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

77%

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

Fix and improve this skill with Tessl

tessl review fix ./experiments/src/skills/alfworld/alfworld-search-pattern-executor/SKILL.md

Quality

Content

78%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 is highly actionable with exact commands and a worked example, and the workflow is clearly sequenced with decision points. Its main weakness is progressive disclosure: an existing reference file (common_sense_locations.md) is not signaled or linked from the body, so the skill fails to route Claude to the candidate-list guidance it describes.

Suggestions

Add a one-line pointer to references/common_sense_locations.md in the Workflow or a References section, e.g. 'Build the candidate_receptacles list using common-sense priorities (see references/common_sense_locations.md).'

De-duplicate Key Rules against the Workflow — fold 'search candidates in order' and 'close after checking' into the steps and keep only net-new rules there.

Strengthen the 'Nothing happened' feedback loop into an explicit verify-then-retry sub-procedure with a stop condition to push workflow clarity higher.

Dimension	Reasoning	Score
Conciseness	The body is lean with no over-explanation of concepts Claude already knows; the Workflow, Action Format, and Example sections all earn their place. Not a 5 because the Key Rules section restates steps already in the Workflow (close after checking, search in order) and the example is somewhat long.	4 / 5
Actionability	Gives exact executable alfworld commands (`go to {receptacle}`, `open {receptacle}`, `close {receptacle}`, `take {object} from {receptacle}`) and a fully worked example with real commands, observations, and concrete 'Nothing happened' retry guidance covering the common cases.	5 / 5
Workflow Clarity	A clear 6-step numbered sequence with explicit decision points (open if closed, stop when found, close and continue when not, report when exhausted) plus a 'Nothing happened' recovery hint. Not a 5 because the error-recovery feedback loop is thin (verify name and retry) rather than a full validate-fix-retry cycle.	4 / 5
Progressive Disclosure	Sections are well-organized for a simple skill, but a bundle file exists (references/common_sense_locations.md) that is never referenced or linked from the body — the canonical 'references present but not clearly signaled' case. Not a 4 because an existing reference file going unmentioned is more than a minor organization gap.	3 / 5
	Total	16 / 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.

The description is strong on completeness, clearly stating both what the skill does and when to use it with an explicit trigger clause, and is written in correct third person. It is slightly held back by jargon ('receptacles') and a broad lead phrase that modestly raises overlap risk.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — 'searches a sequence of likely locations', 'Takes a list of candidate receptacles', 'orchestrates navigation and inspection', 'outputs when the target is found or all locations are exhausted' — with only minor abstraction in 'orchestrates'. Not a 5 because 'orchestrates navigation and inspection' is slightly higher-level than naming each concrete action.	4 / 5
Completeness	Explicitly answers both: what ('Systematically searches a sequence of likely locations... orchestrates navigation and inspection, and outputs when the target is found or all locations are exhausted') and when ('Use when you need to find a specific object and know which receptacles to check'). Matches the anchor that requires both what and when with concrete trigger phrases.	5 / 5
Trigger Term Quality	The trigger 'Use when you need to find a specific object and know which receptacles to check but not which one contains it' includes the natural phrase 'find a specific object', but 'receptacles' is domain jargon and common synonyms/variants are absent. Not a 4 because keyword coverage is thin rather than merely missing a few terms.	3 / 5
Distinctiveness Conflict Risk	The candidate-receptacle / navigation-and-inspection framing carves a fairly distinct niche tied to alfworld object search, with minor overlap risk against general search skills. Not a 5 because the lead phrase 'find a specific object' is broad enough to invite some overlap.	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: 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.