CtrlK
BlogDocsLog inGet started
Tessl Logo

alfworld-appliance-preparer

Prepares a household appliance (microwave, oven, toaster, fridge) for use by ensuring it is in the correct open/closed state. Use when the agent needs to heat, cool, or cook an item and must first open or close the appliance before placing an object inside. Takes an appliance identifier as input and outputs a confirmation that the appliance is ready for the next action.

75

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

85%

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

A compact, actionable instruction skill with a clear sequenced workflow, observation-based validation, and a single well-signaled reference file. Its only weakness is mild redundancy between the Core Logic, Important Considerations, and Example sections.

Suggestions

Merge 'Important Considerations' (State Awareness, Error Handling) into the relevant Core Logic steps rather than restating them, so each point appears once.

Trim the standalone Example section or fold it into Core Logic step 3, since the open-microwave sequence is already illustrated there.

Make the validation checkpoint in 'Confirm Readiness' explicit as a pass/fail gate (e.g., 'Only proceed when the observation confirms the desired state') to strengthen the feedback loop.

DimensionReasoningScore

Conciseness

The body is mostly lean and avoids explaining concepts Claude already knows, but the 'Important Considerations' section largely restates Core Logic (state awareness, error handling) and the worked Example duplicates the open-microwave sequence already illustrated, so it could be tightened.

2 / 3

Actionability

It gives executable alfworld commands (`go to microwave 1`, `open microwave 1`) paired with expected observations and a concrete input/output example; absence of code is not penalized for this instruction-only skill since the guidance is directly actionable.

3 / 3

Workflow Clarity

A clear three-step sequence (Navigate → Check State & Prepare → Confirm Readiness) with an explicit observation-based validation checkpoint and an error-recovery feedback loop ('Nothing happened' → re-check and proceed) for a non-destructive single task.

3 / 3

Progressive Disclosure

Under 50 lines with well-organized sections and a single clearly signaled, one-level-deep reference (`references/trajectory_example.md`, verified to exist) — appropriate split for a skill this size.

3 / 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, third-person description that concretely states the capability, input, and output and pairs them with an explicit 'Use when…' trigger covering heat/cool/cook scenarios. It occupies a distinct niche with little conflict risk.

DimensionReasoningScore

Specificity

Lists concrete appliances (microwave, oven, toaster, fridge) and a specific action (ensuring the correct open/closed state), plus input/output shape — multiple specific concrete actions rather than vague language.

3 / 3

Completeness

It explicitly answers both 'what' (prepares an appliance into the correct open/closed state, taking an appliance identifier and outputting a confirmation) and 'when' via an explicit 'Use when…' trigger, so it does not cap at 2.

3 / 3

Trigger Term Quality

The 'Use when the agent needs to heat, cool, or cook an item and must first open or close the appliance' clause supplies natural trigger terms a user/agent would say, covering the common cases.

3 / 3

Distinctiveness Conflict Risk

The niche is narrow and specific (preparing a named household appliance's open/closed state before a heat/cool/cook action) with distinct triggers, making unintended triggering of other skills unlikely.

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.