alfworld-search-pattern-executor

Systematically searches a sequence of likely locations for a target object based on common sense. Use when you need to find a specific object and know which receptacles to check but not which one contains it. Takes a list of candidate receptacles, orchestrates navigation and inspection, and outputs when the target is found or all locations are exhausted.

Quality

84%

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

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 delivers copy-paste-ready commands, a fully worked example, and a well-sequenced workflow with error recovery. The main structural flaw is that the bundled common-sense locations reference is never linked from the skill, so a reader gets no navigation to it and no guidance on how to build the candidate list in the first place.

Suggestions

Add a short 'Selecting candidates' section pointing to references/common_sense_locations.md (e.g., 'Build the candidate list using [common_sense_locations.md](references/common_sense_locations.md)') so the bundled reference is discoverable and the skill's entry point is complete.

Trim or merge the 'Action Format' section into the Workflow, since each of the four commands already appears there verbatim.

Briefly state where the candidate_receptacles list comes from in the Workflow intro, closing the gap between 'Takes a list of candidate receptacles' in the description and the body's assumption that candidates are already known.

Dimension	Reasoning	Score
Conciseness	The body is lean with no concept over-explanation, but the 'Action Format' section re-documents the four commands (`go to`, `open`, `close`, `take`) already embedded verbatim in the Workflow steps, a minor redundancy that could be trimmed — matching the 'efficient; minor instances of over-explanation' anchor.	4 / 5
Actionability	Guidance is fully executable: exact action syntax (`go to {receptacle}`, `open {receptacle}`, `close {receptacle}`, `take {target_object} from {receptacle}`), a complete worked Thought/Action/Observation transcript for the common case, and a concrete recovery rule for the "Nothing happened" failure mode.	5 / 5
Workflow Clarity	The six numbered steps form a clear sequence with explicit conditionals (open if closed, stop if found, close if opened, report if exhausted), per-step observation checkpoints, and a feedback loop for the "Nothing happened" error — no destructive or batch operations, so no cap applies.	5 / 5
Progressive Disclosure	The body itself is well-organized and under 50 lines, but the provided bundle file references/common_sense_locations.md — which explicitly states it should be used to generate the candidate_receptacles list — is never referenced from SKILL.md, leaving the reference orphaned and candidate-list generation unaddressed; this matches the 'references present but not clearly signaled' anchor.	3 / 5
	Total	17 / 20 Passed

Description

76%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 with an explicit 'Use when...' clause, third-person voice, and concrete behavior. Its weakest point is trigger-term coverage: it leans on the jargon term 'receptacles' and lacks common natural-language synonyms a user would say.

Suggestions

Add natural trigger synonyms such as 'look for', 'search for', or 'where is an object' to the 'Use when' clause so users' phrasing matches more readily.

Reduce reliance on the jargon term 'receptacles' (or pair it with a plain-language equivalent like 'containers or furniture') in the trigger conditions.

Mention the outcome actions more completely (e.g., picking up the object once found) to lift specificity toward comprehensive coverage.

Dimension	Reasoning	Score
Specificity	The description lists several concrete actions — "Takes a list of candidate receptacles, orchestrates navigation and inspection, and outputs when the target is found or all locations are exhausted" — but omits supporting actions like opening receptacles or picking up the object, so it is not comprehensive enough for a 5.	4 / 5
Completeness	It clearly answers both what ("Systematically searches a sequence of likely locations... orchestrates navigation and inspection") and when ("Use when you need to find a specific object and know which receptacles to check but not which one contains it") with an explicit, concrete trigger clause in third-person voice.	5 / 5
Trigger Term Quality	"Use when you need to find a specific object" and "know which receptacles to check" are natural trigger phrases, but "receptacles" is technical jargon and common variations like "look for", "search for", or "where is" are missing, matching the anchor for some relevant keywords but missing synonyms.	3 / 5
Distinctiveness Conflict Risk	The embodied-environment search framing (receptacles, navigation, inspection, found-vs-exhausted outcome) carves a mostly distinct niche, though it could still overlap with generic search/lookup skills, matching the 'mostly distinct; minor overlap risk' anchor.	4 / 5
	Total	16 / 20 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-search-pattern-executor/SKILL.md
Commit: 358ec82

Reviewed: 8 days 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.