CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

60

Quality

75%

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

Fix and improve this skill with Tessl

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

Quality

Content

55%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 admirably concise and well-sectioned, but it is fatally incomplete: it promises 'the following action' and then stops, so the agent never receives the actual command to execute, and the bundled trajectory example that contains the concrete action format is never referenced. The prerequisites are the only genuinely actionable part.

Suggestions

Complete the 'Core Action Sequence' section with the exact action template, e.g. 'take {obj} from {recep}' using the IDs from the confirming observation, so the skill is executable as written.

Add a brief success-confirmation step (e.g., expect an observation like 'You pick up the {obj} from the {recep}') so the agent can verify the object entered its inventory.

Link the bundled reference from the body (e.g., 'See [trajectory_example.md](references/trajectory_example.md) for a full worked example') so the existing file is discoverable rather than orphaned.

DimensionReasoningScore

Conciseness

The body is lean and assumes competence: prerequisites are stated in two terse numbered items with a concrete observation template ("On the {recep}, you see a {obj}..."), and there is no padding or explanation of concepts Claude already knows. Every line earns its place, matching the anchor 5 example of minimal, well-organized instruction; a 4 would require over-explanation that is simply absent.

5 / 5

Actionability

The 'Core Action Sequence' section says 'Execute the following action precisely:' and then ends — the actual action (e.g., 'take {obj} from {recep}') is never given in the body, so there are no executable instructions at all. It is above anchor 1 only because the prerequisites include one concrete observation format and the proximity requirement, but the specific step to execute is missing entirely.

2 / 5

Workflow Clarity

A rough sequence is implied (visual confirmation, proximity, then an action) but the central step — the action itself — is absent, leaving the workflow poorly defined with a major gap. The simple-skill exception (score 5 for a single unambiguous action) cannot apply because the single action is not stated; it also lacks any confirmation step that the pickup succeeded.

2 / 5

Progressive Disclosure

The body is short and cleanly sectioned (Instructions / Prerequisites / Core Action Sequence), which for a sub-50-line simple skill would merit a 5. However, the bundle contains references/trajectory_example.md, which is never mentioned or linked from the body, so the one bundled reference is orphaned rather than clearly signaled — a minor organization gap that maps to anchor 4.

4 / 5

Total

13

/

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.

A strong description that clearly states what the skill does, its inputs and effects, and an explicit 'Use when...' trigger. Its main weaknesses are that it covers only one action (inherent to the skill, but limiting specificity breadth) and omits the literal 'take ... from ...' command phrasing that would serve as the most natural trigger term.

DimensionReasoningScore

Specificity

The description specifies the concrete action ("picks up a target object from a specified receptacle after the object has been visually confirmed") plus its inputs ("requires the object and source receptacle as inputs") and effect ("results in the object being added to the agent's inventory"). It is not a 5 because the skill has only one action, so it does not list multiple specific capabilities; it is above 3 because the single action is fully specified with inputs, outputs, and precondition rather than just named.

4 / 5

Completeness

It explicitly answers both questions: what ("picks up a target object from a specified receptacle... results in the object being 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"). The 'when' clause is explicit and concrete with trigger phrasing, matching the anchor 5 example structure; anchor 4 would require the 'when' to be less explicit, which it is not.

5 / 5

Trigger Term Quality

It includes natural domain phrases a user or agent would say: "picks up", "target object", "receptacle", "located an object in a receptacle", "acquire", "inventory". It misses the literal ALFWorld command verb "take ... from ..." and object-type synonyms, so it falls just short of the comprehensive anchor 5.

4 / 5

Distinctiveness Conflict Risk

The niche is clear (visually-confirmed object pickup into inventory) with distinct vocabulary like "receptacle" and "agent's inventory", giving minimal conflict risk with unrelated skills. It is not a 5 because it could overlap with closely related embodied-agent manipulation skills (putting, moving, or searching for objects) that share the object/receptacle vocabulary.

4 / 5

Total

17

/

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.