CtrlK
BlogDocsLog inGet started
Tessl Logo

alfworld-receptacle-closer

Closes an open receptacle to maintain environment tidiness after inspection. Use when you have finished searching a container (drawer, cabinet, fridge) and no longer need it open. Takes a receptacle identifier as input and outputs confirmation that the receptacle is closed, preventing clutter during multi-step search tasks.

73

Quality

92%

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

88%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 lean, actionable body for a genuinely simple skill: the action format and worked example make it fully executable, and the single-step workflow is unambiguous. The two weaknesses are the slightly padded Key Principle/When to Use sections and the orphaned references/action_primer.md bundle file that the body never points to.

Suggestions

Add a brief pointer to the bundle file, e.g. under Core Instruction: "For the full action syntax and receptacle types, see [action_primer.md](references/action_primer.md)", so the existing reference is discoverable.

Trim the Key Principle section ("Do not overthink it") and condense the When to Use section, which restates the frontmatter description, to save tokens without losing clarity.

Optionally enumerate the receptacle types from action_primer.md (microwave, box, washingmachine) in the body so the agent knows the full range of valid targets.

DimensionReasoningScore

Conciseness

The body is short and mostly earns its tokens (three-step Core Instruction, one concrete example), but "This is a low-cognitive-load, procedural step. Do not overthink it" is coaching fluff, and the When to Use section restates the frontmatter description. Efficient with minor instances that could be trimmed — the 4 anchor, not the 5 anchor's "every token earns its place".

4 / 5

Actionability

The output format is fully executable ("Action: close {recep}") and the Example from Trajectory gives a copy-paste-ready concrete instance ("close drawer 2"). For an instruction-only skill this is specific, complete guidance with the common case covered — the 5 anchor, not the 4 anchor which expects minor gaps.

5 / 5

Workflow Clarity

This is a simple single-task skill and the action is unambiguous: identify the open target, execute close, emit the specified format. Per the simple-skill exception it warrants 5; it is not a destructive or batch operation, so the validation cap does not apply.

5 / 5

Progressive Disclosure

The body is well-organized with clear sections and appropriately short, but the bundle contains references/action_primer.md (with the action syntax and receptacle types) that is never referenced or linked from the body. Scoring against the actual bundle structure, this is a navigation gap — good structure with a minor organization issue, matching the 4 anchor rather than the 5 anchor's well-signaled references.

4 / 5

Total

18

/

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: it explicitly states the action, input, and output, and includes a clear 'Use when...' trigger clause with natural synonym coverage (receptacle, container, drawer, cabinet, fridge). The only weakness is that a few natural receptacle-type keywords are omitted. It comfortably beats all the bad examples and compares well to the good examples.

DimensionReasoningScore

Specificity

"Closes an open receptacle" states the concrete action, and "Takes a receptacle identifier as input and outputs confirmation that the receptacle is closed" explicitly specifies input and output. For a single-action skill this coverage is comprehensive with no gaps, matching the 5 anchor rather than the 4 anchor ("minor gaps in coverage").

5 / 5

Completeness

Both questions are answered explicitly: what ("Closes an open receptacle... outputs confirmation that the receptacle is closed") and when ("Use when you have finished searching a container... and no longer need it open"). This matches the 5 anchor with concrete trigger phrasing; the 4 anchor requires a 'when' that could be more explicit, which is not the case here.

5 / 5

Trigger Term Quality

"receptacle", "container", "drawer, cabinet, fridge", "finished searching", "no longer need it open" give good natural keyword coverage with synonyms, but other common receptacle types (microwave, box, washingmachine) are missing. It sits between the 3 anchor (missing common variations) and the 5 anchor (comprehensive synonyms), noticeably above the midpoint.

4 / 5

Distinctiveness Conflict Risk

The trigger condition (post-inspection cleanup of an open receptacle) carves out a clear niche distinct from opening/searching skills, and the closed/open direction is unambiguous. Minimal conflict risk, matching the 5 anchor rather than the 4 anchor's "minor overlap risk with closely related 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.

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.