CtrlK
BlogDocsLog inGet started
Tessl Logo

webshop-variant-chooser

This skill selects a product variant (e.g., size, quantity) from available options on a product detail page. It is triggered when a product page displays multiple choices, assessing the options (like '1.1 pound (pack of 1)' or 'pack of 2') and selecting one that aligns with user needs, often defaulting to a standard single unit if unspecified.

56

Quality

64%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./experiments/src/skills/webshop/webshop-variant-chooser/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

61%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.

A concise, well-structured instruction body for a simple skill, undermined by an incomplete 'Action Format' section that omits the promised response format and lacks validation guidance.

Suggestions

Complete the 'Action Format' section by providing the exact response format promised after 'Your response must strictly follow this format:'.

Add a brief validation/verify step (e.g., confirm the clicked variant's displayed price/details match the user constraint) before finalizing the selection.

Link the trajectory reference explicitly, e.g. 'as shown in the [trajectory](references/trajectory.md)', so the bundled reference is clearly signaled.

DimensionReasoningScore

Conciseness

The body is lean and avoids explaining concepts Claude already knows; every section earns its place, with only minor tightening possible.

4 / 5

Actionability

Decision logic and the click[value] action are concrete, but the 'Action Format' section is truncated ('Your response must strictly follow this format:' with no format shown), leaving executable guidance incomplete.

3 / 5

Workflow Clarity

Steps are clearly sequenced (Parse, Assess, Select and Act), but there are no validation checkpoints and the truncated Action Format section leaves the final action ambiguous.

3 / 5

Progressive Disclosure

Short, well-organized body for a simple single-purpose skill; the trajectory reference is signaled informally but not linked via a markdown path to references/trajectory.md.

4 / 5

Total

14

/

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.

A clear, mostly well-scoped description that names concrete actions and an explicit trigger. Trigger term coverage and comprehensiveness have minor room to improve.

DimensionReasoningScore

Specificity

Names the domain ('selects a product variant') with several concrete actions (assess options, select one, default to single unit) and concrete examples, but coverage is not fully comprehensive.

4 / 5

Completeness

Both 'what' (selects a variant from available options) and 'when' ('It is triggered when a product page displays multiple choices') are present and fairly explicit, though the trigger phrasing could be slightly more concrete.

4 / 5

Trigger Term Quality

Relevant keywords like 'product variant', 'size, quantity', and 'product detail page' are present, but it leans specialized and misses common user phrasings or synonyms.

3 / 5

Distinctiveness Conflict Risk

The product-variant-selection niche is well-scoped to product detail pages with minimal overlap risk; only minor overlap with closely related shopping skills.

4 / 5

Total

15

/

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.

Validation16 / 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.