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

75%

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

63%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 clearly sequenced with a good worked example, but its central executable step depends on a script that is neither present in the bundle nor given an invocation command, and the one real reference file is never linked. Fixing the script reference and wiring up action_format.md would raise both actionability and progressive disclosure.

Suggestions

Ship the actual `selector.py` in a scripts/ directory and give its invocation in step 2 (e.g., `python scripts/selector.py --max-price 50 --requirements "portable double horn easy to carry"`), or inline the selection logic if the script is not bundled.

Reference `references/action_format.md` from the body (e.g., in step 3) so the verbatim-value and case-sensitivity rules for `click[value]` are discoverable instead of orphaned.

Add an explicit validation checkpoint in step 3: confirm the selected product_id appears in the observation's clickable actions before executing `click[product_id]`.

Dimension	Reasoning	Score
Conciseness	The body is lean with no padding and no explanation of concepts Claude already knows. Not 5 because the three bullets describing the script's internal filtering/scoring logic and the example's Thought paragraph partially restate what step 2 already specifies, and could be trimmed.	4 / 5
Actionability	The action format "click[product_id]" and the fully worked example are concrete, but the central step — "Use the bundled `selector.py` script" — gives no path and no invocation command, and no such script exists in the bundle (no scripts/ directory). This is a major executability gap rather than a minor one, matching the 'incomplete / missing key details' anchor rather than 'mostly executable'.	3 / 5
Workflow Clarity	A clear three-step sequence (assess list → apply selection heuristic → execute click) with the output action format pinned and a thought-process template. Not 5 because verification is only implicit ("for final verification and purchase") rather than an explicit checkpoint confirming the selected product_id is clickable.	4 / 5
Progressive Disclosure	Sections are well organized for a short skill, but reference integrity is broken: the body points to a nonexistent bundled script (`selector.py` is not in the bundle) while the existing `references/action_format.md` — which contains the critical verbatim/case-sensitivity rule for `click[value]` — is never referenced from the body, leaving a real reference buried.	3 / 5
	Total	14 / 20 Passed

Description

87%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 description: third-person, concrete about the action and its output format, with an explicit and specific 'Use when' clause. Trigger coverage is good though a few natural synonyms are missing.

Dimension	Reasoning	Score
Specificity	"Selects the most promising product candidate from a filtered shortlist" and "Triggers navigation to the selected product's detail page via click[product_id]" name concrete actions with the exact action format. Not 5 because it covers only two actions in a narrow scope rather than multiple comprehensive capabilities; not 3 because it goes beyond naming the domain to specify the selection action and its output mechanism.	4 / 5
Completeness	Explicitly answers both: what ("Selects the most promising product candidate from a filtered shortlist for detailed inspection") and when ("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") with concrete trigger conditions and the output action.	5 / 5
Trigger Term Quality	Natural phrases users would say are present: "search results page", "multiple viable items", "best feature match", "lowest price". Not 5 because common variations such as "choose/pick a product", "compare prices", or "product detail page" are absent, leaving a few natural terms missing.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche — final selection from a filtered shortlist on a search results page — with distinct triggers that would not fire for search-initiation or page-inspection skills. Minimal conflict risk.	5 / 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-product-selector/SKILL.md
Commit: c490239

Reviewed: 30 minutes 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.