webshop-search-constructor

This skill formulates an effective search query from structured product criteria. It is used when initiating a product search on an e-commerce platform, converting attributes into a concise, relevant keyword string. The input is a set of parsed criteria (e.g., 'jewelry box', '10 slots', 'easy to clean', 'price < $60'), and the output is a formatted search action string (e.g., 'search[jewelry box, 10 slots, less than $60, easy to clean]') optimized for the platform's search engine.

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

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 body is concise, well-structured, and gives concrete executable guidance with a clear worked example, but it suffers from a bundle/structure mismatch: an existing reference guide is not linked, and a referenced script does not exist. Adding a validation checkpoint before issuing the search would further strengthen the workflow.

Suggestions

Link to references/query_optimization_guide.md from the body (e.g., under a 'Query optimization' section) so the existing detailed reference is discoverable rather than orphaned.

Either add the scripts/construct_search_query.py script to the bundle or replace the scripted workflow with inline formatting instructions so the documented command is actually executable.

Add a validation step (e.g., 'Confirm the search action is available in the current observation before issuing search[...]') to guard the outward-facing search action.

Dimension	Reasoning	Score
Conciseness	The body is lean (~30 lines) with no padding or over-explanation of known concepts, but the 'Workflow Example' section partly restates the Core Process steps with values, a minor redundancy that could be tightened.	4 / 5
Actionability	Provides a concrete, copy-paste-ready CLI command plus the expected script output and final action format, but the referenced scripts/construct_search_query.py does not exist in the bundle, leaving a gap in true executability.	4 / 5
Workflow Clarity	The receive-construct-execute sequence is clearly laid out with a worked example for this simple single-purpose skill, but there is no validation checkpoint (e.g., confirming the search action is available before issuing it), a minor gap.	4 / 5
Progressive Disclosure	Sections are well-organized, but the existing references/query_optimization_guide.md is never linked from the body (orphaned, undiscoverable) while the body references a scripts/construct_search_query.py that is absent from the bundle — a structural mismatch in how references are signaled.	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.

The description is specific, complete, and distinctive, clearly stating both the capability and its trigger condition in third person with concrete input/output examples. The only minor gap is keyword synonym coverage for trigger terms.

Suggestions

Add natural-language synonyms users might say (e.g., 'find products', 'shop for', 'online shopping') alongside 'product search' to broaden trigger coverage.

Consider adding an explicit 'Use when...' clause form to make the trigger phrasing match the rubric's preferred pattern even more directly.

Dimension	Reasoning	Score
Specificity	Names the domain and multiple concrete actions ('formulates an effective search query', 'converting attributes into a concise, relevant keyword string', 'output is a formatted search action string') with concrete input/output examples, giving comprehensive coverage.	5 / 5
Completeness	Explicitly answers both what ('formulates an effective search query...converting attributes into a concise, relevant keyword string') and when ('It is used when initiating a product search on an e-commerce platform') with a concrete trigger phrase.	5 / 5
Trigger Term Quality	Includes several natural terms a user would say ('product search', 'e-commerce platform', 'search query', 'search engine'), but lacks common synonyms such as 'find products', 'shop for', or 'online shopping'.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche — constructing optimized e-commerce search queries from structured criteria with a distinctive search[...] action format — minimizing overlap with other skills.	5 / 5
	Total	19 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: zjunlp/SkillNet
Path: experiments/src/skills/webshop/webshop-search-constructor/SKILL.md
Commit: cce11c3

Reviewed: 2 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.