webshop-result-analyzer

This skill evaluates a list of search results against the target product criteria. Trigger it when a search result page is observed, to identify promising product listings. It analyzes each result's title, price, and brief description to shortlist items that best match the required attributes (like size, color, and price), outputting a prioritized list of candidate product IDs or links for further inspection.

Quality

71%

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-result-analyzer/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.

A concise, well-structured instruction body that respects Claude's intelligence, but it loses actionability and workflow clarity by delegating the core scoring to a bundled script with no invocation spec and leaving the output template empty. Reference files exist but are not signaled from the body.

Suggestions

Add a concrete invocation example for `analyze_results.py` (command, arguments, expected output) so the scoring step is copy-paste executable rather than a black box.

Complete the section 4 output format with an actual template/example instead of the trailing "Present the analysis in this format:" with nothing after it.

Link the existing reference files from the body (e.g., "See [attribute_patterns.md](references/attribute_patterns.md) for regex patterns") so progressive disclosure is clearly signaled.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence — it gives the input format, the attribute categories, and the matching procedure without explaining what a product listing or a price range is. Every line earns its place.	3 / 3
Actionability	It points to a bundled script ("Use the bundled Python script `analyze_results.py`") but gives no invocation example, arguments, or return format, so Claude cannot execute it concretely without inspecting the script. The attribute extraction steps are concrete but the core scoring step is delegated without an executable spec.	2 / 3
Workflow Clarity	Steps are numbered and sequenced (Extract → Analyze → Score → Output), but there is no validation or verification checkpoint, and section 4's output format is left as an empty "Present the analysis in this format:" with no actual template.	2 / 3
Progressive Disclosure	Content is organized into clear numbered sections and two real reference files exist (attribute_patterns.md, execution_example.md), but the body does not actually link to or signal them with paths, and execution_example.md appears truncated/empty, so navigation is not clearly signaled.	2 / 3
	Total	9 / 12 Passed

Description

77%

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 strong, specific description that clearly conveys both what the skill does and when to use it. The main weakness is trigger-term coverage, which leans on the generic "search result page" rather than natural shopping/e-commerce language a user would say.

Suggestions

Add natural shopping trigger terms a user would actually say (e.g., "shopping results", "Amazon search results", "product listings", "e-commerce search") alongside "search result page".

Sharpen the trigger to reduce overlap with non-shopping search skills, e.g. "Trigger when observing an e-commerce product search result page with multiple listings to compare."

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "evaluates a list of search results", "analyzes each result's title, price, and brief description to shortlist items", and "outputting a prioritized list of candidate product IDs or links".	3 / 3
Completeness	Explicitly states what it does ("evaluates a list of search results against the target product criteria") and when to trigger ("Trigger it when a search result page is observed"), satisfying both the what and the when with an explicit trigger.	3 / 3
Trigger Term Quality	Includes some relevant user-facing terms ("search result page", "product listings") but misses common variations users would naturally say such as "shopping", "e-commerce", "Amazon results", or "buy".	2 / 3
Distinctiveness Conflict Risk	The product-search shortlisting niche is fairly specific, but the trigger "search result page" is generic and could overlap with general web-search or document-search skills.	2 / 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-result-analyzer/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.