CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

68

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

71%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 content delivers a clear, actionable revisit workflow with a good worked example, but it ships incomplete: the 'Thought Process Template' section is an empty promise and the directly relevant bundled action reference is never referenced. Fixing those two gaps would lift most dimensions.

Suggestions

Complete the 'Thought Process Template' section — it currently ends with 'structure your reasoning as follows:' and no template follows.

Link references/alfworld_actions_ref.md from the body (e.g., under Core Procedure) so the bundled action reference is discoverable.

Remove the redundant closed-receptacle bullet in step 3, which repeats the 'For Closed Receptacles' guidance from step 2.

DimensionReasoningScore

Conciseness

The body is lean and assumes competence (no explaining of ALFWorld basics), but step 3's bullet 'opening it is a critical verification step' duplicates step 2's closed-receptacle handling, and the 'Thought Process Template' section ends mid-sentence with no template, wasting tokens. It is efficient with minor trims possible, matching the level-4 anchor rather than the fully lean level-5 anchor.

4 / 5

Actionability

Concrete command templates ('go to {recep}', 'open {recep}', 'take {obj} from {recep}') plus a complete worked Thought/Action/Observation example make the guidance mostly executable. The missing pieces — the promised but empty 'Thought Process Template' and the unlinked action reference — keep it below fully copy-paste-ready coverage.

4 / 5

Workflow Clarity

A clear four-step sequence with per-location verification logic ('If the target object is now present, retrieve it... note it as thoroughly checked and move to the next location') and an explicit both-branch conclusion. The empty template section and absence of any recovery guidance for unexpected observations are minor gaps, matching level 4 rather than the fully validated level-5 anchor.

4 / 5

Progressive Disclosure

The body is short and well-sectioned, but the bundle provides references/alfworld_actions_ref.md — which even contains a 'Key Notes for Search Verifier Skill' section — and the body never signals or links it. Per the rubric's bundle-structure guideline this is 'references present but not clearly signaled', fitting the level-3 anchor.

3 / 5

Total

15

/

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 description: third-person voice, concrete actions, and an explicit 'Use when...' trigger clause tied to a specific failure condition. The only weakness is slightly thin synonym coverage in the trigger terms.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions — 'Systematically revisits receptacles, re-opens closed containers, and re-inspects contents' — giving comprehensive coverage of the skill's behavior. There are no meaningful coverage gaps, so it exceeds the 'several specific actions' level-4 anchor.

5 / 5

Completeness

It explicitly answers both questions: the 'what' ('Re-examines previously visited locations... revisits receptacles, re-opens closed containers, re-inspects contents') and an explicit 'Use when...' clause with concrete trigger conditions. This matches the level-5 anchor exactly; the 'when' is explicit, not merely present.

5 / 5

Trigger Term Quality

Natural trigger phrases like 'initial search fails to find enough objects', 'double-checking', and 'before concluding task failure' map well to what a user or agent would say. Common synonyms such as 'recheck', 'verify', or 'missed object' are absent, keeping it just below the comprehensive level-5 anchor.

4 / 5

Distinctiveness Conflict Risk

The niche — re-verifying already-searched locations before declaring task failure — is clearly distinct from initial-search or general-exploration skills, and the 'when an initial search fails' framing minimizes wrong-skill triggering.

5 / 5

Total

19

/

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.

Validation — 16 / 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.