CtrlK
BlogDocsLog inGet started
Tessl Logo

alfworld-object-cooler

Cools a held object using an appropriate cooling appliance such as a fridge or freezer. Use when the task requires reducing the temperature of an object (e.g., "cool some pot", "chill the mug") and the agent is already holding the object. Performs the ALFWorld `cool` action and outputs the cooled object ready for subsequent placement or serving steps.

77

Quality

96%

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

92%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A clean, actionable, well-sequenced body for a simple skill, with concrete commands and a validation/feedback loop. Its main gap is progressive disclosure: a useful reference file is bundled but never linked from the body.

Suggestions

Add a one-line pointer to the bundled reference, e.g. under Core Action: 'See [references/action_semantics.md](references/action_semantics.md) for valid receptacles and the full cool/heat action semantics.'

Move the duplicated detail currently inline (e.g., the 'Nothing happened' failure cases and valid-receptacle list) into action_semantics.md and summarize it in the body to avoid drift between the two.

Pull the non-obvious note from the reference ('the fridge does not need to be open') into the Prerequisites section, since it is decision-relevant and not derivable from the body.

DimensionReasoningScore

Conciseness

The body is lean — Purpose, Prerequisites, Core Action, Execution Flow, Example, Next Steps — and assumes Claude's competence without explaining what ALFWorld or a fridge is; the slight restatement between Prerequisites and 'Verify State' is a deliberate validation checkpoint, not padding, so it stays at the 'lean and efficient' anchor.

3 / 3

Actionability

Gives the exact command format 'cool {obj} with {recep}' and a fully concrete worked example 'cool pot 1 with fridge 1' producing the expected observation, which is copy-paste ready within ALFWorld rather than pseudocode.

3 / 3

Workflow Clarity

The Execution Flow is explicitly sequenced (Verify State → Execute → Verify Outcome) with an error-recovery feedback loop ('If the observation is "Nothing happened,"... check the prerequisites or try a different receptacle'); for a simple single-action skill this matches the 'clear sequence with explicit validation steps' anchor.

3 / 3

Progressive Disclosure

The body is well-sectioned but never references the existing bundle file references/action_semantics.md, which holds non-trivial detail (receptacle need not be open, common valid receptacles, related actions) — a signaling gap against the actual bundle structure. It is not level 3 because a one-level-deep reference exists but is not signaled, and not level 1 because internal organization is clear with no nested references.

2 / 3

Total

11

/

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.

A strong, concise description that states the concrete action, scope conditions (held object, cooling appliance), and explicit triggers, all in third person. It distinguishes the skill clearly and would be selected for the right task.

DimensionReasoningScore

Specificity

Names the concrete action ('Performs the ALFWorld `cool` action'), the appliance class ('fridge or freezer'), and the post-state ('outputs the cooled object ready for subsequent placement or serving'); as specific as possible for a single-action skill, fitting the 'concrete actions' anchor rather than the vague 'names domain and some actions' level below.

3 / 3

Completeness

Clearly answers what ('Cools a held object using an appropriate cooling appliance...') and when via an explicit 'Use when...' clause with example triggers, matching the 'both what AND when with explicit triggers' anchor; it is not the level-2 case where 'when' is only implied.

3 / 3

Trigger Term Quality

Includes natural phrasings a task would use — 'cool some pot', 'chill the mug', 'reduce the temperature of an object' — giving good coverage of common variations rather than only technical jargon.

3 / 3

Distinctiveness Conflict Risk

The ALFWorld `cool` action on a held object via a fridge/freezer is a clear niche unlikely to trigger for heating or unrelated skills; third-person voice ('Cools...', 'Performs...') incurs no voice penalty.

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.