CtrlK
BlogDocsLog inGet started
Tessl Logo

alfworld-object-locator

Use when the agent needs to find a specific object in ALFWorld that is not currently in inventory and whose location is unknown. This skill parses the environment observation, ranks receptacles by likelihood of containing the target object using common-sense reasoning, and outputs a navigation action to the most promising location.

71

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

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.

The body is actionable and workflow-clear with concrete commands and worked examples, and it is mostly token-efficient. Its main weakness is progressive disclosure: it inlines content that already lives in the references/ bundle without signaling or linking to those files.

Suggestions

Replace the inlined 'Rank by Likelihood' table with a pointer to references/object_mappings.md (e.g., 'See [object_mappings.md](references/object_mappings.md) for full object→receptacle mappings') to avoid duplication and surface the reference.

Link references/skill_usage_examples.md from the Example section rather than reproducing standalone example traces in the body, keeping the body as an overview.

Trim the duplicated receptacle categorization list or move it into the reference, since the detailed mappings already live there.

DimensionReasoningScore

Conciseness

Mostly efficient and assumes ALFWorld competence, but the inlined likelihood table partially duplicates references/object_mappings.md and could be trimmed in favor of a pointer.

4 / 5

Actionability

Provides concrete executable commands (`go to {receptacle}`, `take {object} from {receptacle}`, `open {receptacle}`) plus two full command/response example traces covering the found-at-first and found-at-second cases.

5 / 5

Workflow Clarity

A clearly sequenced parse → rank → search → track workflow with an explicit YES/NO/Still-NO decision checkpoint, an open-and-recheck feedback loop, and a dedicated error-handling section for recovery.

5 / 5

Progressive Disclosure

The body is well-sectioned but never links to the two existing reference files, instead inlining a mapping table and examples that duplicate references/object_mappings.md and references/skill_usage_examples.md — references present but not signaled.

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, third-person description that clearly states both capability and trigger conditions with concrete actions and a well-scoped niche. It could be marginally improved with synonym trigger terms and an extra action verb, but already answers what and when explicitly.

DimensionReasoningScore

Specificity

Lists several concrete actions — 'parses the environment observation', 'ranks receptacles by likelihood', 'outputs a navigation action' — but stops short of the search/open-container steps, leaving minor gaps in coverage.

4 / 5

Completeness

Explicitly answers both 'what' (parses observations, ranks receptacles, outputs a navigation action) and 'when' (Use when finding an object not in inventory with unknown location) with concrete trigger phrases.

5 / 5

Trigger Term Quality

Natural trigger phrasing ('find a specific object', 'not currently in inventory', 'location is unknown') covers the common case well, though it lacks synonyms or alternate phrasings a user might say.

4 / 5

Distinctiveness Conflict Risk

Targets a clear ALFWorld-specific niche — locating an out-of-inventory object with unknown location — with distinct triggers and minimal overlap with other skills.

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.

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.