scienceworld-object-classifier

Moves a tested or examined object into a designated container (e.g., a specific colored box) based on a determined property. Use when you have completed a test or inspection and need to fulfill a classification or sorting subtask. It takes the object and target container as inputs and performs the move action.

Quality

83%

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

77%

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

A lean, actionable body with a clear sequenced workflow and concrete commands. It loses points for redundant restatements of the move command and for shipping a reference file that is never referenced from the body.

Suggestions

Link the existing references/conductivity_test_guide.md from the body (e.g., under Prerequisites or a References section) so the bundle file is discoverable rather than orphaned.

De-duplicate the `move <OBJECT> to <CONTAINER>` command, which currently appears in Core Action, Workflow, and the Example; state it once and reference it.

Trim the Purpose section, which restates the frontmatter description, to improve token efficiency.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and avoids explaining concepts Claude already knows, but the `move <OBJECT> to <CONTAINER>` command is restated in Core Action, Workflow, and the Example, and the Purpose section restates the frontmatter, so it could be tightened rather than earning the 'every token earns its place' top anchor.	2 / 3
Actionability	It provides fully executable, copy-paste-ready commands ("move <OBJECT> to <CONTAINER>", "move metal pot to yellow box", "look around", "drop <OBJECT>") with a concrete worked example, matching the top anchor.	3 / 3
Workflow Clarity	The Workflow gives a clear confirm→move→verify sequence with an explicit verification step ("look at <CONTAINER> to confirm the object is now inside"); for a simple, single-action, non-destructive skill this meets the top anchor per the simple-skills scoring note.	3 / 3
Progressive Disclosure	The body is well organized into sections, but the provided bundle file references/conductivity_test_guide.md is never linked or signaled in the body — it is an orphaned reference — so it does not meet the 'well-signaled one-level-deep references' top anchor.	2 / 3
	Total	10 / 12 Passed

Description

90%

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 concise, third-person description that clearly states both what the skill does and when to use it, with natural trigger terms and low conflict risk. Its only limitation is that it describes a single action rather than multiple capabilities, capping the specificity dimension.

Dimension	Reasoning	Score
Specificity	The description names a single concrete action ("Moves a tested or examined object into a designated container", "performs the move action") with an example ("a specific colored box") and inputs, but it does not list multiple distinct actions, matching the 'names domain and some actions, but not comprehensive' anchor rather than the 'multiple specific concrete actions' level.	2 / 3
Completeness	It explicitly answers both what ("Moves a tested or examined object into a designated container…based on a determined property") and when via an explicit "Use when…" trigger clause, matching the top anchor.	3 / 3
Trigger Term Quality	The "Use when you have completed a test or inspection and need to fulfill a classification or sorting subtask" clause gives good coverage of natural terms (test, inspection, classification, sorting) a user would say in this domain, exceeding the 'some relevant keywords' anchor.	3 / 3
Distinctiveness Conflict Risk	The narrow post-test sorting niche ("a tested or examined object into a designated container…based on a determined property") with distinct triggers is clearly distinguishable and unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 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-object-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.