CtrlK
BlogDocsLog inGet started
Tessl Logo

scienceworld-room-explorer

Performs an initial survey of a room to identify all visible objects, containers, devices, and their states using the 'look around' action. Use this skill when you first enter a new location, need to refresh your understanding of the environment, or must identify available resources before planning a sequence of actions. Returns a detailed observation that serves as foundational context for subsequent tasks.

69

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

77%

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

A clear, actionable single-purpose skill body with a concrete worked example and an unambiguous core action. Its weaknesses are mild redundancy between the Purpose and When-to-Use sections and a reference file that is present but not linked from the body.

Suggestions

Link references/action_primer.md from the "Integration with Other Skills" section (e.g. "See [action_primer.md](references/action_primer.md) for follow-up object, device, and navigation actions") so the bundle is clearly signaled and one level deep.

Merge or trim the "Purpose" section so it does not restate the frontmatter description and overlap the "When to Use" list — fold its non-redundant content into the existing sections.

Optionally move the inline follow-up action examples (`pick up`, `connect`, `use`, `examine OBJ`) to the primer reference to keep the overview lean.

DimensionReasoningScore

Conciseness

The body is mostly efficient and does not over-explain known concepts, but the "Purpose" section restates the frontmatter description and overlaps with "When to Use" ("critical first step for any task requiring object interaction" vs. the numbered triggers), so it could be tightened.

2 / 3

Actionability

For an instruction-only skill it gives concrete, executable guidance — the single core action (`look around`) is stated unambiguously, the Output Processing is a concrete parsing checklist, and the Example shows copy-paste-ready commands (`teleport to kitchen`, `look around`) with a realistic parsed inventory.

3 / 3

Workflow Clarity

This is a simple single-action skill and the action is unambiguous ("Execute the `look around` action. This is the only action required for this skill."), followed by a clear parse-into-inventory sequence; no destructive or batch operation requires validation checkpoints, so the simple-skill allowance yields a 3.

3 / 3

Progressive Disclosure

The body is organized into clear sections, but a bundle file (references/action_primer.md) exists and is never signaled or linked from SKILL.md, while the body inlines follow-up actions (`pick up`, `connect`, `use`, `examine OBJ`) that the reference covers in detail — matching the "references present but not clearly signaled" anchor rather than a 3.

2 / 3

Total

10

/

12

Passed

Description

90%

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 description that clearly states capability, purpose, and explicit triggers with a distinct niche. Its only notable weakness is second-person voice in the trigger clause, which costs it the top specificity score.

Suggestions

Rewrite the trigger clause in third person or bare imperative to avoid the second-person penalty, e.g. "Use when first entering a new location, refreshing environmental understanding, or identifying available resources before planning actions."

DimensionReasoningScore

Specificity

The description lists concrete elements ("identify all visible objects, containers, devices, and their states using the 'look around' action"), which approaches a 3, but the trigger clause uses second person ("Use this skill when you first enter a new location", "your understanding"), triggering the voice penalty that reduces specificity by 1.

2 / 3

Completeness

It explicitly answers what ("Performs an initial survey of a room to identify… using the 'look around' action") and when (explicit "Use this skill when…" clause with multiple triggers), matching the both-what-and-when anchor.

3 / 3

Trigger Term Quality

Natural trigger phrases are well covered ("first enter a new location", "refresh your understanding of the environment", "identify available resources", "planning a sequence of actions") — situations an agent would genuinely encounter when needing this skill.

3 / 3

Distinctiveness Conflict Risk

It occupies a clear niche (room survey in the ScienceWorld environment) with distinct triggers tied to entering/refreshing locations, making conflict with other skills unlikely.

3 / 3

Total

11

/

12

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
zjunlp/SkillNet
Reviewed

Table of Contents

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.