alfworld-object-retriever

This skill picks up a target object from a specified receptacle after the object has been visually confirmed. Use this skill when the agent has located an object in a receptacle and needs to acquire it. It requires the object and source receptacle as inputs and results in the object being added to the agent's inventory.

Quality

63%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./experiments/src/skills/alfworld/alfworld-object-retriever/SKILL.md

Quality

Content

43%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.

The body is concise and well-sectioned but critically incomplete: it announces a 'Core Action Sequence' and then stops before stating the action. The existing trajectory reference is also never linked from the body. The skill is currently not executable as written.

Suggestions

Complete the 'Core Action Sequence' with the concrete action to execute (e.g. the exact `take <obj> from <recep>` command) so the skill is actionable rather than trailing off.

Add a verification/confirmation checkpoint referencing the expected success observation (e.g. 'You pick up the {obj} from the {recep}') to sequence the workflow with a feedback loop.

Link the existing references/trajectory_example.md from the body (e.g. under an 'Example' section) so the bundled reference is clearly signaled rather than orphaned.

Dimension	Reasoning	Score
Conciseness	The body is lean with no padding or over-explanation of concepts Claude already knows ('Visual Confirmation', 'Proximity' prerequisites are terse). It is efficient rather than fully tight because the document trails off mid-instruction, so a couple of tokens do not yet 'earn their place', keeping it at the 4-anchor rather than 5.	4 / 5
Actionability	The body declares 'Execute the following action precisely:' but provides no action afterward — the core executable step is missing. This matches the 2-anchor ('high-level hints but missing the specific steps to execute'); it is above 1 because prerequisites give some concrete framing, but below 3 since there is no executable code or command.	2 / 5
Workflow Clarity	A rough sequence exists (Prerequisites, then Core Action Sequence) but the action sequence is a dangling colon with no defined step and no validation/confirmation checkpoint. This fits the 2-anchor ('rough sequence present but many gaps; steps poorly defined') rather than 3, which would require listed steps with only validation gaps.	2 / 5
Progressive Disclosure	Section headers (Instructions, Prerequisites, Core Action Sequence) give some structure, and a bundle file exists at references/trajectory_example.md. Per the rubric's bundle-structure guidance, that reference is present but never signaled or linked from the body, matching the 3-anchor ('references present but not clearly signaled').	3 / 5
	Total	11 / 20 Passed

Description

83%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.

The description is strong: it states concrete capabilities with explicit inputs and outputs, provides a clear 'Use when' trigger, and occupies a distinct niche. Its only limitation is the single-task scope and slight term overlap with related ALFWorld skills.

Dimension	Reasoning	Score
Specificity	Quotes concrete actions ('picks up a target object from a specified receptacle', 'results in the object being added to the agent's inventory') and explicit inputs ('requires the object and source receptacle as inputs'). It lists several specific, concrete facets but the skill is a single atomic operation, so coverage is just short of the 5-anchor's 'multiple specific concrete actions; comprehensive'.	4 / 5
Completeness	Explicitly answers 'what' ('picks up a target object... added to the agent's inventory') and 'when' ('Use this skill when the agent has located an object in a receptacle and needs to acquire it') with concrete trigger phrases, matching the 5-anchor. Not below: a weak/implied 'when' would be a 4, but here the trigger is explicit.	5 / 5
Trigger Term Quality	Contains a natural trigger clause ('Use this skill when the agent has located an object in a receptacle and needs to acquire it') with relevant keywords (object, receptacle, acquire, inventory). Good coverage but ALFWorld-specific jargon and a few common synonyms are missing, fitting the 4-anchor rather than 5.	4 / 5
Distinctiveness Conflict Risk	Scoped to a clear ALFWorld niche ('target object from a specified receptacle after... visually confirmed') with distinct triggers. Minor overlap risk with sibling skills (e.g. placing) on shared terms 'object'/'receptacle', so it sits at the 4-anchor rather than the 5-anchor's 'minimal conflict risk'.	4 / 5
	Total	17 / 20 Passed

Validation

100%

Warnings & errors only

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
Path: experiments/src/skills/alfworld/alfworld-object-retriever/SKILL.md
Commit: cce11c3

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

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.