	19 / 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-object-selector/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.