rysweet/amplihack-rs/gherkin-expert
Claude Code and agent skill by rysweet/amplihack-rs
Trust tier 3
- community
Source check pending
Checking that the SKILL.md file is still in the repository.
Gherkin/BDD specification expert for writing behavioral scenarios, acceptance criteria, and applying structured specifications to improve code generation quality
Install
npx vskill@latest install rysweet/amplihack-rs/gherkin-expertSKILL.md
Gherkin Expert Skill
Purpose
Provides expert-level Gherkin/BDD specification assistance for writing behavioral scenarios that clarify acceptance criteria and improve downstream code generation quality.
When This Skill Activates
- User asks to write or review Gherkin feature files or scenarios
- User needs help structuring complex acceptance criteria
- User wants to translate business requirements into Given/When/Then format
- User asks about BDD methodology or scenario design
- User wants behavioral specifications for multi-actor or multi-step workflows
- User mentions Cucumber, SpecFlow, or BDD frameworks
- User is working on features with complex acceptance criteria that would benefit from structured scenarios
How It Works
This skill delegates to the gherkin-expert agent which has knowledge of:
- Gherkin syntax and idioms — Feature/Scenario/Given/When/Then, backgrounds, scenario outlines, data tables, tags
- BDD methodology — discovery workshops, living documentation, specification by example
- Scenario design — single-behavior focus, declarative style, avoiding implementation details
- Domain modeling — ubiquitous language, bounded contexts expressed through scenarios
- AI prompt improvement — using Gherkin specs as prompt context for better code generation (empirically validated: +26% over English-only)
When Gherkin Adds Value (Judgment Call)
Gherkin is a tool, not a rule. Use judgment:
Good fit:
- Complex multi-step behavioral requirements with many edge cases
- Multi-actor scenarios (user does X, system responds Y, admin sees Z)
- Business rules with combinatorial conditions (scenario outlines)
- Acceptance criteria that stakeholders need to validate
- Features where "what done looks like" is ambiguous in English
English is fine:
- Simple CRUD operations with obvious behavior
- Internal tooling with a single developer as audience
- Config changes, styling, documentation
- Requirements where the hard part is algorithm design, not behavior specification
Usage Examples
Key Resources
- Gherkin experiment results:
experiments/hive_mind/gherkin_v2_recipe_executor/ - Issue #3939: Formal specification integration roadmap
- Gherkin reference: https://cucumber.io/docs/gherkin/reference/
Security
- Security scanPassed, 95 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingdocs/claude/skills/gherkin-expert/SKILL.md
Popularity
- 7-day trend score
- 0
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/rysweet/amplihack-rs/gherkin-expert)