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

80%

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

Fix and improve this skill with Tessl

tessl review fix ./experiments/src/skills/alfworld/alfworld-environment-scanner/SKILL.md

Quality

Content

75%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 is well-structured, concise, and actionable for a single-purpose instruction skill, with a clear workflow and concrete output format. The main gap is an orphaned reference bundle file that the body never points to.

Suggestions

Either link references/alfworld_actions_guide.md from the body (e.g., a 'See [alfworld_actions_guide.md] for the full action vocabulary' line) or remove it if unused, so the bundle structure is navigable.

Replace the subjective 'Choose the most logical first receptacle' with an explicit selection rule or priority order (e.g., prefer large central surfaces, then nearest) to make the terminal action unambiguous.

Drop the 'Primary Objective' section or merge it into the workflow, since it restates the frontmatter description and adds tokens without new information.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and organized into labeled sections; the receptacle/object definitions are domain-specific rather than general knowledge Claude already has, so they earn their place. Not a 5 because the Primary Objective restates the description and the example thought could be trimmed.	4 / 5
Actionability	Gives concrete, actionable guidance for an instruction-only skill: naming convention ('armchair 2'), output format ('Scan Complete. Receptacles: [list]. Objects: [list].'), a worked example, and a single terminal 'go to <receptacle>' action. Not a 5 because the choice of first receptacle is left to subjective judgment ('most logical') with no decision rule.	4 / 5
Workflow Clarity	A clear sequenced workflow (Trigger -> Parse & Extract -> Categorize -> Output Structured Mental Map) plus execution rules (Single Action, No Looping, Integration). No destructive/batch validation cap applies; not a 5 because the final receptacle selection lacks an explicit checkpoint or selection rule.	4 / 5
Progressive Disclosure	Well-organized sections for a short single-purpose skill, which the simple-skill exception would allow to score 5; however a bundle file exists at references/alfworld_actions_guide.md yet is never referenced or linked from the body, a minor navigation gap that holds it at 4.	4 / 5
	Total	16 / 20 Passed

Description

85%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 specific, complete, and well-scoped to the ALFWorld niche, clearly stating both what the skill does and when to use it in third-person voice. It could broaden its trigger-term synonyms but is otherwise strong.

Dimension	Reasoning	Score
Specificity	Names the ALFWorld domain and several concrete actions ('Performs an initial scan', 'identify all visible objects and receptacles', 'Processes raw observation text into a structured list of entities, categorizing them as objects or receptacles'); not a 5 because the action set is narrow and centered on a single scan operation.	4 / 5
Completeness	Explicitly answers both 'what' (scan, identify objects/receptacles, process raw observation text into structured entities, categorize) and 'when' ('Use when you first enter an environment and need to build a mental map for task planning') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural trigger phrases a user would say ('Use when you first enter an environment and need to build a mental map for task planning') plus domain terms; not a 5 because it lacks synonyms or common variations beyond 'enter an environment' and 'build a mental map'.	4 / 5
Distinctiveness Conflict Risk	Scoped to a clear niche ('initial scan of the ALFWorld environment') with distinct triggers unlikely to fire for unrelated skills, so conflict risk is minimal.	5 / 5
	Total	18 / 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-environment-scanner/SKILL.md
Commit: cce11c3

Reviewed: 2 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.