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

81%

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

77%

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 clearly sequenced with a good worked example, but it is held back by an empty template stub and a bundle reference file that is not linked or signaled anywhere in the content.

Suggestions

Remove or fill in the empty "Thought Process Template" section so it does not consume tokens without delivering content.

Link references/alfworld_actions_ref.md from the body (e.g., under a short "Action reference" note) so the existing bundle file is discoverable.

Add a brief observation-based validation note in the verification step (e.g., confirm "Nothing happened" is not returned) to make the re-inspection checkpoint explicit.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean and assumes Claude's competence, but the "Thought Process Template" section is a stub heading with no content beneath it, wasting tokens.	2 / 3
Actionability	It provides concrete, copy-pasteable action templates ("go to {recep}", "open {recep}", "take {obj} from {recep}") plus a fully worked Thought/Action/Observation example.	3 / 3
Workflow Clarity	A clearly numbered four-step sequence with explicit verification logic and a checklist-style revisit; the read-only re-inspection task does not require destructive-operation feedback loops.	3 / 3
Progressive Disclosure	Sections are well organized for a simple skill, but a real bundle file (references/alfworld_actions_ref.md) exists yet is never referenced or linked in the body, so navigation to it is not signaled.	2 / 3
	Total	10 / 12 Passed

Description

85%

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 that concretely names its actions, clearly states both what it does and when to use it, and occupies a distinct niche. The main weakness is trigger-term naturalness, relying on domain-internal phrasing rather than terms a user would spontaneously say.

Suggestions

Add natural-language trigger terms a user might say (e.g., "re-search", "double-check locations", "verify nothing was missed") alongside the Alfworld-specific phrasing to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	"Systematically revisits receptacles, re-opens closed containers, and re-inspects contents" lists multiple specific concrete actions rather than vague language.	3 / 3
Completeness	It explicitly answers what it does (re-examines/revisits/verifies locations) and when to use it via an explicit "Use when..." clause.	3 / 3
Trigger Term Quality	"Use when an initial search fails to find enough objects or when double-checking is required" gives a relevant trigger, but the terms are domain-internal (Alfworld) rather than the natural vocabulary a user would spontaneously say.	2 / 3
Distinctiveness Conflict Risk	It is clearly scoped to re-verification of already-visited locations, a niche distinct from an initial-search skill, making wrong-skill triggering unlikely.	3 / 3
	Total	11 / 12 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: 7bb9a48

Reviewed: 1 day 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.