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.

77

Quality

96%

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

92%

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

The body is a lean, actionable, well-sequenced workflow with concrete commands and a validation loop. Its main weakness is progressive disclosure: two reference bundle files exist but are never linked from SKILL.md, and the inline mappings duplicate one of them.

Suggestions

Add explicit, signaled links to the bundle files — e.g., a short 'References' section pointing to references/object_mappings.md for the full object→receptacle mappings and references/skill_usage_examples.md for worked trajectories — so the materials are discoverable from SKILL.md.

Replace the inline object→receptacle table with a condensed summary that defers detail to object_mappings.md, keeping SKILL.md a lean overview instead of duplicating the reference content.

In the 'Track Searched Locations' / not-found fallback, reference object_mappings.md as the source for expanding the search to lower-probability receptacles, tying the fallback to the bundled reference.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence — it does not explain what ALFWorld is or what a fridge is, and each section (workflow, ranking table, examples, error handling) earns its place. It is not level 2 because there is no padded explanation or unnecessary concept coverage to tighten.

3 / 3

Actionability

It gives executable ALFWorld commands ("go to {receptacle}", "take {object} from {receptacle}", "open {receptacle}") with concrete worked transcripts showing inputs and observations. It is above level 2 because the guidance is copy-paste-ready rather than pseudocode or abstract description.

3 / 3

Workflow Clarity

A clear four-step sequence includes an explicit validation checkpoint (read the observation and check whether the object is mentioned) with a feedback loop (open closed containers and re-check, then move on) plus an error-handling section. It is not capped at 2 because this is a search/navigation task, not a destructive or batch operation, and the checkpoints are explicit rather than implicit.

3 / 3

Progressive Disclosure

The body is well-organized with clear sections, but neither bundle reference file (object_mappings.md, skill_usage_examples.md) is linked or signaled from SKILL.md, and the inline object→receptacle table duplicates content that already lives in object_mappings.md. It is not level 3 because references are not clearly signaled and content that exists separately is restated inline; it is above level 1 because the structure is clean with no nested reference chains.

2 / 3

Total

11

/

12

Passed

Description

100%

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 concise, well-constructed description that clearly states both what the skill does and when to use it, with concrete actions and natural trigger phrasing. It is appropriately scoped to its ALFWorld niche and free of vague fluff.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions — "parses the environment observation, ranks receptacles by likelihood… using common-sense reasoning, and outputs a navigation action" — matching the anchor for several specific actions. It is not the level below because it does more than name a domain and a single action, and it stays in third-person voice with no fluff.

3 / 3

Completeness

It explicitly answers both halves: a "Use when…" clause covers when, and "parses… ranks… outputs a navigation action" covers what. It is not level 2 because the when-trigger is explicit, not merely implied.

3 / 3

Trigger Term Quality

Phrases like "find a specific object in ALFWorld", "not currently in inventory", and "location is unknown" are natural trigger language an agent would use when it needs this skill. It is above level 2 because the trigger conditions are articulated explicitly and naturally rather than as a single generic keyword.

3 / 3

Distinctiveness Conflict Risk

The skill targets a narrow ALFWorld niche (locating an out-of-inventory object whose location is unknown) with distinct triggers, making it unlikely to fire for unrelated skills. It is above level 2 because the niche is specific rather than overlapping with similar general skills.

3 / 3

Total

12

/

12

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.