CtrlK
BlogDocsLog inGet started
Tessl Logo

webshop-query-interpreter

Interprets a user's shopping query to extract key product requirements such as item type, attributes, and constraints. Use when a new shopping instruction is received and you need to parse natural language into structured criteria (product category, desired features, price limits) before performing a search. The output is a clear set of search parameters for use in subsequent product lookup steps.

62

Quality

73%

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-query-interpreter/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.

A concise, actionable skill body with a clear process and good worked examples. Its main gaps are the un-signaled reference bundle and missing edge-case handling for ambiguous queries.

Suggestions

Link the existing reference files from the body (e.g., 'See references/query_patterns.md for linguistic patterns, currency formats, and edge cases') so the bundle is discoverable rather than orphaned.

Resolve the Hand Off ambiguity by naming a single target skill and its exact invocation, instead of offering 'webshop-search-executor or webshop-product-search'.

Add a brief validation/edge-case step (e.g., if no product type is identifiable or a constraint is ambiguous, ask the user to clarify) to round out the workflow.

DimensionReasoningScore

Conciseness

The body is lean and mostly assumes Claude's competence, but the two full worked examples largely duplicate the same pattern, which is minor over-explanation that could be trimmed.

4 / 5

Actionability

Provides a concrete copy-paste output template plus two fully worked examples, but the Hand Off step names two alternative skills ('webshop-search-executor or webshop-product-search') leaving ambiguity about which to call.

4 / 5

Workflow Clarity

A clearly sequenced three-step process (Parse, Structure, Hand Off) demonstrated by examples, but it lacks any guidance for edge cases such as ambiguous or incomplete queries.

4 / 5

Progressive Disclosure

The body is well-organized into Trigger, Core Process, and Example sections, but the provided bundle files (references/query_patterns.md, references/execution_example.md) are never referenced or linked from the body, leaving genuinely useful material orphaned.

3 / 5

Total

15

/

20

Passed

Description

76%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, well-structured description that answers both what and when with an explicit trigger clause. Its main weakness is trigger-term coverage that omits the natural user phrasings the skill is meant to recognize.

Suggestions

Add natural trigger phrases users actually say (e.g., 'I need', 'I want', 'looking for', 'find me') so Claude recognizes real shopping requests, not just the abstract term 'shopping instruction'.

Sharpen the distinctiveness from the paired search-executor skill by contrasting 'interprets/parses' (this skill) versus 'executes the search' (the other).

DimensionReasoningScore

Specificity

Names several concrete actions ('extract key product requirements', 'parse natural language into structured criteria', 'output is a clear set of search parameters') with only minor coverage gaps around ambiguity handling.

4 / 5

Completeness

Clearly states what it does ('Interprets a user's shopping query to extract...') and an explicit 'Use when a new shopping instruction is received' trigger with concrete conditions.

5 / 5

Trigger Term Quality

Includes relevant keywords ('shopping query', 'shopping instruction', 'product', 'price limits') but misses the natural phrases users actually say ('find me', 'looking for', 'I want', 'I need') catalogued in the reference patterns.

3 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (query interpretation vs. search execution) but shares the 'shopping'/'product' trigger surface with the paired webshop-search-executor skill, creating minor overlap risk.

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.

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.