CtrlK
BlogDocsLog inGet started
Tessl Logo

alfworld-receptacle-navigator

Plans and executes movement to a target receptacle within the ALFWorld environment. Use when the agent needs to reach a specific location before interacting with objects there (e.g., go to fridge to cool an item, go to garbagecan to dispose of an item). Takes a receptacle identifier as input, executes the `go to` action, and outputs confirmation of arrival at the destination.

80

Quality

100%

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

100%

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

A tight, well-structured skill body: actionable `go to` guidance with a concrete example, an explicit verification checkpoint plus an error-recovery loop, and a single real one-level reference. It scores at the top anchor on all four dimensions for a simple single-task skill.

DimensionReasoningScore

Conciseness

Lean and well-sectioned with no padding of concepts Claude already knows (no explanation of what ALFWorld or receptacles are); every section earns its place, fitting the 'every token earns its place' anchor rather than the slightly padded score-2 level.

3 / 3

Actionability

Gives a concrete executable action (`go to {target_receptacle}`) plus a complete example trace with a real observation ('You are at fridge 1. On the fridge 1, you see nothing.'), meeting the 'fully executable / specific examples' anchor; as an instruction-only skill, executable guidance substitutes for code.

3 / 3

Workflow Clarity

Numbered steps with an explicit arrival-verification checkpoint and a feedback loop on 'Nothing happened' (consult references, reformulate target), satisfying the 'clear sequence with explicit validation and error-recovery' anchor; the single-action task is unambiguous per the simple-skills note.

3 / 3

Progressive Disclosure

The body is a concise overview with a single, clearly signaled one-level-deep reference to `references/common_receptacles.md`, which exists in the bundle and is not nested further, matching the 'clear overview with well-signaled one-level-deep references' anchor.

3 / 3

Total

12

/

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 well-crafted description: concrete third-person capabilities, natural trigger terms, an explicit 'Use when' clause, and a clearly scoped niche that minimizes conflict risk. It hits the top anchor on every dimension without verbosity.

DimensionReasoningScore

Specificity

Lists multiple concrete actions in third person ('Plans and executes movement', 'Takes a receptacle identifier as input, executes the `go to` action, and outputs confirmation of arrival'), matching the 'lists multiple specific concrete actions' anchor rather than the partial score-2 anchor.

3 / 3

Completeness

Explicitly answers both what (plan/execute movement, parse input, run `go to`, confirm arrival) and when via an explicit 'Use when the agent needs to reach a specific location before interacting with objects there' clause, satisfying the top anchor and avoiding the score-2 cap for a missing 'Use when' trigger.

3 / 3

Trigger Term Quality

Uses natural trigger phrasings a caller would actually say ('go to fridge to cool an item', 'go to garbagecan to dispose of an item', 'reach a specific location'), giving good coverage rather than the sparse score-2 'some relevant keywords' level.

3 / 3

Distinctiveness Conflict Risk

Scoped to a clear ALFWorld niche (receptacle navigation via `go to`) with distinct, domain-specific triggers, making it unlikely to fire for unrelated skills; not the generic score-2 'works with document files' level.

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.