scienceworld-environment-scanner

This skill performs an initial observation of the current location to identify available objects, containers, and connections to other rooms. Use this when starting a new task in ScienceWorld to gather situational awareness, especially when the agent needs to understand its surroundings before taking action. It outputs a detailed room description, listing visible items and accessible doors.

Quality

76%

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

Fix and improve this skill with Tessl

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

Quality

Content

77%

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

The body is lean and clearly sequences a simple single-action workflow, but it is held back by an empty 'Example Output Format' section and a references file that is never linked from the main skill.

Suggestions

Fill in the '## Example Output Format' section with a concrete sample of the structured output (Current Room / Visible Objects & Substances / Accessible Doors / Initial Assessment) to make guidance copy-paste ready.

Add a clearly signaled one-level reference to references/action_primer.md (e.g., 'See [action_primer.md](references/action_primer.md) for post-scan actions') so the bundle is discoverable rather than orphaned.

Dimension	Reasoning	Score
Conciseness	The body is short and tight, assuming Claude's competence without explaining concepts it already knows; the only mild padding ('This is the primary and mandatory step of this skill. It provides the foundational observation of the room.') is minor, so it earns the lean/efficient level-3 anchor.	3 / 3
Actionability	It names one concrete command (`look around`) and a structured output template, but the '## Example Output Format' section is a heading with no example content, leaving the promised concrete example missing — a key detail gap that caps it at 2 rather than 3.	2 / 3
Workflow Clarity	This is a simple single-action skill and the action is unambiguous and mandatory ('Always begin by using the `look around` action'), followed by a clearly sequenced interpretation structure; per the simple-skills note this can score 3, and there are no destructive/batch operations requiring validation.	3 / 3
Progressive Disclosure	The body is well-organized into clear sections, but a bundle file (references/action_primer.md) exists and is never referenced or linked from the body, so the reference is present but not signaled — matching the level-2 anchor rather than the well-signaled level-3 case.	2 / 3
	Total	10 / 12 Passed

Description

75%

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 well-structured with explicit 'what' and 'when' guidance tied to a clearly distinct ScienceWorld niche, but its action list and trigger phrasing are somewhat abstract rather than comprehensive and natural.

Suggestions

Tighten the action list into more distinct, concrete verbs (e.g., 'Scan a room with `look around`, then enumerate visible objects, containers, and exits') to push specificity toward 3.

Add more natural trigger phrasings a user or agent would actually say (e.g., 'when you arrive in a new room', 'to see what's around you') alongside 'situational awareness'.

Dimension	Reasoning	Score
Specificity	It names the domain and several concrete actions ("identify available objects, containers, and connections to other rooms", "outputs a detailed room description, listing visible items and accessible doors"), but these are mostly variants of a single observe-and-describe operation rather than a comprehensive set of distinct actions, so it stops short of a 3.	2 / 3
Completeness	It clearly answers both what (performs an initial observation to identify objects, containers, and connections and outputs a room description) and when ("Use this when starting a new task in ScienceWorld... when the agent needs to understand its surroundings before taking action") with explicit triggers, matching the level-3 anchor.	3 / 3
Trigger Term Quality	It includes a 'Use this when...' clause with relevant triggers ("starting a new task in ScienceWorld", "understand its surroundings", "gather situational awareness"), but the terms are somewhat abstract and miss common natural variations a user/agent might phrase, landing at 2 rather than 3.	2 / 3
Distinctiveness Conflict Risk	It is scoped to a specific simulator (ScienceWorld) and a specific scanning action, giving it a clear niche with distinct triggers unlikely to conflict with unrelated skills, matching the level-3 anchor; it is not the generic 'level 2' case.	3 / 3
	Total	10 / 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-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.