alfworld-environment-scanner

Performs an initial scan of the ALFWorld environment to identify all visible objects and receptacles. Use when you first enter an environment and need to build a mental map for task planning. Processes raw observation text into a structured list of entities, categorizing them as objects or receptacles.

Quality

81%

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

62%

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

A well-structured, single-purpose instruction skill with a clear sequenced workflow and concrete output format. Its main weaknesses are an unreferenced bundle file that duplicates guidance already reinvented inline and a couple of under-specified judgment steps.

Suggestions

Link references/alfworld_actions_guide.md from the body (e.g., 'For the full action set, naming conventions, and observation semantics, see [alfworld_actions_guide.md](references/alfworld_actions_guide.md)') instead of restating naming conventions inline.

Tighten conciseness by removing the 'Example from Trajectory' section, which duplicates the Core Workflow, or compress it to a single illustrative observation+action line.

Make receptacle selection more actionable by giving a concrete priority rule (e.g., 'prefer the largest central surface such as diningtable 1 or sofa 1') rather than the vague 'most logical first receptacle'.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and does not over-explain background, but the 'Example from Trajectory' section duplicates the Core Workflow and the full receptacle list example is verbose, so it fits the score-2 'could be tightened' anchor rather than the score-3 'every token earns its place' anchor.	2 / 3
Actionability	Concrete guidance is present — the output format 'Scan Complete. Receptacles: [list]. Objects: [list].', naming convention 'armchair 2', and the single 'go to sofa 1' action — but 'Mentally categorize' and 'Choose the most logical first receptacle' are internal judgment steps rather than a deterministic procedure, fitting the score-2 incomplete-guidance anchor rather than fully copy-paste-ready score 3.	2 / 3
Workflow Clarity	The four numbered Core Workflow steps (Trigger, Parse & Extract, Categorize, Output) plus explicit Execution Rules give a clear sequence, and as a simple single-action skill (culminating in one 'go to' action with no destructive/batch step requiring validation) it meets the score-3 simple-skill allowance rather than the score-2 checkpoint-gap anchor.	3 / 3
Progressive Disclosure	Sections are well organized, but the provided references/alfworld_actions_guide.md — which covers naming conventions and observation semantics directly relevant to parsing — is never linked or signaled in the body, and the body reinvents the naming convention inline, fitting the score-2 'references present but not clearly signaled' anchor rather than the score-3 well-signaled-one-level-deep anchor.	2 / 3
	Total	9 / 12 Passed

Description

100%

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 names concrete actions, includes an explicit 'Use when' trigger, and is tightly scoped to the ALFWorld scanning niche. It avoids vagueness and over-claims while staying concise.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Performs an initial scan... to identify all visible objects and receptacles' and 'Processes raw observation text into a structured list of entities, categorizing them as objects or receptacles' — matching the score-3 anchor of multiple specific concrete actions rather than the domain-only score-2 anchor.	3 / 3
Completeness	Clearly answers both what ('Performs an initial scan... identify all visible objects and receptacles') and when with an explicit 'Use when you first enter an environment and need to build a mental map for task planning' trigger, matching the score-3 anchor and exceeding the score-2 cap where the 'when' is missing or only implied.	3 / 3
Trigger Term Quality	Natural ALFWorld-domain terms a user would say are well covered: 'initial scan', 'environment', 'objects and receptacles', 'build a mental map', 'task planning', 'observation text', matching the score-3 anchor for good coverage of natural terms rather than the partial score-2 anchor.	3 / 3
Distinctiveness Conflict Risk	The ALFWorld-specific niche and 'first enter an environment' trigger make it clearly distinguishable and unlikely to fire for the wrong skill, matching the score-3 clear-niche anchor rather than the overlap-prone score-2 anchor.	3 / 3
	Total	12 / 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/alfworld/alfworld-environment-scanner/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.