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

73%

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

57%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 body is concise and sensibly sequenced, but actionability and workflow clarity are undermined by a missing bundled script, an empty output-format section, and no validation step for a batch operation. Reference files exist but are never linked from the body.

Suggestions

Provide the referenced `analyze_results.py` (in a scripts/ directory) or replace the script delegation with concrete inline scoring logic, since the file is currently absent from the bundle.

Fill in the Step 4 output format that is currently promised but left blank.

Add an explicit validation/verification checkpoint (e.g., confirm each candidate meets the price constraint before presenting) since this is a batch operation over multiple listings.

Link the existing reference files (attribute_patterns.md for match patterns, execution_example.md for a worked example) from the relevant steps so progressive disclosure is clearly signaled.

Dimension	Reasoning	Score
Conciseness	The body is lean and well-sectioned with no over-explanation of concepts Claude already knows, but contains minor trimmable padding such as 'to perform a consistent, deterministic analysis' and 'for comparison against the budget'.	4 / 5
Actionability	Step 2 gives concrete extraction guidance (Product ID like B09GXNYJCD, converting a price range to its max), but the critical scoring step delegates to a bundled `analyze_results.py` that is not present in the bundle, and Step 4 promises an output format that is left empty.	3 / 5
Workflow Clarity	Steps 1–4 are clearly sequenced, but this is a batch operation over multiple listings with no validation or verification checkpoints, and the final output format is missing — the batch-operation cap at 3 applies.	3 / 5
Progressive Disclosure	Section structure (## 1–4) is reasonable, but the body references `analyze_results.py` (absent from the bundle) while never linking the two reference files that actually exist (attribute_patterns.md, execution_example.md), so references are not clearly signaled or matched to the bundle.	3 / 5
	Total	13 / 20 Passed

Description

88%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 strong, concrete description that clearly states capabilities and an explicit trigger condition in third person. Trigger terms are good but could add more natural synonyms to fully distinguish the skill from generic search-result handling.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — 'evaluates a list of search results against the target product criteria', 'analyzes each result's title, price, and brief description', 'shortlist items', 'outputting a prioritized list of candidate product IDs or links' — with comprehensive coverage of what the skill does.	5 / 5
Completeness	Explicitly answers both what ('evaluates... analyzes... shortlist... outputting a prioritized list') and when ('Trigger it when a search result page is observed') with a concrete trigger phrase.	5 / 5
Trigger Term Quality	Includes natural terms like 'search result page', 'search results', and 'product listings' that a user would say, but lacks synonyms or variations (e.g., 'search results page', 'product search'); good coverage with a few natural terms missing.	4 / 5
Distinctiveness Conflict Risk	The webshop product-search niche is mostly distinct, but the trigger 'search result page' is somewhat generic and could overlap with non-product search-result skills, giving minor conflict risk.	4 / 5
	Total	18 / 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-result-analyzer/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.