CtrlK
BlogDocsLog inGet started
Tessl Logo

alfworld-object-storer

Use when the agent is holding an object and needs to place it into a target receptacle in ALFWorld. This skill checks receptacle suitability, opens closed containers if needed, and executes the `put` command to store the object. It handles both open surfaces (countertops, beds) and closed containers (drawers, cabinets).

71

Quality

89%

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%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.

A lean, highly actionable body with a clear validated workflow and concrete transcripts. The main structural weakness is progressive disclosure: the existing receptacle suitability reference is orphaned — never signaled from SKILL.md — so its heuristics are undiscoverable when the agent needs them most.

Suggestions

In step 2's table (or the "Unsuitable" row), add a pointer such as: "For detailed receptacle suitability heuristics, see [receptacle_suitability_guide.md](references/receptacle_suitability_guide.md)" so the bundled reference is discoverable.

In the Error Handling section's "Receptacle unsuitable" bullet, link the suitability guide before deferring to the object-locator skill, giving the agent a concrete evaluation protocol instead of only a redirect.

Trim the redundancy between the "When to Use" section and the description, and drop the "Agent not at receptacle" error-handling bullet that repeats step 1's navigation instruction, to push conciseness toward a 5.

DimensionReasoningScore

Conciseness

The body is efficient — a state table instead of prose, no explanation of what ALFWorld or receptacles are, and tight command templates. It misses a 5 because of small redundancies: the "When to Use" section reiterates the description, and the Error Handling bullet "Agent not at receptacle: Navigate..." duplicates step 1's "If not at the receptacle, navigate there first".

4 / 5

Actionability

Guidance is fully executable: exact commands (`go to {target_receptacle}`, `open {target_receptacle}`, `put {object_name} in/on {target_receptacle}`, `inventory`) and two complete copy-paste-ready transcripts with real observations covering the two main cases (closed container, open surface). Error handling is keyed to a concrete observation string ("Nothing happened").

5 / 5

Workflow Clarity

The four-step sequence (validate prerequisites → check receptacle state → execute → verify placement) has explicit checkpoints: step 1 confirms holding/location, step 4 confirms the observation shows the object in/on the receptacle, and the Error Handling section supplies recovery loops for failed placements. This is a simple, non-destructive skill, so the batch/destruction cap does not apply.

5 / 5

Progressive Disclosure

The body itself is well organized into scannable sections, but the bundle contains `references/receptacle_suitability_guide.md` — whose suitability heuristics (e.g., "Countertops: typically not storage locations") directly inform step 2's "Unsuitable" row and the Error Handling section — and the body never links to or mentions it. This matches the 3 anchor ("references present but not clearly signaled") rather than 4 ("references mostly clear"), since there is zero navigation from SKILL.md to the one reference file.

3 / 5

Total

17

/

20

Passed

Description

87%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: third-person voice, explicit "Use when" trigger, and concrete capability statements scoped to a well-defined niche. The only meaningful improvement would be slightly fuller action coverage (navigation and verification) and a few more trigger synonyms.

DimensionReasoningScore

Specificity

The description lists several concrete actions — "checks receptacle suitability, opens closed containers if needed, and executes the `put` command to store the object" — plus coverage of "open surfaces (countertops, beds) and closed containers (drawers, cabinets)". It falls short of the 5 anchor only because prerequisite steps the skill actually performs (navigation to the receptacle, placement verification) are not mentioned.

4 / 5

Completeness

It explicitly answers both questions: the opening "Use when the agent is holding an object and needs to place it into a target receptacle in ALFWorld" gives concrete when-triggers, and the following sentences state what the skill does (suitability check, opening closed containers, executing `put`). This matches the 5 anchor's pattern of concrete trigger phrases plus a full capability statement, and clearly exceeds the 4 anchor where the 'when' is generic.

5 / 5

Trigger Term Quality

Natural trigger phrasing is present — "holding an object", "place it into a target receptacle", "store", "put" — and these are the phrases an ALFWorld agent state would naturally produce. Not a 5 because common synonyms and variations (e.g., "put away", "put it in/on", receptacle-type keywords like drawer/cabinet as triggers) are only partially covered.

4 / 5

Distinctiveness Conflict Risk

The description carves out a clear niche — final placement of a held object into a receptacle in ALFWorld — with triggers (holding object + identified receptacle) that distinguish it from sibling skills like object location or cleaning/heating. It is not generic and does not claim capabilities belonging to adjacent skills, so conflict risk is minimal.

5 / 5

Total

18

/

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.