webshop-product-selector

Selects the most promising product candidate from a filtered shortlist for detailed inspection. Use when you are on a search results page with multiple viable items and need to make a final selection based on a heuristic such as best feature match or lowest price. Triggers navigation to the selected product's detail page via click[product_id].

Quality

78%

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-selector/SKILL.md

Quality

Content

72%

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 well-structured with a strong worked example, but actionability and workflow clarity are capped because it directs Claude to a bundled selector.py script that is not present and omits any verification checkpoint before the final selection action.

Suggestions

Either ship scripts/selector.py with a documented invocation (e.g., 'python scripts/selector.py <observation>') or replace the script reference with an inline, runnable selection procedure.

Add an explicit verification checkpoint to the Decision Process — e.g., confirm the selected product_id appears in the current observation's clickable actions and matches the expected case before emitting click[product_id].

Reconcile the click value casing: the reference warns product IDs are often lowercase (b093c1thvp) while the example uses uppercase (B093C1THVP); clarify which casing the action requires.

Dimension	Reasoning	Score
Conciseness	The ~30-line body is lean, assumes Claude's competence, avoids explaining basic concepts, and every section (decision process, template, worked example) earns its place.	3 / 3
Actionability	It gives the concrete click[product_id] format, the selector's filter/score/tie-break logic, and a full worked example, but the central instruction to 'Use the bundled selector.py script' references a non-existent file with no runnable invocation or inline fallback, leaving key details missing.	2 / 3
Workflow Clarity	The three-step Assess/Apply/Execute sequence and thought template are clear, but the workflow has no validation checkpoint before committing to a single product and depends on an absent script, so it caps at the 'steps listed but validation gaps' anchor.	2 / 3
Progressive Disclosure	This short single-purpose skill is a concise overview with a real one-level-deep reference (references/action_format.md) and well-organized sections, meeting the simple-skill allowance for a top score.	3 / 3
	Total	10 / 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.

The description clearly conveys both purpose and trigger conditions with concrete actions and a distinct niche. Trigger-term quality is the only moderate dimension because the keywords are scenario-based rather than densely varied user phrasings.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — selecting a candidate via heuristic ('best feature match or lowest price') and triggering navigation 'via click[product_id]' — so it meets the comprehensive-actions anchor rather than the partial score 2.	3 / 3
Completeness	Explicitly states what it does (select a candidate, navigate to detail page) and includes an explicit 'Use when you are on a search results page...' trigger clause, satisfying both what and when.	3 / 3
Trigger Term Quality	Phrases like 'search results page with multiple viable items' and 'make a final selection' are natural but situational, lacking the broad set of common keyword variants users would say, matching the 'some relevant keywords but missing variations' anchor.	2 / 3
Distinctiveness Conflict Risk	The WebShop search-results product-selection niche with a click[product_id] action is a clear, distinct trigger set unlikely to overlap with other 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-selector/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.