webshop-search-executor

Executes a search on an e-commerce platform using parsed keywords. Use when you have extracted search terms from a user query and need to perform the actual search[] action on the WebShop interface. Takes structured search terms and performs a search action, returning a list of product results for evaluation.

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

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

Quality

Content

80%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 is lean, token-efficient, and gives fully executable action formats with concrete examples. Its weaknesses are a missing validation checkpoint in the search-result workflow and an unreferenced, overlapping bundle file that underuses progressive disclosure.

Suggestions

Add an explicit validation step before returning results (e.g., verify at least one product satisfies the user's price/attribute constraints, else apply the edge-case retry) to lift workflow clarity.

Either reference references/action_grammar.md from the body for the detailed grammar and keep only a minimal inline summary, or fold the redundant grammar out of SKILL.md so the bundle file is clearly signaled and content is appropriately split.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence, presenting only trigger conditions, edge cases, action formats, and two compact examples with no padding or explanation of concepts Claude already knows, matching the lean-and-efficient anchor.	5 / 5
Actionability	Provides fully executable, copy-paste-ready action formats ('search[<keywords>]', 'click[<product_id>]') with two complete worked examples covering common cases, matching the fully-executable anchor.	5 / 5
Workflow Clarity	A rough sequence (trigger -> action protocol -> examples) is present with edge-case handling, but there is no explicit validation checkpoint verifying that results match the user's constraints before returning; for a result-returning search operation this validation gap caps the score at 3 per the batch/validation guideline.	3 / 5
Progressive Disclosure	The body is well-sectioned and under 50 lines, but the bundled references/action_grammar.md is never referenced from the body and overlaps with grammar already inlined in SKILL.md, leaving the reference unsignaled and content not appropriately split per the bundle-structure guideline.	3 / 5
	Total	16 / 20 Passed

Description

71%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 clearly states both what the skill does and when to use it, with a well-scoped WebShop-specific niche that minimizes conflict risk. Trigger phrasing is somewhat technical and misses the most natural user-facing terms, keeping it from the top of the trigger dimension.

Suggestions

Add natural user-facing trigger phrases (e.g., 'find or search for products', 'shop for items') alongside the technical 'search[] action' phrasing to improve trigger-term quality.

Consider mentioning adjacent concrete actions (e.g., clicking a product from results) in the description to broaden specificity coverage beyond search alone.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('Executes a search', 'perform the actual search[] action', 'performs a search action, returning a list of product results'), but coverage is limited to search only with no adjacent actions, so it falls below the comprehensive-anchor 5.	4 / 5
Completeness	Explicitly answers both what ('Executes a search... returning a list of product results') and when ('Use when you have extracted search terms from a user query and need to perform the actual search[] action'); the when clause is concrete but could be slightly more specific, fitting the both-present anchor 4.	4 / 5
Trigger Term Quality	Includes relevant terms ('search terms', 'search action', 'WebShop interface', 'product results') but leans technical and misses natural user phrasings like 'find products' or 'search for items', matching the some-relevant-keywords-but-missing-variations anchor.	3 / 5
Distinctiveness Conflict Risk	Scoped to a clear niche ('WebShop interface' e-commerce search execution) with a distinct trigger tied to extracted search terms, giving minimal overlap risk with other skills.	5 / 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/webshop/webshop-search-executor/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.