CtrlK
BlogDocsLog inGet started
Tessl Logo

add-cucumber-tests

Generates Tzatziki-based Cucumber BDD tests (.feature files) from a functional specification. Use this skill whenever a user wants to write Cucumber tests, add BDD scenarios, create feature files, generate tests, or test application behaviors with Gherkin — especially in Java/Spring projects using Tzatziki step definitions for HTTP, JPA, Kafka, MongoDB, OpenSearch, logging, or MCP. Also use when the user mentions writing integration tests, acceptance tests, or end-to-end tests in a project that already has Tzatziki/Cucumber dependencies, including TestNG-based setups.

74

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

85%

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

The body is a well-structured, actionable workflow with strong validation feedback loops and clean progressive disclosure to real reference files. Its main weakness is conciseness: the meta-explanatory Principles section repeats guidance already covered in the Workflow, and several passages could be tightened.

Suggestions

Consolidate the modify-vs-new-scenario guidance into a single location (either Principle 6 or Step 5) and cross-reference it from the other, instead of fully re-arguing the rationale in three places.

Trim the extended justifications in the Principles (e.g. the maintenance-burden paragraph in Principle 6 and the warning box in Principle 1) to the operational rule plus a one-line rationale, since the Workflow already enforces the behavior.

Consider shortening Step 1's edge-case taxonomy exposition, which anticipates content elaborated again in Step 5's 'Identifying edge cases' section.

DimensionReasoningScore

Conciseness

The body assumes Claude's domain knowledge (no basic Gherkin/Cucumber primers) and is mostly efficient, but the Principles section overlaps the Workflow substantially — the modify-vs-new guidance is argued in Principle 6, Step 1's classification, and again in Step 5 with a worked example — and several paragraphs run longer than needed to convey their point.

2 / 3

Actionability

Provides fully executable commands (e.g. "./mvnw -pl <module> -Dtest=<RunnerClass> test", "grep -o 'tzatziki-[a-z-]*' pom.xml | sort -u"), concrete file paths, and specific runtime error signatures ("step(s) are undefined", "UndefinedStepException", "Tests run: 0") to act on.

3 / 3

Workflow Clarity

A clearly sequenced 6-step workflow with explicit, mandatory validation checkpoints — Step 4 environment verification, the Step 5 ⛔ approval gate, and the Step 6 run→inspect→fix→repeat feedback loop — plus a Success Criteria checklist.

3 / 3

Progressive Disclosure

The SKILL.md body is a well-signaled overview pointing one level deep to 11 reference files, all verified to exist on disk, with content appropriately split out of the main file and clear inline guidance on when to read each.

3 / 3

Total

11

/

12

Passed

Description

100%

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 the skill's purpose and gives rich, natural trigger terms covering both direct and adjacent phrasings. Third-person voice is used throughout, and the niche is distinct enough to avoid conflicts.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "write Cucumber tests, add BDD scenarios, create feature files, generate tests, or test application behaviors with Gherkin" — matching the anchor for listing several specific actions rather than naming only a domain.

3 / 3

Completeness

Explicitly answers both what ("Generates Tzatziki-based Cucumber BDD tests (.feature files) from a functional specification") and when ("Use this skill whenever a user wants to... Also use when the user mentions..."), with explicit trigger guidance.

3 / 3

Trigger Term Quality

Covers a broad range of natural terms a user would say — "Cucumber tests", "BDD scenarios", "feature files", "Gherkin", "integration tests", "acceptance tests", "end-to-end tests", "Tzatziki/Cucumber" — not just technical jargon.

3 / 3

Distinctiveness Conflict Risk

Occupies a clear niche (Tzatziki-based Cucumber BDD in Java/Spring) with distinctive triggers unlikely to fire for unrelated skills.

3 / 3

Total

12

/

12

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 3 missing

Warning

Total

15

/

16

Passed

Repository
Decathlon/tzatziki
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.