alfworld-search-verifier

Re-examines previously visited locations to confirm the absence of a target object or to check for overlooked items. Use when an initial search fails to find enough objects or when double-checking is required before concluding task failure. Systematically revisits receptacles, re-opens closed containers, and re-inspects contents to ensure no viable location was missed.

Quality

83%

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

75%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-structured, actionable instruction skill with a clear procedure and concrete Alfworld example. Main weaknesses are the incomplete "Thought Process Template" section and the lack of an explicit in-body pointer to the bundled action reference.

Suggestions

Complete or remove the trailing "Thought Process Template" section, which currently ends with a colon and no following template content.

Add an explicit pointer to the bundled reference, e.g. "See [alfworld_actions_ref.md](references/alfworld_actions_ref.md) for the full action list and formats," so the reference is clearly signaled.

Add a final verification checkpoint in the Conclusion step (e.g., confirm every receptacle on the tracking list was revisited) to close the workflow validation gap.

Dimension	Reasoning	Score
Conciseness	The body is lean, uses concrete action formats, and avoids explaining Alfworld basics, but the empty "Thought Process Template" section and a few padded lines ("The state may have changed, or an item may have been overlooked") keep it from a 5.	4 / 5
Actionability	Provides concrete action commands (`go to {recep}`, `open {recep}`, `take {obj} from {recep}`) and a copy-paste-ready Thought/Action/Observation example, but the dangling empty template section and missing explicit pointer to the action reference leave minor gaps.	4 / 5
Workflow Clarity	The four-step Core Procedure is clearly sequenced with per-location verification logic and a recovery path (retrieve if found), but there is no explicit final "all locations checked?" checklist, leaving a minor validation gap.	4 / 5
Progressive Disclosure	Well-organized sections with an appropriately split one-level-deep reference (alfworld_actions_ref.md exists in references/), but the reference is not explicitly linked from the body and the empty template section is a minor organization gap.	4 / 5
	Total	16 / 20 Passed

Description

92%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. Only minor room for improvement in trigger-term synonym breadth.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "revisits receptacles, re-opens closed containers, and re-inspects contents" — giving comprehensive coverage of the verification workflow rather than vague abstraction.	5 / 5
Completeness	Explicitly answers both what (re-examine, revisit, re-open, re-inspect) and when ("Use when an initial search fails... or when double-checking is required before concluding task failure") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural phrases like "initial search fails to find enough objects" and "double-checking is required" are present, but synonym coverage is incomplete and the domain has no file-extension-style terms to round it out.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche — post-search re-verification of already-visited locations — with distinct triggers that separate it from an initial-search skill, minimizing conflict risk.	5 / 5
	Total	19 / 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-verifier/SKILL.md
Commit: 076c6df

Reviewed: 6 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.