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.

59

Quality

68%

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

57%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 decision logic is well structured and token-efficient, but the skill is critically incomplete: the "Action Format" section promises a strict format and then the file ends, so the exact response format is never specified. The sole bundle reference (trajectory.md) is neither linked by path nor complete, compounding the incompleteness.

Suggestions

Complete the "Action Format" section — the body ends with "Your response must strictly follow this format:" and no format follows; add the exact response template (e.g., the precise `click[value=...]` output string).

Replace the oblique mention "as shown in the trajectory" with an explicit path link to [trajectory.md](references/trajectory.md), and finish that file — it currently ends at an empty "Observation 1 (Search Results Page):" heading.

Add an explicit verification checkpoint after selection (e.g., re-check that the clicked variant still satisfies a stated price constraint before finalizing) rather than leaving verification implicit in a 'may need to' bullet.

DimensionReasoningScore

Conciseness

The body is lean and assumes competence (e.g., "Identify the list of available variant options from the observation text") with no padding explaining known concepts. Minor redundancy: "Use this skill when you are on a product detail page and the observation contains a list of variant options" followed by "The skill is triggered by the presence of multiple clickable options" repeats the same trigger twice in one paragraph. Not 5 due to that duplication; not 3 since the rest is efficient.

4 / 5

Actionability

Quotes: "execute a `click[value]` action", "Ensure the selected variant's price (if displayed) complies", "Prefer the standard, single-unit option" — concrete decision rules exist. However the "Action Format" section ends with "Your response must strictly follow this format:" and the file ends there; the required response format is never shown. Not 4: a key executable detail is missing entirely; not 2: the steps and action token are specific, not high-level hints.

3 / 5

Workflow Clarity

A clear 1-2-3 sequence (Parse → Assess → Select) with decision branches, and a verify-before-commit bullet ("You may need to click on a variant to see its updated price/details before finalizing the selection"). But the workflow's terminal step — the required output format — is severed by the truncated "Action Format" section, leaving the final checkpoint missing. Not 4: the gap is not minor; not 2: the sequence itself is well defined. This is a single low-risk click action, so the destructive/batch cap is not triggered.

3 / 5

Progressive Disclosure

Sections ("When to Use", "Core Decision Logic", "Action Format") are well organized and the body is short, but the only bundle file, references/trajectory.md, is referenced obliquely as "as shown in the trajectory" with no path or link, and the trajectory file itself is truncated (ends at an empty "Observation 1 (Search Results Page):" heading). The reference is present but not clearly signaled or navigable. Not 4: an unreferenced-by-path, incomplete file is more than a minor organization gap; not 2: the body's own structure is good.

3 / 5

Total

13

/

20

Passed

Description

78%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: it states a concrete capability, gives an explicit trigger condition, and anchors the behavior with realistic examples. It is specific and distinctive, though the trigger phrasing is system-voiced rather than user-oriented and could include a few more natural synonym phrases.

DimensionReasoningScore

Specificity

Quotes: "selects a product variant (e.g., size, quantity) from available options", "assessing the options (like '1.1 pound (pack of 1)' or 'pack of 2')", "defaulting to a standard single unit if unspecified". Names the domain and several concrete actions with illustrative examples. Not 5: the actions are one composite selection workflow rather than comprehensive coverage; not 3: multiple specific actions are listed beyond the 1-2 anchor.

4 / 5

Completeness

Quotes: what — "selects a product variant... from available options on a product detail page"; when — "It is triggered when a product page displays multiple choices". Both what and an explicit trigger clause are present, so the 3-cap for missing 'Use when...' guidance does not apply. Not 5: the trigger is phrased from the system's perspective rather than as concrete user-side trigger phrases; not 3: the 'when' is explicitly stated, not merely implied.

4 / 5

Trigger Term Quality

Quotes: "size, quantity", "product detail page", "displays multiple choices", "pack of 2", "single unit". Good coverage of natural terms a user or observation would contain for this domain. Not 5: missing common variations like "product options", "select size", or "choose quantity"; not 3: the terms present go well beyond a bare domain mention.

4 / 5

Distinctiveness Conflict Risk

Quotes: "selects a product variant... on a product detail page", "multiple choices". A clear niche (variant selection on product pages in a shopping environment) with distinct triggers; minimal conflict risk with other skill domains. Not 4: no meaningful overlap with related skills is apparent.

5 / 5

Total

17

/

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.