CtrlK
BlogDocsLog inGet started
Tessl Logo

scienceworld-container-inspector

Inspects the contents of a container or device using the 'look at' action. Use this skill when you need to verify what is inside a container (e.g., checking if lead is in the blast furnace), monitor the state of contents (e.g., solid vs. liquid phase changes), or confirm that a placement or process step succeeded. Returns a detailed list of contents and their states for process monitoring.

72

Quality

87%

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

82%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.

A well-structured, actionable body that documents a single game action with concrete examples and error handling. Main gaps are minor verbosity in interpretation prose and an orphaned, incomplete reference file.

Suggestions

Either link references/container_inspection_examples.md from the body (e.g., under an Examples section) or remove it, and complete its truncated content so the reference is usable.

Trim interpretive prose such as the 'This confirms the heating process was successful...' line to keep the body lean.

Add an explicit validation checkpoint in the Integration sequence (e.g., 'Confirm desired state via look at before proceeding to use').

DimensionReasoningScore

Conciseness

Mostly efficient and focused on the game-specific API Claude does not already know, with minor interpretive padding such as 'This confirms the heating process was successful and the lead has melted' that could be trimmed.

4 / 5

Actionability

Provides a concrete executable command (`look at <CONTAINER_NAME>`), a real trajectory example with full observation, a concrete integration sequence, and specific error-handling commands — copy-paste ready and covering common cases.

5 / 5

Workflow Clarity

Clear integration sequence (move → look → activate → look → use) with error-recovery guidance, but explicit validation checkpoints within the larger workflow are only implicit; the single-action core is unambiguous.

4 / 5

Progressive Disclosure

Body is under 50 lines and well-organized into clear sections (When to Use, Core Instruction, Expected Output, Example, Integration, Error Handling), but the bundled references/container_inspection_examples.md is orphaned — not linked from the body — and appears truncated/incomplete.

4 / 5

Total

17

/

20

Passed

Description

92%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.

A strong description: third-person voice, explicit what-and-when structure, concrete actions, and distinct domain triggers. Minor room to broaden natural trigger-term synonyms.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Inspects the contents', 'verify what is inside', 'monitor the state of contents', 'confirm that a placement or process step succeeded', 'Returns a detailed list of contents and their states' — giving comprehensive coverage of the skill's capabilities.

5 / 5

Completeness

Explicitly states both what ('Inspects the contents... Returns a detailed list of contents and their states') and when ('Use this skill when you need to verify what is inside..., monitor the state..., or confirm that a placement or process step succeeded') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Good keyword coverage with natural domain terms ('look at', container, blast furnace, lead, state changes, placement) and concrete trigger examples, but a few natural phrasing variations a user might say are not enumerated.

4 / 5

Distinctiveness Conflict Risk

Targets a clear niche — inspecting ScienceWorld containers/devices via the specific 'look at' action — with distinct triggers and minimal overlap risk with other skills.

5 / 5

Total

19

/

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.