alfworld-storage-explorer

Systematically explores storage receptacles (drawers, cabinets, shelves) to find an appropriate placement location for an object. Use when the agent needs to store an item but the exact target receptacle is unknown or ambiguous. Opens, inspects, and closes candidate receptacles to assess suitability, then places the object in the best match.

Quality

73%

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-storage-explorer/SKILL.md

Quality

Content

62%

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

The content has a clear, well-sequenced workflow with validation and error-recovery feedback loops and a concrete worked example. Its main weaknesses are a truncated 'Output Format' section, some restated/abstract guidance, and an orphaned reference file that is never linked from the body.

Suggestions

Complete the truncated 'Output Format' section or remove it so the skill does not trail off mid-instruction.

Link references/storage_heuristics.md from the body (e.g., a '## Storage heuristics — see [storage_heuristics.md](references/storage_heuristics.md)') so the bundle reference is discoverable.

Tighten the overlap between 'Core Strategy' and 'Phase 2' (e.g., state the 'inspect before placing' rule once) and make the 'Evaluate suitability' criteria more concrete.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and does not over-explain general concepts, but 'inspect before placing' is restated across 'Core Strategy' and 'Phase 2', and the 'Output Format' section is truncated ('Maintain the standard action format:' with no content), so it is not the lean level above.	2 / 3
Actionability	The example gives concrete, executable alfworld commands ('go to drawer 1', 'open drawer 1', 'put sponge 1 in/on drawer 1'), but the 'Output Format' section is cut off and 'Evaluate suitability based on Current contents / Available space / Logical categorization' is abstract rather than fully concrete, leaving incomplete guidance.	2 / 3
Workflow Clarity	A clear 3-phase sequence (Initial Assessment → Systematic Exploration → Decision Making) is given, with an explicit 'Inspect Before Placing' verification checkpoint and an 'Error Handling' section providing feedback loops ('try alternative locations', reconsider understanding), matching the anchor for clear sequence with validation and error recovery.	3 / 3
Progressive Disclosure	The body is well-organized into labeled sections, but the bundle file references/storage_heuristics.md is never linked or signaled from the body, so an existing reference is effectively orphaned rather than clearly surfaced; not the level above because references are not clearly signaled.	2 / 3
	Total	9 / 12 Passed

Description

85%

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, gives an explicit 'Use when' trigger, and occupies a distinct niche. Its only weakness is trigger-term quality, which leans on the technical word 'receptacle' rather than natural user phrasings.

Suggestions

Add natural trigger phrasings users actually say, e.g. 'Use when the task says put, place, or store an item but does not name a specific receptacle.'

Reduce reliance on the jargon term 'receptacle' in the trigger clause in favor of plain words like 'drawer, cabinet, or shelf'.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Systematically explores storage receptacles', 'Opens, inspects, and closes candidate receptacles', 'places the object in the best match' — matching the anchor for several specific concrete actions.	3 / 3
Completeness	It explicitly answers both what ('explores storage receptacles... Opens, inspects, and closes... places the object') and when ('Use when the agent needs to store an item but the exact target receptacle is unknown or ambiguous'), matching the anchor with an explicit 'Use when' trigger.	3 / 3
Trigger Term Quality	It includes some natural terms ('drawers, cabinets, shelves', 'store an item') but the trigger framing centers on the technical term 'receptacle' and omits common variations users would say like 'put' or 'place'; not the level above because coverage of natural phrasings is incomplete.	2 / 3
Distinctiveness Conflict Risk	It carves a clear niche (alfworld storage exploration when the target is unknown/ambiguous) with distinct triggers, making it unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 12 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-storage-explorer/SKILL.md
Commit: 7bb9a48

Reviewed: 1 day 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.