CtrlK
BlogDocsLog inGet started
Tessl Logo

alfworld-clean-object

Cleans a specified object using an appropriate cleaning receptacle (e.g., sinkbasin). Use when a task requires an object to be in a clean state (e.g., "clean potato", "wash apple") before proceeding. Navigates to the cleaning location, performs the clean action, and confirms the object is now clean.

72

Quality

88%

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.

The skill body is actionable and workflow-clear for a simple single-task operation, with executable commands and a verification checkpoint. Its main weakness is progressive disclosure: bundled reference files are not linked from the body and are partly duplicated inline, with minor conciseness redundancy in the Post-Condition section.

Suggestions

Replace or augment the inline 'Error Recovery' section with a one-level-deep link such as 'See [troubleshooting.md](references/troubleshooting.md)' to avoid duplicating bundled reference material and improve progressive disclosure.

Link trajectory_analysis.md from the body (e.g., under a 'Background' note) so the existing reference file is discoverable instead of orphaned.

Remove the 'Post-Condition' section or fold its single useful sentence into workflow step 3, since it restates the 'object is now clean' confirmation already given.

DimensionReasoningScore

Conciseness

The body is mostly lean and free of concept explanations Claude already knows, but the 'Post-Condition' section restates workflow step 3 and the inline 'Error Recovery' duplicates the bundled troubleshooting.md reference, so not every token earns its place — landing at 'mostly efficient but could be tightened' rather than the lean anchor at 3.

2 / 3

Actionability

Provides fully executable, copy-paste-ready commands ('go to sinkbasin 1', 'clean potato 1 with sinkbasin 1') plus a complete example with real observation strings, matching the executable-code anchor rather than the pseudocode anchor at 2.

3 / 3

Workflow Clarity

The simple single-task skill has an unambiguous sequence (navigate -> clean, verifying the 'You clean the {object}' observation -> proceed) with an explicit verification checkpoint and error recovery, which the rubric permits to score 3 for clear simple skills.

3 / 3

Progressive Disclosure

Sections are well organized, but bundle reference files (troubleshooting.md, trajectory_analysis.md) exist yet are never signaled or linked from the body, and inline content (Error Recovery) duplicates a reference file — matching the 'references present but not clearly signaled; content that should be separate is inline' anchor rather than the one-level-deep well-signaled anchor at 3.

2 / 3

Total

10

/

12

Passed

Description

100%

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 concise, third-person, and fully answers both what and when with natural trigger phrases. It is among the strongest reference examples and shows no over-claims or fluff.

DimensionReasoningScore

Specificity

Names multiple concrete actions in third person — 'Cleans a specified object using an appropriate cleaning receptacle', 'Navigates to the cleaning location, performs the clean action, and confirms the object is now clean' — matching the multi-action anchor rather than the single-domain anchor at 2.

3 / 3

Completeness

Explicitly answers both what (cleans an object via a cleaning receptacle) and when ('Use when a task requires an object to be in a clean state ... before proceeding'), matching the explicit-trigger anchor rather than the what-only anchor at 2.

3 / 3

Trigger Term Quality

Provides natural user phrases 'clean potato' and 'wash apple' plus a 'Use when a task requires an object to be in a clean state' clause, giving good coverage of terms a user would say rather than only generic or jargon keywords at 1 or 2.

3 / 3

Distinctiveness Conflict Risk

Targets a clear niche (cleaning a held object at a sinkbasin) with distinct triggers unlikely to fire for unrelated skills, rather than the overlapping-domain anchors at 1 or 2.

3 / 3

Total

12

/

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.