webshop-product-evaluator

Evaluates product listings against user requirements such as price limits and feature matches to identify viable options. Use when you are on a search results page containing multiple products and need to select the most promising candidate for detailed inspection. The skill analyzes product titles, prices, and brief descriptions to rank and choose the best match.

Quality

88%

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

Quality

Content

92%

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

A concise, highly actionable skill body with a clearly sequenced workflow and a strong worked example. The one gap is progressive disclosure: an existing reference file is not linked from the body, leaving navigation implicit.

Suggestions

Add a one-line pointer in the body (e.g., under Core Process) to references/evaluation_logic.md so the bundled reference is clearly signaled rather than orphaned.

Optionally deduplicate the parsing/selection heuristics between the body and evaluation_logic.md, keeping the body to the high-level workflow and deferring detail to the reference.

Consider surfacing the price-ascending tie-break rule from the reference directly in the Evaluate step so the selection policy is visible without loading the reference.

Dimension	Reasoning	Score
Conciseness	The body is lean — it skips concept explanations Claude already knows, presents a tight four-step process, and every section earns its place; the only mild redundancy ("When to Use" echoing the description) is not enough to drop it below the level-3 lean anchor.	3 / 3
Actionability	Gives concrete executable actions (`click[B09NYFDNVX]`, `search`, `click[Next >]`) plus a fully worked example with real ASINs, prices, and a Thought/Action template — copy-paste ready, matching the level-3 anchor.	3 / 3
Workflow Clarity	The Parse → Extract Requirements → Evaluate → Take Action sequence is clearly ordered with an explicit fallback branch (refine search or Next); per the simple-skill note, no validation checkpoint is required for this non-destructive selection task, so it reaches level 3.	3 / 3
Progressive Disclosure	Sections are well-organized, but the bundled references/evaluation_logic.md exists and duplicates/extends the body's logic yet is never linked or signaled from SKILL.md, fitting the level-2 anchor "references present but not clearly signaled" rather than the level-3 well-signaled one.	2 / 3
	Total	11 / 12 Passed

Description

85%

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 well-constructed description that clearly states both capability and an explicit use-when trigger, with a distinctive webshop niche. Its only weakness is trigger-term naturalness, leaning on environment state rather than the phrasings a user would naturally voice.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "Evaluates product listings against user requirements," "analyzes product titles, prices, and brief descriptions to rank and choose the best match" — matching the level-3 anchor rather than the level-2 single-domain example.	3 / 3
Completeness	Explicitly answers both what ("Evaluates product listings... analyzes... to rank and choose") and when ("Use when you are on a search results page containing multiple products"), matching the level-3 anchor with an explicit Use-when clause.	3 / 3
Trigger Term Quality	The trigger "Use when you are on a search results page containing multiple products and need to select the most promising candidate" is state-based with some relevant terms but lacks common natural variations a user would say (e.g., "compare products," "pick a product," "shopping"), so it sits at level 2 rather than level 3.	2 / 3
Distinctiveness Conflict Risk	The webshop search-results selection niche ("search results page containing multiple products," "select the most promising candidate for detailed inspection") is clearly distinct and unlikely to trigger for unrelated skills.	3 / 3
	Total	11 / 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-product-evaluator/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.