scienceworld-room-scanner

This skill performs a 'look around' action to scan and describe the current room's contents, including visible objects, containers, and doors. Use when entering a new room or when the agent needs to locate specific items or assess the environment state. The skill outputs a detailed room description, which is essential for inventory discovery and situational awareness.

Quality

88%

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

92%

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

A tight, actionable, single-purpose skill body that scores well on conciseness, actionability, and workflow clarity. Its one gap is that the bundled reference file is not linked or signaled from the overview.

Suggestions

Add a brief pointer in the body to the bundled reference, e.g. 'See references/action_primer.md for the `look around` observation format and related actions'.

Confirm whether action_primer.md is meant to extend the skill; if so, signal it explicitly so the bundle is reachable from SKILL.md.

Dimension	Reasoning	Score
Conciseness	The body is lean and well-sectioned with no padding or re-explanation of concepts Claude already knows; each section (Purpose, Output Processing, Integration Notes, Example) earns its tokens, matching the 'lean and efficient' anchor.	3 / 3
Actionability	It gives the exact executable command `look around` plus a real parsed example observation, providing copy-paste-ready concrete guidance even without code blocks, fitting the 'fully executable / specific examples' anchor.	3 / 3
Workflow Clarity	This is a simple single-action skill whose single action is unambiguous ('the agent must perform the `look around` action'), which the rubric's simple-skills note allows to score 3; no destructive/batch validation is needed.	3 / 3
Progressive Disclosure	The body is self-contained and well-organized, but the bundled `references/action_primer.md` is never referenced or signaled in the SKILL.md body, leaving a provided reference disconnected from navigation — the 'references present but not clearly signaled' anchor.	2 / 3
	Total	11 / 12 Passed

Description

85%

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 focused, third-person description with an explicit Use-when clause and concrete scan targets. Its main weakness is mildly jargon-heavy trigger phrasing ('situational awareness', 'inventory discovery') that blunts natural-user-term quality.

Suggestions

Swap jargon ('situational awareness', 'inventory discovery') for natural user phrasing such as 'see what's in a room' or 'find items in the current room'.

Add a couple of common variations (e.g., 'look around', 'scan the room', 'see what's here') to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	The description enumerates concrete scan targets ("visible objects, containers, and doors") and specific verbs ("scan and describe", "locate", "assess"), matching the 'lists multiple specific concrete' anchor rather than the vaguer single-domain 2-anchor.	3 / 3
Completeness	It states both what the skill does ("performs a 'look around' action to scan and describe...") and an explicit when ("Use when entering a new room or when the agent needs to locate specific items..."), satisfying the explicit what-and-when anchor.	3 / 3
Trigger Term Quality	It offers relevant triggers ("entering a new room", "locate specific items") but leans toward jargon ("situational awareness", "inventory discovery") rather than natural user phrasing, so it lands at 'some relevant keywords but missing common variations' rather than full coverage.	2 / 3
Distinctiveness Conflict Risk	The ScienceWorld room-scanning niche anchored on the `look around` action is a clear, distinct trigger set unlikely to fire for unrelated skills, fitting the 'clear niche with distinct triggers' anchor.	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-room-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.