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

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-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 well-organized and concise with a clear decision process and a useful worked example, but its actionability and file structure are undermined by a missing referenced script and an orphaned, unlinked reference file.

Suggestions

Either add the bundled scripts/selector.py implementing the described filter/score/tiebreak heuristic, or replace the "Use the bundled selector.py script" instruction with the concrete algorithm expressed as runnable code so the guidance is executable as written.

Link references/action_format.md explicitly from the body (e.g., "See [action_format.md](references/action_format.md) for the click[value] rules") so the existing reference is clearly signaled and discoverable.

Add an explicit validation checkpoint in the Decision Process — e.g., a step verifying the selected product_id appears in the current observation's available actions before emitting click[product_id].

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence without explaining what products or search results are; the worked example is detailed but earns its place as a template demonstration, with only minor redundancy between the opening line and the description (anchor 4).	4 / 5
Actionability	The selection heuristic is described in prose (filter by max price, score keyword matches, tiebreak by lowest price) and the action format click[product_id] is concrete, but the recommended bundled selector.py script is not present in the bundle and no executable code is shown, leaving the guidance incomplete (anchor 3, pseudocode-like rather than executable).	3 / 5
Workflow Clarity	A clear three-step sequence (Assess the List, Apply Selection Heuristic, Execute Action) is provided and the operation is a single non-destructive click, so the destructive/batch cap does not apply; validation is only weakly signaled via the reference's "ensure the product_id is present" note rather than an explicit checkpoint in the main flow (anchor 4).	4 / 5
Progressive Disclosure	The body is well-sectioned but its file references are inconsistent with the actual bundle: selector.py is referenced but absent, and references/action_format.md exists but is never linked from the body, so references are not clearly signaled and structure is misaligned (anchor 3).	3 / 5
	Total	14 / 20 Passed

Description

83%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 is third-person, concise, and clearly states both the capability and the trigger conditions with concrete action format. It is strong overall, with only minor gaps in action coverage and trigger synonyms.

Dimension	Reasoning	Score
Specificity	Names concrete actions — "Selects the most promising product candidate from a filtered shortlist" and "Triggers navigation to the selected product's detail page via click[product_id]" — covering selection and the click action, but the action set is narrow so coverage is not fully comprehensive (anchor 4).	4 / 5
Completeness	Explicitly answers both what ("Selects the most promising product candidate...") and when ("Use when you are on a search results page with multiple viable items and need to make a final selection...") with concrete trigger phrases, matching the anchor-5 example.	5 / 5
Trigger Term Quality	Includes natural terms a user would say such as "search results page", "multiple viable items", "best feature match", and "lowest price"; good coverage but a few common synonyms (e.g., "shortlist", "pick", "choose") are missing (anchor 4).	4 / 5
Distinctiveness Conflict Risk	The shortlist-selection niche with a price/keyword heuristic is fairly distinct, but it could overlap with adjacent WebShop navigation skills, so minor overlap risk remains (anchor 4 rather than 5).	4 / 5
	Total	17 / 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: 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.