alfworld-object-locator

Use when the agent needs to find a specific object in ALFWorld that is not currently in inventory and whose location is unknown. This skill parses the environment observation, ranks receptacles by likelihood of containing the target object using common-sense reasoning, and outputs a navigation action to the most promising location.

Quality

91%

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

85%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.

The body delivers highly actionable, well-sequenced guidance with concrete command examples and error recovery, and it is admirably free of padding. Its main structural weakness is that the two bundled reference files are never mentioned or linked, so detailed mappings and usage examples are duplicated inline instead of being progressively disclosed.

Suggestions

Add explicit, well-signaled pointers to the bundle files (e.g., "**Full object-receptacle mappings**: See [references/object_mappings.md](references/object_mappings.md)" and "**More usage examples**: See [references/skill_usage_examples.md](references/skill_usage_examples.md)") so the bundle is discoverable.

Trim the inline likelihood table to a compact summary of the ranking heuristic and delegate the per-object mappings to references/object_mappings.md, removing the duplication and saving tokens.

Sync the inline examples with references/skill_usage_examples.md (e.g., cover the "no clear match / object not found" case shown there) or point to it instead of restating examples.

Dimension	Reasoning	Score
Conciseness	The body is lean with no explanations of concepts Claude already knows, but the inline object-to-receptacle table substantially duplicates the more detailed mappings in references/object_mappings.md. Matches anchor 4 (minor trimmable content) rather than 5, where every token would be unique to the body.	4 / 5
Actionability	Concrete, copy-paste-ready commands ("go to {receptacle}", "take {object} from {receptacle}", "open {receptacle}") backed by two full dialogue traces covering both a first-hit and a miss-then-recover case. Fully executable guidance matching the top anchor.	5 / 5
Workflow Clarity	A clear four-step sequence (parse → rank → navigate/search → track) with explicit checkpoints: re-reading observations, opening closed receptacles and re-checking, expanding the search on exhaustion, plus a dedicated Error Handling section with recovery guidance. Matches anchor 5's feedback loops and validation steps.	5 / 5
Progressive Disclosure	The body is well-sectioned, but it never references the actual bundle files — references/object_mappings.md and references/skill_usage_examples.md are orphaned while equivalent mapping and example content is inlined. Fits anchor 3 (content that should be separate is inline, references not signaled) better than 4, which requires references to be mostly clearly signaled.	3 / 5
	Total	17 / 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.

The description is a strong example: it pairs an explicit, condition-rich "Use when" trigger with a concrete three-part statement of what the skill does, all in third person and without padding. The only improvement space is broader synonym coverage in the trigger phrasing.

Dimension	Reasoning	Score
Specificity	"parses the environment observation", "ranks receptacles by likelihood of containing the target object", and "outputs a navigation action" are multiple concrete actions that comprehensively cover the skill's workflow. It exceeds anchor 4 because there are no minor gaps — the actions span the entire locate-and-navigate pipeline.	5 / 5
Completeness	An explicit "Use when the agent needs to find a specific object in ALFWorld that is not currently in inventory and whose location is unknown" clause answers 'when' with concrete conditions, and the three-action capability statement answers 'what'. Clearly matches the top anchor rather than anchor 4, where 'when' would be less specific.	5 / 5
Trigger Term Quality	"find a specific object", "ALFWorld", "not currently in inventory", and "location is unknown" are natural phrases for this need. Falls short of anchor 5 because common synonyms such as "locate", "search for", or "where is" are absent.	4 / 5
Distinctiveness Conflict Risk	The trigger is scoped to a single named environment (ALFWorld) and a narrow task (finding an unlocated object), giving it a clear niche with distinct triggers and minimal conflict risk with other skills.	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/alfworld/alfworld-object-locator/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.