CtrlK
BlogDocsLog inGet started
Tessl Logo

testland/bdd-step-library-curator

Keeps a BDD step-definition library DRY across a Cucumber / Behave / Reqnroll project - inventories every step definition, detects duplicates (different patterns matching the same intent), recommends canonical consolidations, reorganizes steps by domain, publishes a step-library README the team greps for "is there already a step for X?" before authoring new ones, and builds a scenario coverage map that fingerprints new Gherkin scenarios against the live suite to classify each as duplicate, partial overlap, or genuine gap before any test is authored. Use when a BDD project's step count grows past ~50, on a quarterly step-library review, when a new engineer is about to write a duplicate step, or when fresh .feature files need a covered-already check.

73

Quality

92%

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

85%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-structured curation workflow with explicit sequencing, strong validation feedback loops for destructive refactors, and clean progressive disclosure into two real reference files. The main slack is minor redundancy between the per-step sections and the worked example, and executable commands living in references rather than inline.

Suggestions

Tighten the worked example to reference Step 3's duplicate-group table rather than restating it, to reduce token redundancy.

Inline the key extraction command (e.g. the Behave grep over features/steps/) so the most common action is executable without opening a reference.

DimensionReasoningScore

Conciseness

Mostly efficient with concrete audit output, README templates, and an anti-patterns table that earn their place, but the worked example restates the Step 3 duplicate-group table and per-step instructions, adding mild redundancy that could be trimmed.

4 / 5

Actionability

Provides concrete, copy-paste-ready templates (step audit, duplicate-group markdown, README index) and names specific scripts (overlap script, check-new-steps.sh), though the actual executable extraction commands and scripts are deferred to references rather than inline.

4 / 5

Workflow Clarity

A clearly sequenced six-step workflow (inventory -> detect -> consolidate -> reorganize/publish -> gate -> cadence) with an explicit destructive-operation verification loop ('run the full BDD suite and assert zero undefined or ambiguous steps... fix that reference and re-run'), satisfying the validation requirement for batch/destructive work.

5 / 5

Progressive Disclosure

SKILL.md is a well-organized overview with clearly signaled, one-level-deep references to two real bundle files (references/step-extraction-and-overlap.md and references/coverage-map.md), splitting detailed methods out while keeping navigation easy.

5 / 5

Total

18

/

20

Passed

Description

96%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.

An exceptionally specific and complete description that pairs a comprehensive capability list with explicit, concrete trigger conditions and natural BDD-domain vocabulary. Its only weakness is a slight adjacency to the per-runner testing skills it coordinates with.

Suggestions

Add a one-clause scoping distinction (e.g. 'curation of an existing library, not authoring new tests') to reduce overlap with the per-runner testing skills.

DimensionReasoningScore

Specificity

Lists multiple concrete actions—inventories step definitions, detects duplicates, recommends canonical consolidations, reorganizes by domain, publishes a README, and builds a scenario coverage map that classifies scenarios as duplicate/partial/gap—covering the full curation lifecycle comprehensively.

5 / 5

Completeness

Explicitly answers both what (inventory/detect/consolidate/reorganize/publish/coverage map) and when ('Use when a BDD project's step count grows past ~50, on a quarterly step-library review, when a new engineer is about to write a duplicate step, or when fresh .feature files need a covered-already check').

5 / 5

Trigger Term Quality

Covers natural terms and synonyms across the BDD ecosystem—Cucumber, Behave, Reqnroll, Gherkin, step definition, .feature files, duplicate step, quarterly step-library review—that a user would actually say.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear curation/DRY niche with distinct triggers, but has minor overlap risk with the per-language runner testing skills (cucumber-testing, behave-testing, reqnroll-testing) it works alongside, which could trigger for generic BDD setup requests.

4 / 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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Reviewed

Table of Contents