CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

67

Quality

80%

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-storage-explorer/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

71%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 well-organized, actionable skill body with a clear phased workflow and concrete example. Its main weakness is progressive disclosure: a bundled reference file is present but never surfaced or linked from the body.

Suggestions

Link references/storage_heuristics.md from the body (e.g., under Key Considerations: 'See [storage_heuristics.md](references/storage_heuristics.md) for category-specific placement patterns') instead of duplicating heuristic content inline.

Add an explicit post-placement verification step (observe confirmation that the object was placed) to close the workflow loop.

Trim the redundancy between 'When to Use' (which restates the frontmatter) and 'Core Strategy' (which overlaps the Execution Pattern phases).

DimensionReasoningScore

Conciseness

Mostly efficient with no over-explanation of known concepts, but 'When to Use' restates the frontmatter and 'Core Strategy' overlaps the phases, leaving minor trims available.

4 / 5

Actionability

Provides concrete executable alfworld commands in the example (go/open/put) and step-level guidance, though only one worked example and abstract evaluation criteria leave minor gaps.

4 / 5

Workflow Clarity

Phase 1/2/3 sequence is clear with an Observe/Evaluate checkpoint and Error Handling feedback loops; not a destructive/batch task so the cap does not apply, but it lacks an explicit post-placement verification step.

4 / 5

Progressive Disclosure

The body is well-sectioned, but references/storage_heuristics.md exists and is never linked from the body, leaving an orphaned reference while its heuristic content is partly duplicated inline.

3 / 5

Total

15

/

20

Passed

Description

88%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, specific description that clearly states both capabilities and trigger conditions in third person. Concrete verbs and an explicit 'Use when' clause make it highly actionable and distinguishable.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'explores storage receptacles', 'Opens, inspects, and closes candidate receptacles', 'places the object in the best match' — with comprehensive coverage and correct third-person voice.

5 / 5

Completeness

Explicitly answers 'what' (explore, inspect, place) and 'when' via a concrete 'Use when the agent needs to store an item but the exact target receptacle is unknown or ambiguous' trigger clause.

5 / 5

Trigger Term Quality

Natural domain terms like 'store an item', 'drawers, cabinets, shelves', and 'target receptacle is unknown or ambiguous' are present, but a few synonyms/variations are missing.

4 / 5

Distinctiveness Conflict Risk

Clear niche of storage-receptacle exploration with distinct triggers; only minor overlap risk with generic put-object skills keeps it below 5.

4 / 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.

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.