CtrlK
BlogDocsLog inGet started
Tessl Logo

webshop-option-selector

This skill selects product options or variants (such as size, color, or quantity) on a product detail page based on user preferences or cost optimization. It should be triggered when a product page displays configurable options. The skill evaluates available choices (e.g., 1pcs vs 2pcs) and selects the one that best aligns with the user's constraints, such as minimizing cost.

62

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./experiments/src/skills/webshop/webshop-option-selector/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

71%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 admirably lean with a clear trigger condition, ordered workflow, and concrete action syntax, but it is undermined by an empty, truncated "Example from Trajectory" section and a bundle reference file that is never linked from the skill. Fixing the dangling example and surfacing references/strategy_docs.md would raise both weak dimensions.

Suggestions

Complete or remove the truncated "Example from Trajectory" section: add a real observation excerpt, the option values present, the strategy applied, and the resulting `click[value]` action so the promised concrete example actually exists.

Link references/strategy_docs.md from the body (e.g., under a "Selection strategies" section: "See [strategy_docs.md](references/strategy_docs.md) for strategy details and edge cases") so the bundled reference is discoverable rather than orphaned.

Add a verification step after executing the selection, such as re-reading the displayed price to confirm the expected option was selected before proceeding to `click[buy now]`.

DimensionReasoningScore

Conciseness

The ~24-line body is lean and efficient: trigger conditions, a three-step core logic, and short precedence/fallback notes with no padding and no explanation of concepts Claude already knows. Every token earns its place, matching the anchor for lean, competence-assuming content.

5 / 5

Actionability

Concrete guidance exists — the `click[value]` action format, the "select the value that results in the lowest final price" rule, the user-preference override, and the "select the first available option" fallback — but the "Example from Trajectory" section terminates at "**Observation Excerpt:**" with no example following it. The dangling, empty example section is a key missing detail, so this is not the mostly-complete guidance of a 4.

3 / 5

Workflow Clarity

The Core Logic section gives a clear, ordered sequence (parse observation → apply selection strategy → execute click in page order) with edge cases addressed in Important Notes. It lacks a post-click verification checkpoint (e.g., confirming the price updated), which is the minor validation gap that keeps it below 5.

4 / 5

Progressive Disclosure

The body is well-sectioned and under 50 lines, but the bundle contains references/strategy_docs.md, which is never mentioned or linked anywhere in SKILL.md — an orphaned, undiscoverable reference whose content (strategies, edge cases) partially duplicates the body. Per the guideline to score against the actual bundle structure, un-signaled references anchor this at 3 rather than the simple-skill 5.

3 / 5

Total

15

/

20

Passed

Description

75%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 that clearly and concretely states both what the skill does and when it should trigger, in third person with natural trigger terms. The main room for improvement is making the trigger condition more specific (naming the environment and concrete page signals) and broadening keyword coverage.

DimensionReasoningScore

Specificity

The description lists several concrete actions with specific examples — "selects product options or variants (such as size, color, or quantity)", "evaluates available choices (e.g., 1pcs vs 2pcs)", "selects the one that best aligns with the user's constraints, such as minimizing cost". It falls short of 5 because coverage is narrower than the skill's actual behavior (no mention of parsing the page state or executing click actions), but exceeds 3 since it goes beyond 1-2 generic actions.

4 / 5

Completeness

Both what ("selects product options or variants... based on user preferences or cost optimization") and when ("It should be triggered when a product page displays configurable options") are explicitly present in third person. The when-clause is explicit but generic — it does not name the concrete page signals (e.g., a "Price:" field) that would make it a 5.

4 / 5

Trigger Term Quality

It includes natural keywords a user or environment would surface — "size", "color", "quantity", "product detail page", "variants", "options", "cost". A few natural terms are missing (e.g., "product page" alone, the WebShop environment name, "add to cart" context), keeping it below the comprehensive synonym coverage of a 5.

4 / 5

Distinctiveness Conflict Risk

The niche is clear — selecting configurable product options/variants on a product detail page — with distinctive terms like "1pcs vs 2pcs" and "configurable options". There is minor overlap risk with a generic add-to-cart/purchase skill, so it does not reach the minimal-conflict clarity of a 5.

4 / 5

Total

16

/

20

Passed

Validation

100%

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
Reviewed

Table of Contents

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.