webshop-product-detail-inspector

This skill examines a product detail page to verify specific attributes or select options like size, color, or quantity. It is used after clicking on a product, to confirm that the item matches the user's needs (e.g., checking for '10 slots' option, price, material). The input is the product page observation, and the output is an action to select a required variant (e.g., click[10 slots]) or proceed if criteria are satisfied.

Quality

68%

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-product-detail-inspector/SKILL.md

Quality

Content

53%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 its decision logic is clearly laid out, but it is undermined by an Output Format section that promises a format and then provides none, and by two existing reference files that are never signaled from the body. The exact action syntax the output depends on is effectively undiscoverable.

Suggestions

Complete the Output Format section with the exact response format (e.g., a one-line action such as click[10 slots] / click[Back to Search] / click[Buy Now]) — it currently ends mid-promise with nothing following.

Reference the bundle files from the body, e.g., 'Action syntax and exact-match rules: see references/action_guidelines.md' and 'Worked example trajectory: see references/trajectory_example.md'.

Inline the critical action constraints (actions must be exact case-sensitive matches from the observation's action list) so the skill is executable without the unreferenced file.

Dimension	Reasoning	Score
Conciseness	The body is lean and well-sectioned with no explanations of concepts Claude already knows; only minor trimmable context-setting ('You are an agent navigating a web shop. Your current task is to inspect a product detail page.'). Not 5 because the Purpose section partially repeats the frontmatter description.	4 / 5
Actionability	Core Logic gives concrete examples ('10 slots', '< $60', 'Back to Search', 'Buy Now'), but the Output Format section ends at 'Your response must be in this exact format:' with no format shown, and the exact case-sensitive action syntax is not provided inline. Not 4 because the most execution-critical detail (the response format) is missing.	3 / 5
Workflow Clarity	The three decision branches (select option / go back / proceed) are clearly sequenced, but the final step is ambiguous because the promised output format is truncated. Not 4 because a key output checkpoint is absent rather than merely implicit; not 2 because the decision sequence itself is well defined.	3 / 5
Progressive Disclosure	Two one-level-deep bundle files exist (references/action_guidelines.md with the exact action syntax, references/trajectory_example.md with a worked example), but the body never mentions or links either, leaving critical guidance buried. Not 3 because even a weakly-signaled reference ('See X.md') is absent; not 1 because the body itself has clear section structure and references are only one level deep.	2 / 5
	Total	12 / 20 Passed

Description

67%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.

The description clearly states what the skill does, when it applies, and what it outputs, with a concrete action example. Its main weaknesses are limited natural trigger-term coverage and a 'when' clause that could use more explicit trigger phrasing.

Suggestions

Broaden natural trigger terms and synonyms, e.g., 'Use when inspecting a product page, checking a variant or option (size, color, quantity, slots), or verifying price before buying.'

Mention the rejection path in the what-clause (e.g., 'or go back to search if criteria are not met') so the full behavior is covered.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('examines a product detail page to verify specific attributes or select options like size, color, or quantity', 'the output is an action to select a required variant (e.g., click[10 slots])') with a literal action example. Not 5 because coverage has minor gaps (e.g., the back-to-search rejection path is omitted); not 3 because it goes beyond 1-2 actions with concrete illustrations.	4 / 5
Completeness	Has a clear 'what' (examine/verify attributes, select variants, emit an action) and an explicit 'when' ('It is used after clicking on a product, to confirm that the item matches the user's needs'). Not 5 because the when-clause lacks concrete trigger phrases; not 3 because the trigger guidance is explicit, not merely implied.	4 / 5
Trigger Term Quality	Relevant keywords like 'size, color, or quantity', 'price', 'material', and '10 slots' are present, but common variations and natural user phrasings ('product page', 'variant', 'pick an option') are missing. Falls between anchor 3 and 4, closer to 3 due to thin natural-term coverage.	3 / 5
Distinctiveness Conflict Risk	The niche (post-click product detail inspection and variant selection in a webshop) is distinct with clear triggers. Not 5 due to minor overlap risk with a general webshop search/navigation skill; not 3 because the scope is well-bounded to the detail-page stage.	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-product-detail-inspector/SKILL.md
Commit: 358ec82

Reviewed: 8 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.