CtrlK
BlogDocsLog inGet started
Tessl Logo

webshop-query-parser

This skill extracts key constraints and product requirements from a user's shopping query. It should be triggered when the agent receives a new shopping instruction, to identify product attributes (e.g., 'gluten free'), price limits (e.g., 'lower than 140.00 dollars'), and other specifications. The skill outputs a structured set of search criteria to guide subsequent product discovery.

68

Quality

81%

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

SKILL.md
Quality
Evals
Security

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A concise, well-sequenced workflow with a useful retry loop, but its actionability and progressive disclosure are undermined by a referenced script that is missing from the bundle and an existing reference file that is never linked from the body.

Suggestions

Either add the missing parse_query.py to a scripts/ directory and show its exact invocation (e.g., `python scripts/parse_query.py "<instruction>"`), or replace the script step with explicit inline parsing instructions so the action is fully executable.

Link the existing references/query_components.md from the body (e.g., under Procedure or a References section) so the attribute/price-pattern reference is discoverable, and remove or fix the dangling parse_query.py reference to match the actual bundle.

Add a brief verification checkpoint confirming extracted price limits are numeric ranges before issuing the first search, which would tighten the already-present review step.

DimensionReasoningScore

Conciseness

The ~30-line body is lean and well-sectioned (When to Use, Core Task, Procedure, Output, Notes) with no padding explaining concepts Claude already knows; every section earns its place, matching the level-3 lean-and-efficient anchor.

3 / 3

Actionability

Provides some concrete guidance (example output dict {'product': 'popcorn', ...} and example search[gluten free popcorn]), but the core step 'Execute the bundled script parse_query.py' gives no executable invocation and the referenced script does not exist in the bundle, fitting the level-2 anchor of some concrete guidance but incomplete with missing key details.

2 / 3

Workflow Clarity

The three-step Procedure is clearly sequenced (Run parser -> Review & Refine -> Formulate Search Strategy) and includes an explicit error-recovery feedback loop in Notes ('If the initial search yields no results, consider broadening the search by removing less critical attributes one at a time'), matching the level-3 anchor of a clear sequence with feedback loops for error recovery.

3 / 3

Progressive Disclosure

The body sections are well organized, but the bundle is misaligned: the body references parse_query.py which does not exist, while the existing references/query_components.md is never linked or signaled from the body, fitting the level-2 anchor of some structure but references present yet not clearly signaled.

2 / 3

Total

10

/

12

Passed

Description

85%

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, specific description that clearly states both capability and trigger condition in third person. The only gap is trigger-term coverage, which is adequate but omits common natural shopping phrases.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'extracts key constraints and product requirements', 'identify product attributes (e.g., 'gluten free')', 'price limits', and 'outputs a structured set of search criteria' — matching the level-3 anchor of multiple specific concrete actions.

3 / 3

Completeness

Explicitly answers both what ('extracts key constraints... outputs a structured set of search criteria') and when ('It should be triggered when the agent receives a new shopping instruction'), matching the level-3 anchor of clearly answering both what AND when with explicit triggers.

3 / 3

Trigger Term Quality

Includes relevant shopping-domain terms ('shopping query', 'shopping instruction') and concrete user-language examples ('gluten free', 'lower than 140.00 dollars'), but lacks common natural variations a shopper would say ('buy', 'find me', 'I need', 'shop for'), fitting the level-2 anchor of some relevant keywords but missing common variations.

2 / 3

Distinctiveness Conflict Risk

The shopping-query parsing niche with product-attribute and price-limit extraction is a clear, distinct trigger unlikely to fire for unrelated skills, matching the level-3 anchor of a clear niche with distinct triggers.

3 / 3

Total

11

/

12

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.