aibdd-spec-by-example-analyze

Converts boundary-aware product intent into Given/When/Then exemplars in Gherkin feature files.

77|15|Updated May 12, 2026
One-click install
npx skills add https://github.com/Waterball-Software-Academy/aixbdd --skill aibdd-spec-by-example-analyze
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: aibdd-spec-by-example-analyze
Source: https://github.com/Waterball-Software-Academy/aixbdd/tree/main/.agents/skills/aibdd-spec-by-example-analyze
Command: npx skills add https://github.com/Waterball-Software-Academy/aixbdd --skill aibdd-spec-by-example-analyze

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires python3, PyYAML, subprocess, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill reduces missing context and ambiguous requirements during Spec by Example creation by enforcing a strict, boundary-aware workflow that transforms impacted feature files into concrete Given/When/Then arrangements with idempotent, audited steps.

Core Features & Use Cases

  • Boundary-aware impacted feature scoping: derives the mutable feature set from an impact matrix query and anchors all outputs to the working directory.
  • Example skeleton locking: applies an Example skeleton to rules that are not yet form-locked, guided by the active boundary profile.
  • Handler candidate enrichment for DSL blocks: enriches # @dsl blocks with concrete # candidates: selections by querying the DSL catalog and shared DSL when needed.
  • Faithful Given/Then DSL arrangement: replaces # @dsl placeholders in Given/Then blocks with concrete DSL steps, with clarifications as a blocking gate.
  • Canonical exemplar instantiation: instantiates all remaining {...} and <...> placeholders into reviewable, runnable scenarios while preserving $alias runtime handles.
  • Blocking clarify loop: any $questions/$NEED_TO_CLARIFY stops forward progress and delegates to /clarify-loop before the workflow can complete.

Quick Start

Run /aibdd-spec-by-example-analyze after you have executed /aibdd-kickoff, /aibdd-discovery, and /aibdd-plan so that arguments.yml and the impacted .feature scope are present.

Frequently Asked Questions about aibdd-spec-by-example-analyze

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate executable acceptance criteria from raw product intent?

Executable acceptance criteria are generated by converting raw boundary-aware product intent into Given/When/Then DSL arrangements inside impacted Gherkin feature files. The process applies staged form-locking and canonical exemplar instantiation to produce concrete, runnable scenarios while preserving runtime aliases.

How does the clarify loop handle ambiguous Gherkin scenarios during specification by example?

The clarify loop blocks forward progress whenever $questions or $NEED_TO_CLARIFY placeholders are encountered during DSL arrangement. It delegates resolution to the clarify-loop process, ensuring all ambiguities are resolved before the Gherkin feature file workflow can complete.

Do I need to run discovery and planning steps before generating Gherkin feature files?

Yes, you must execute aibdd-kickoff, aibdd-discovery, and aibdd-plan beforehand. This ensures the required arguments.yml file and the impacted .feature scope are present in the working directory before generating Given/When/Then arrangements.

What's the best way to resolve handler candidates for DSL blocks in BDD specifications?

Handler candidates are resolved by enriching # @dsl blocks with concrete # candidates: selections. The process queries the DSL catalog and shared DSL to match concrete handler implementations to the Given/Then step arrangements within the boundary-aware feature scope.

Why are my placeholder variables not being instantiated in the acceptance scenarios?

Placeholder instantiation requires completing the canonical exemplar instantiation phase, which replaces all {...} and <...> placeholders with reviewable scenarios. If $questions or $NEED_TO_CLARIFY markers remain, the blocking clarify loop stops forward progress until ambiguity resolution is complete.

Can I use Python and PyYAML for impact analysis across multiple BDD feature files?

Yes, the workflow uses Python3, PyYAML, and subprocess dependencies to perform boundary-aware impacted feature scoping. It derives the mutable feature set from an impact matrix query and anchors all generated Given/When/Then artifacts to the current working directory.