scienceworld-material-classifier

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.

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

100%

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

The content is a well-constructed simple skill: concise, fully actionable with concrete commands and a worked example, a clear sequenced workflow with a verification step, and clean one-level progressive disclosure to a real reference file.

Dimension	Reasoning	Score
Conciseness	The body is lean: a brief 'When to Use' clause and a tight five-step procedure with no concept explanations or padding, assuming Claude's competence throughout.	3 / 3
Actionability	It gives concrete executable game commands (`focus on <OBJECT>`, `connect <OBJECT> terminal 1 to <WIRE> terminal 2`, `move <OBJECT> to <CONTAINER>`, `look at <CONTAINER>`) plus a fully worked example with real values, making the guidance copy-paste ready.	3 / 3
Workflow Clarity	The five steps are clearly sequenced, step 3 contains an explicit conditional fallback ('If testing fails, infer...'), and step 5 provides a verification checkpoint ('verify the object was placed correctly') confirmed in the example by an observation.	3 / 3
Progressive Disclosure	The SKILL.md is a concise overview that signals a single one-level-deep reference ('Consult references/material_properties.md for lookup'), and that referenced file exists in the bundle, keeping navigation shallow and clear.	3 / 3
	Total	12 / 12 Passed

Description

75%

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 clearly states both capability and trigger conditions in third person, with an explicit 'Trigger it when' clause and a distinctive niche. It is held back only by slightly abstract action phrasing and narrow trigger-term coverage.

Suggestions

Tighten action verbs to concrete operations (e.g., 'Infers a material's conductivity or magnetism, classifies it, and routes it to the correct sorting container') to lift specificity.

Broaden trigger terms with natural user phrasings such as 'when a circuit or magnet test is unavailable', 'cannot test the material', or 'sorting task' to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain and several actions ("makes a determination about a material's property", "classify the material", "decide its final disposition"), but the phrasing stays somewhat abstract ("makes a determination", "requiring a logical inference") rather than crisp concrete verbs, so it stops short of the comprehensive multi-action anchor.	2 / 3
Completeness	It explicitly answers both what ("classify the material and decide its final disposition") and when ("Trigger it when experimental actions are invalid or unavailable, requiring a logical inference"), with an explicit trigger clause rather than implied guidance.	3 / 3
Trigger Term Quality	It includes a real trigger clause ("Trigger it when experimental actions are invalid or unavailable") and terms like "conductivity" and "direct testing fails", but coverage is narrow with only one example property and few natural keyword variations a user would actually say.	2 / 3
Distinctiveness Conflict Risk	The inference-when-testing-fails niche for material-property classification is a clear, narrow scope with distinct triggers, making it unlikely to fire for unrelated skills.	3 / 3
	Total	10 / 12 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-material-classifier/SKILL.md
Commit: 7bb9a48

Reviewed: 1 day 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.