CtrlK
BlogDocsLog inGet started
Tessl Logo

testland/gherkin-from-stories

Converts requirements in any input shape into Gherkin scenarios - a user story ("As a … I want … so that …"), a signed-off acceptance-criteria list (ATDD: @AC-N-tagged scenarios, NotImplementedError step stubs, AC-to-test traceability table), existing manual test steps (declarative rewrite that strips UI mechanics), or a raw spec / PRD section (acceptance-criteria extraction with Gherkin or plain-list output). Maps criteria to Scenario blocks, detects Scenario Outline opportunities, factors shared Background, reuses the curated step library, and flags implicit preconditions instead of fabricating them. Emits Gherkin (plus stubs in ATDD mode): runner detection and full step wiring belong to bdd-scenario-author. Use whenever requirements text of any shape needs to become a .feature file.

70

Quality

88%

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

Overview
Quality
Evals
Security
Files

Quality

Content

78%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-organized, actionable skill body that routes four input shapes through a shared discipline with concrete Gherkin examples and externalized detail files. Could be tightened by removing the ISTQB definition and inlining the bare minimum of the R1-R5 rules so the body is self-sufficient.

Suggestions

Drop the quoted ISTQB ATDD definition and the shift-left overview diagram; assume Claude knows the ATDD concept and state only the skill-specific contract.

Inline a one-line summary of each R1-R5 rule (or the classification table) so the manual-steps section is executable without opening the reference, keeping the full catalog in references/manual-step-rules.md.

Add an explicit post-emit validation step (e.g., 'lint the .feature; re-run after fixing flagged Givens') to close the workflow loop.

DimensionReasoningScore

Conciseness

Mostly efficient with concrete worked examples and a tight output template, but includes over-explanation Claude already knows (the quoted ISTQB ATDD definition and the introductory shift-left flow diagram) that could be trimmed.

4 / 5

Actionability

Provides copy-paste-ready Gherkin examples, numbered per-shape procedures, and a concrete output template; minor gaps because the R1-R5 rewrite rules and classification table are named but only defined in referenced files.

4 / 5

Workflow Clarity

Each input shape has a clearly sequenced numbered workflow with explicit validation ('Validate: at most one When per scenario', 'Validate observability of every Then') and a flag-and-ask feedback loop, but no explicit re-validate-after-fix loop for the emitted artifact.

4 / 5

Progressive Disclosure

Clear overview with well-signaled, one-level-deep references to three real reference files (atdd-traceability.md, manual-step-rules.md, spec-extraction-examples.md), each appropriately split by input shape with a consolidated References section for navigation.

5 / 5

Total

17

/

20

Passed

Description

92%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, third-person description that conveys comprehensive capability coverage and an explicit trigger clause while distinguishing itself from sibling skills. Slightly dense with ATDD implementation jargon that dilutes the natural trigger phrases.

Suggestions

Move implementation-detail terms ('@AC-N-tagged scenarios', 'NotImplementedError step stubs', 'AC-to-test traceability table') out of the description and into the ATDD reference; keep the description's triggers at the user-facing vocabulary level.

Lead with the core transform and the 'Use whenever...' clause earlier so the trigger is not buried after the input-shape enumeration.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Maps criteria to Scenario blocks, detects Scenario Outline opportunities, factors shared Background, reuses the curated step library, and flags implicit preconditions' — with comprehensive coverage across all four input shapes.

5 / 5

Completeness

Explicitly answers both what ('Converts requirements in any input shape into Gherkin scenarios') and when ('Use whenever requirements text of any shape needs to become a .feature file').

5 / 5

Trigger Term Quality

Good natural-keyword coverage ('user story', 'acceptance criteria', 'ATDD', 'manual test steps', 'spec', 'PRD', 'Gherkin', '.feature file') with synonyms, though the dense ATDD jargon ('@AC-N-tagged', 'NotImplementedError step stubs') are terms users would rarely say verbatim.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (requirements → .feature authoring) and explicitly fences off the adjacent skill: 'runner detection and full step wiring belong to bdd-scenario-author', minimizing overlap risk.

5 / 5

Total

19

/

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

Table of Contents

DiscoveryImplementationValidation