CtrlK
BlogDocsLog inGet started
Tessl Logo
PluginPublic

testland/gherkin-from-stories

Use whenever user stories, acceptance criteria, manual test steps or a spec need to become Gherkin, or when asked how to write good acceptance scenarios: maps each criterion to scenarios, finds Scenario Outlines and Background, reuses existing steps and flags hidden preconditions. Writes .feature files only, not step code.

Quality

92%

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

Overview
Quality
Evals
Security
Files

Quality

Content

92%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 well-engineered instruction skill: four input routes clearly sequenced with explicit validation steps and a flag-and-ask feedback loop, copy-paste-ready Gherkin and output templates, and proper progressive disclosure to three real one-level-deep references. The only trimmable material is minor background explanation (ISTQB ATDD definition, declarative-vs-imperative primer).

DimensionReasoningScore

Conciseness

The body is dense with load-bearing material — routing table, worked Gherkin blocks, numbered procedures, an output template — with almost no padding of concepts Claude already knows. It is not 5 because a few spots explain known material (the quoted ISTQB definition of ATDD, the declarative-vs-imperative primer) that could be trimmed; it is not 3 because those instances are minor and every section carries skill-specific method rather than generic tutorial prose.

4 / 5

Actionability

Guidance is fully executable for an instruction-only skill: copy-paste-ready Gherkin templates for each input shape, a fully specified markdown output template, concrete rewrite rules ("remove UI mechanics, collapse multi-step UI sequences into one business action..."), and exact stub guidance ("bodies raise NotImplementedError"). The common cases (story, AC list, manual steps, raw spec) are each covered by a worked example; there are no pseudocode-only sections.

5 / 5

Workflow Clarity

Each input shape has a clearly sequenced numbered workflow, and validation is explicit throughout: "Validate: at most one When per scenario; lint; specificity preserved", "Validate observability of every Then". The flag-and-ask pattern ("The Gherkin Feature can't be authored without these answers") is a genuine feedback loop, and the anti-patterns table acts as a checklist. This matches the top anchor rather than 4, where checkpoints would be merely present rather than paired with a halt-and-recover loop.

5 / 5

Progressive Disclosure

The body is a clear overview that keeps actionable summaries inline while pushing deep detail to three real, one-level-deep reference files (atdd-traceability.md, manual-step-rules.md, spec-extraction-examples.md — all present in references/ and containing no further nested .md links). Each link is well-signaled with a description of its contents, and a References section repeats them with annotations. Content is appropriately split and navigation is easy, matching the top anchor.

5 / 5

Total

19

/

20

Passed

Description

88%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: third-person, concrete, and dense with natural trigger phrases for all four input shapes, with an explicit use-when clause and a clear scope boundary. The only gaps are a few missing synonyms (BDD, Cucumber) and a slight overlap risk on the generic 'how to write good acceptance scenarios' trigger.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions — "maps each criterion to scenarios", "finds Scenario Outlines and Background", "reuses existing steps", "flags hidden preconditions", "Writes .feature files only, not step code" — comprehensively covering the transform plus its boundary. It is not 4 because coverage extends beyond several actions to an explicit scope exclusion, with no generic filler.

5 / 5

Completeness

Both questions are explicitly answered: what it does ("maps each criterion to scenarios... flags hidden preconditions. Writes .feature files only") and when to use it ("Use whenever user stories, acceptance criteria, manual test steps or a spec need to become Gherkin, or when asked how to write good acceptance scenarios"). The explicit "Use whenever" clause with multiple concrete trigger conditions matches the top anchor; score 4 would require the 'when' to be less explicit, which it is not.

5 / 5

Trigger Term Quality

Natural trigger terms are strong: "user stories", "acceptance criteria", "manual test steps", "spec", "Gherkin", "acceptance scenarios", and the ".feature" file extension. It is not 5 because common synonyms a user would naturally say — "BDD", "Cucumber", "feature file" as a phrase — are absent, leaving a few natural terms missing; it is well above 3 since keyword coverage is broad and phrased the way users actually ask.

4 / 5

Distinctiveness Conflict Risk

The niche is clear — turning requirements text into Gherkin .feature files — and "Writes .feature files only, not step code" explicitly fences off step-definition skills. It is not 5 because the trigger "when asked how to write good acceptance scenarios" could also route style-advice questions that belong to a gherkin-style-reviewer-type skill, a minor overlap with a closely related skill; it is clearly above 3 given the explicit boundary statement.

4 / 5

Total

18

/

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Reviewed

On this page