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

70%

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

65%

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

The body is concrete and actionable with exact action grammar and examples, but it underuses its reference file and does not sequence the full search-to-select workflow with explicit checkpoints.

Suggestions

Add a one-line pointer to `references/action_grammar.md` from the Action Protocol section so Claude reaches the detailed click/observation parsing instead of duplicating grammar inline.

Replace the redundant second example with one demonstrating the click/select path, or sequence an explicit search -> evaluate -> click workflow with a validation checkpoint against the user's constraints.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence, but the two examples are near-identical (both `search[...]` for a product under a price ceiling), so the second adds little and could be tightened.	2 / 3
Actionability	Provides exact action grammar (`search[<keywords>]`, `click[<product_id>]`) with concrete, filled examples that are effectively copy-paste ready for an instruction-only skill.	3 / 3
Workflow Clarity	Edge cases give some recovery guidance (0 results -> broaden; price exceeded -> adjust terms), but the search-to-click sequence is not laid out as an explicitly validated workflow and no example demonstrates the click path.	2 / 3
Progressive Disclosure	Sections are well-organized, but the bundled `references/action_grammar.md` (detailed click-value and observation parsing) is never linked or signaled from the body, and part of the grammar is duplicated inline.	2 / 3
	Total	9 / 12 Passed

Description

75%

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 well-structured with an explicit trigger clause and a clear, distinctive niche, but its action coverage is narrow and the trigger phrasing targets the orchestrator's internal state rather than natural user language.

Suggestions

Reframe the trigger around natural user intent (e.g., "Use when the user wants to find or buy a product on WebShop") rather than the agent's internal pipeline state.

Broaden the specificity beyond restating 'search' by noting the full capability set (search, then select/click a product from results).

Dimension	Reasoning	Score
Specificity	Names a concrete domain and action ("Executes a search on an e-commerce platform", "performs the actual search[] action", "returning a list of product results"), but restates one action several ways rather than listing multiple distinct capabilities.	2 / 3
Completeness	Clearly states what it does (executes a search, returns product results) and an explicit "Use when..." trigger clause, answering both what and when.	3 / 3
Trigger Term Quality	Includes relevant terms like "search" and "product", but the trigger is framed around the agent's pipeline state ("when you have extracted search terms from a user query") rather than language a user would naturally say.	2 / 3
Distinctiveness Conflict Risk	Scoped to the WebShop e-commerce search interface with a distinct single-purpose trigger, making it unlikely to fire for unrelated skills.	3 / 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-search-executor/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.