webshop-query-interpreter

Interprets a user's shopping query to extract key product requirements such as item type, attributes, and constraints. Use when a new shopping instruction is received and you need to parse natural language into structured criteria (product category, desired features, price limits) before performing a search. The output is a clear set of search parameters for use in subsequent product lookup steps.

Quality

85%

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

92%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is lean, actionable, and clearly sequenced with a concrete output template and worked examples, but it fails to link the bundled reference files that would aid query parsing.

Suggestions

Add a one-line pointer in the Parse step, e.g. "See [query_patterns.md](references/query_patterns.md) for common linguistic patterns and edge cases," so the existing reference is discoverable.

Optionally reference execution_example.md from the Example section as a demonstration of the end-to-end trajectory.

Dimension	Reasoning	Score
Conciseness	The body is lean and free of concept-padding Claude already knows; every section (Trigger, Core Process, Example) earns its place with no verbosity.	3 / 3
Actionability	Provides a copy-paste-ready output template (Product Type / Attributes / Constraints / Search Query) plus two fully worked examples with Thought and Structured Output, giving concrete executable guidance for an instruction-only skill.	3 / 3
Workflow Clarity	A clear three-step sequence — Parse the Instruction, Structure the Output, Hand Off — is explicitly numbered; the task is simple and non-destructive so no validation checkpoint is required.	3 / 3
Progressive Disclosure	The body is well-organized, but the provided bundle files references/query_patterns.md and references/execution_example.md are never referenced or signaled from the body, leaving useful material orphaned rather than navigable.	2 / 3
	Total	11 / 12 Passed

Description

77%

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 specific and complete with an explicit Use-when trigger, but its trigger phrasing is not natural user language and its distinctiveness from sibling webshop search skills is only moderate.

Suggestions

Rewrite the trigger to mirror natural user language, e.g. "Use when the user says they want or need a product and you must turn that request into structured search criteria."

Sharpen distinctiveness by contrasting the skill's role with the search executor, e.g. "Produces search parameters only; does not perform the product search itself."

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "extract key product requirements such as item type, attributes, and constraints", "parse natural language into structured criteria (product category, desired features, price limits)", and "output is a clear set of search parameters" — matching the multi-action anchor.	3 / 3
Completeness	Clearly states what (interprets queries, extracts requirements, outputs search parameters) and when via an explicit "Use when a new shopping instruction is received and you need to parse natural language into structured criteria...before performing a search" clause.	3 / 3
Trigger Term Quality	The trigger "Use when a new shopping instruction is received" uses internal phrasing a user would not naturally say; it omits common natural variations like "I need/find me a product", so coverage is partial rather than complete.	2 / 3
Distinctiveness Conflict Risk	The query-interpretation niche is somewhat distinct, but the generic "shopping query/instruction" framing and sibling search skills (webshop-search-executor, webshop-product-search) create real overlap risk rather than a clearly unconflicted niche.	2 / 3
	Total	10 / 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/webshop/webshop-query-interpreter/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.