webshop-search-formulator

This skill generates effective search keywords based on parsed product criteria. It is triggered after query parsing, when the agent needs to perform an initial product search on an e-commerce platform. The skill takes structured attributes (e.g., 'women's size 5 patent-beige high heel') and produces a concise, platform-appropriate search string designed to return relevant results, balancing specificity with recall.

Quality

57%

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/webshop/webshop-search-formulator/SKILL.md

Quality

Content

51%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.

Well-organized, lean content with a real referenced bundle file, but the document ends mid-sentence in the Action Format section, omitting the exact action template and a concrete final example — the one thing the skill is meant to produce.

Suggestions

Complete the 'Action Format' section with the literal template (e.g. `search[keywords]`) and 1-2 concrete worked examples of the final action string.

Add a brief validation/self-check step (confirm output matches the `search[...]` format and excludes post-search filters) before emitting the action.

Dimension	Reasoning	Score
Conciseness	Mostly lean instructional prose that assumes Claude's competence, with only minor over-explanation (e.g. defining 'Balance Specificity & Recall' at slight length). No padding with concepts Claude already knows.	4 / 5
Actionability	The body promises a single `search[keywords]` action and the Action Format section declares 'Your final output must be a single action in the exact format:' but then cuts off with no actual format template or concrete example, leaving the single most actionable element missing.	2 / 5
Workflow Clarity	A clear input-process-output sequence is present and a worked trajectory example grounds it, but there are no validation checkpoints; since this skill emits a single non-destructive action the missing-feedback cap does not strictly apply, yet the truncated action format leaves the terminal step ambiguous.	3 / 5
Progressive Disclosure	SKILL.md is an organized overview with clearly signaled one-level-deep reference to references/search_strategy_guide.md, and the referenced file exists and holds the deeper detail; only minor organization gaps remain.	4 / 5
	Total	13 / 20 Passed

Description

63%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.

A clear, third-person description that names concrete inputs and outputs and includes an explicit trigger clause. It is somewhat verbose and the trigger is framed as an internal agent event rather than natural user phrasing.

Suggestions

Add a 'Use when...' clause with natural user phrases (e.g. 'Use when searching for products on an e-commerce site or when the user asks to find/shop for an item').

Tighten the prose; the explanation of balancing specificity with recall reads as mild padding and could be trimmed.

Dimension	Reasoning	Score
Specificity	States concrete inputs (structured attributes such as 'women's size 5 patent-beige high heel') and a concrete output (a concise platform-appropriate search string), but does not enumerate multiple distinct actions.	4 / 5
Completeness	Clearly answers 'what' (generates search keywords) and gives a 'when' clause ('It is triggered after query parsing, when the agent needs to perform an initial product search'), though the trigger is phrased as agent-internal rather than a user-facing 'Use when...' phrase.	4 / 5
Trigger Term Quality	Contains relevant terms like 'product search', 'search keywords', and 'e-commerce platform', but lacks the natural variations a user might say (e.g. 'shopping', 'find products', 'Amazon search').	3 / 5
Distinctiveness Conflict Risk	The 'initial product search on an e-commerce platform' niche is fairly distinct with minimal overlap risk against other skills, though it could conceivably overlap with a broader product-browsing skill.	4 / 5
	Total	15 / 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-formulator/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.