CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

66

Quality

79%

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

Fix and improve this skill with Tessl

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

Quality

Content

71%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 content gives clear, lean, actionable guidance for a simple single-action skill, but is undermined by an empty 'Example Output Format' section and a bundled reference file that is never linked from the body.

Suggestions

Fill in the '## Example Output Format' section with a concrete sample of the structured room description so the expected output is unambiguous.

Link to references/action_primer.md from the body (e.g., 'See action_primer.md for other common actions') so the bundled reference is discoverable and one level deep.

Trim redundant phrasing such as 'This is the primary and mandatory step of this skill. It provides the foundational observation of the room.' to tighten the Core Action step.

DimensionReasoningScore

Conciseness

The body is lean and does not explain concepts Claude already knows; minor padding ('This is the primary and mandatory step... It provides the foundational observation of the room') could be trimmed, keeping it just below the 5 anchor.

4 / 5

Actionability

Gives a concrete executable command ('Always begin by using the `look around` action') and a concrete output structure (Current Room, Visible Objects, Accessible Doors, Initial Assessment), but the empty 'Example Output Format' section leaves a gap in copy-ready examples.

4 / 5

Workflow Clarity

The single-action workflow (execute `look around` then structure the output) is clearly sequenced for a simple skill, but the empty example section makes the expected output format ambiguous, holding it below 5.

4 / 5

Progressive Disclosure

Sections are reasonably organized, but the provided bundle file (references/action_primer.md) is never referenced or signaled from the body, and the 'Example Output Format' section is empty, leaving references unclear.

3 / 5

Total

15

/

20

Passed

Description

87%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 strong: it clearly states what the skill does and when to use it with concrete, natural trigger phrases, and occupies a distinct niche. Minor specificity gains are possible by enumerating a few more concrete output categories.

DimensionReasoningScore

Specificity

Names the domain and several concrete actions ('identify available objects, containers, and connections to other rooms', 'listing visible items and accessible doors'), giving comprehensive coverage for this narrow task; slightly below the 5 anchor's richness of distinct listed actions.

4 / 5

Completeness

Explicitly states both what it does ('performs an initial observation... to identify... objects, containers, and connections') and when to use it with concrete triggers ('Use this when starting a new task in ScienceWorld... before taking action'), matching the 5 anchor.

5 / 5

Trigger Term Quality

Includes natural trigger phrases a user would say ('starting a new task in ScienceWorld', 'gather situational awareness', 'understand its surroundings'); good coverage with a few natural variations missing.

4 / 5

Distinctiveness Conflict Risk

Targets a clear niche (ScienceWorld environment scanning) with distinct triggers and minimal overlap risk with other skills.

5 / 5

Total

18

/

20

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.