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.

71

Quality

89%

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

85%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 concise, highly actionable, well-sequenced instruction body for a simple skill. The main weakness is bundle hygiene: two reference files exist but are never referenced, while overlapping troubleshooting content is duplicated inline.

Suggestions

Link the existing reference files from the body (e.g., under Error Recovery: 'See [troubleshooting.md](references/troubleshooting.md) for detailed failure modes') instead of duplicating their content inline.

Either surface references/trajectory_analysis.md with a one-line pointer (e.g., how this skill was derived) or remove it from the bundle so no orphaned files remain.

Trim the redundancy between Workflow step 3, the Example's Result line, and the Post-Condition section — one statement of the outcome suffices.

DimensionReasoningScore

Conciseness

The body is lean and assumes competence ("Clean an object you are holding using a sinkbasin") with no padding or explanation of known concepts. It misses 5 because the clean-state outcome is restated in three places (Workflow step 3, the Example's Result, and the Post-Condition section) and the Action Format section duplicates the command already shown in the workflow.

4 / 5

Actionability

Fully executable, copy-paste-ready commands throughout: `go to sinkbasin 1`, `clean {object} with sinkbasin 1`, the general format `clean {obj} with {recep}` with a concrete instance, a complete worked Thought/Action/Observation example, and specific error-recovery checks. This matches the anchor for executable guidance covering the common cases.

5 / 5

Workflow Clarity

A simple single-purpose skill with an unambiguous action, satisfying the simple-skill exception. The sequence (navigate → clean → proceed) includes an explicit validation checkpoint ("verify observation confirms 'You clean the {object}'") and an error-recovery feedback loop for the "Nothing happened" failure mode, matching the anchor with explicit validation and error recovery.

5 / 5

Progressive Disclosure

The body itself has clear, well-organized sections, but the bundle contains references/trajectory_analysis.md and references/troubleshooting.md that are never linked or signaled anywhere in the body — the Error Recovery section instead duplicates troubleshooting.md's content inline. This matches the anchor for references present but not clearly signaled with content that should be separate left inline; it is not 4 because the orphaned bundle files are a real navigation gap, not a minor one, and not 2 because the body's own structure is good and nothing is deeply nested.

3 / 5

Total

17

/

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.

A strong description: third person, concise, with an explicit Use-when clause and natural trigger phrases. Minor room to improve specificity by naming the concrete command form and to broaden trigger synonyms.

DimensionReasoningScore

Specificity

Lists several concrete actions — "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 several-specific-actions anchor. It falls short of 5 because "performs the clean action" restates the opening rather than adding a distinct capability, leaving minor gaps in coverage.

4 / 5

Completeness

Explicitly answers both what ("Cleans a specified object using an appropriate cleaning receptacle... Navigates... performs the clean action, and confirms") and when with a concrete "Use when" clause containing literal trigger phrases ("clean potato", "wash apple"). This directly matches the anchor 5 example structure; a missing or weaker trigger clause would place it at 3-4.

5 / 5

Trigger Term Quality

Natural trigger phrases like "clean potato" and "wash apple" capture the two most common synonyms users would say, plus "task requires an object to be in a clean state". Not 5 because other natural variations (e.g., rinse, scrub) and any command-form triggers are absent; not 3 because the quoted example phrases are exactly what a user would say.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (cleaning a held object at a sinkbasin) with distinct trigger phrasing unlikely to fire for sibling skills like heating, cooling, or placing objects. Anchor 4 would require identifiable overlap with closely related skills, and none is evident from the description itself.

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.

Validation — 16 / 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.