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

81%

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

82%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 instruction body: concrete commands, a worked example, and edge-case handling with essentially no padding. Remaining gaps are minor — an optional rather than mandatory verification step and an unsignaled related reference file.

Suggestions

Make the verification step mandatory rather than 'Optionally' (e.g., '3. Verify: look at <CONTAINER> and confirm the object is inside; if not, re-check inventory and repeat'), strengthening the feedback loop.

Add a one-line pointer to references/conductivity_test_guide.md for the prerequisite test step, since the guide explicitly names this skill and covers the logic the body assumes.

Trim the redundancy between the Purpose section and the frontmatter description, and collapse the two repeated 'final action only' boundary notes into one.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes competence, but the Purpose section largely repeats the frontmatter description and Important Notes restates the 'after the test only' boundary twice ('Do not use it to perform the initial test' and 'assumes the classification logic... handled by a prior process').	4 / 5
Actionability	Fully executable commands with explicit format ('move <OBJECT> to <CONTAINER>'), a concrete worked example ('move metal pot to yellow box'), the inventory edge case ('drop <OBJECT>'), and the expected verification output ('containing a metal pot') are all provided copy-paste ready.	5 / 5
Workflow Clarity	A clear three-step sequence (confirm environment, execute move, verify) with an inventory pre-check exists, but the verification checkpoint is explicitly marked 'Optionally', leaving a minor validation gap rather than a mandatory feedback step.	4 / 5
Progressive Disclosure	The skill is under 50 lines with well-organized sections that would otherwise merit a 5 under the simple-skill exception, but the bundle contains a directly related reference (conductivity_test_guide.md covering the prerequisite test) that the body never signals, a minor navigation gap.	4 / 5
	Total	17 / 20 Passed

Description

70%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 answers both what and when with an explicit trigger clause and domain-specific language. Its main weaknesses are redundant restatement of the single action (limiting specificity) and missing natural trigger synonyms.

Suggestions

Replace the redundant final sentence ('It takes the object and target container as inputs and performs the move action') with an additional concrete capability or parameter detail, e.g., the exact command form 'move <object> to <container>'.

Broaden trigger coverage with natural synonyms such as 'sort', 'put in the box', or 'after determining a property' to catch more phrasings users would naturally say.

Name the operating environment/domain (e.g., the ScienceWorld-like task setting) to further reduce overlap with generic object-moving skills.

Dimension	Reasoning	Score
Specificity	One concrete action is clearly named ("Moves a tested or examined object into a designated container"), but the closing sentence ("performs the move action") merely restates it rather than adding capability coverage, matching the 1-2-concrete-actions anchor rather than the several-actions anchor.	3 / 5
Completeness	Both an explicit "what" (move a tested object into its designated container) and an explicit "Use when..." trigger are present; the when-clause is concrete, but the what is restated redundantly rather than sharpened, keeping it below the fully concrete anchor 5.	4 / 5
Trigger Term Quality	Natural trigger phrases like "completed a test or inspection", "classification or sorting subtask", and "colored box" are present, but common variations users might say (e.g., "put/place in the box", environment-specific terms) are missing, so it falls just short of comprehensive coverage.	4 / 5
Distinctiveness Conflict Risk	The niche is clear (final sorting action after a completed property test) with distinct triggers, though "moves an object into a container" leaves minor overlap risk with generic object-manipulation or move skills.	4 / 5
	Total	15 / 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-classifier/SKILL.md
Commit: 358ec82

Reviewed: 8 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.