By dgomezs
A comprehensive TDD workflow plugin that combines Test-Driven Development with Specification by Example. Includes specialized agents for each TDD phase (RED-GREEN-REFACTOR), requirements analysis, technical design, and BDD-style test scenarios.
Research codebase to understand existing implementation
Create requirements.md with testable acceptance criteria from a ticket or prompt
Create technical design (tech-design.md) from requirements.md
Continue TDD implementation using orchestrator agent
Create or manage test scenarios from requirements.md using the qa-engineer agent. Supports creating, adding, modifying, or discovering scenarios.
Use this agent to understand HOW specific code works. This agent analyzes implementation details, traces data flow, and documents technical workings with precise file:line references. It reads code thoroughly to explain logic, transformations, and component interactions without suggesting improvements. Optionally loads code analysis skills for complexity, coupling, and cohesion metrics.
Use this agent to find WHERE files and components live in the codebase. This agent excels at discovering file locations, understanding directory structures, and mapping component organization. It should be used when you need to locate relevant code for a specific feature, domain concept, or functionality.
Use this agent to discover patterns, conventions, and repeated structures in the codebase. This agent finds examples of how similar problems have been solved, identifies architectural patterns in use, and documents coding conventions without evaluating their quality.
You generate test scenario CONTENT from acceptance criteria. The calling command handles all file operations, numbering, and organization.
Use this agent when you need to analyze requirements from JIRA tickets, user stories, or task descriptions and create a structured specification document (requirements.md) with testable acceptance criteria. This agent should be invoked at the start of any feature development workflow to establish clear requirements and scope before design or implementation begins. Examples: <example> Context: User wants to start implementing a new feature from a JIRA ticket. user: "I need to implement the user authentication feature described in jira-AUTH-123.md" assistant: "I'll use the requirements-analyzer agent to create a specification document from your JIRA ticket." <Task tool call to requirements-analyzer agent with source file path> assistant: "I've created requirements.md with clear acceptance criteria, scope boundaries, and dependencies. The specification is ready for the next steps: technical design and test scenario creation." </example> <example> Context: User has a feature request document and wants to start development. user: "Can you help me implement the bulk vulnerability ignore feature? Here's the requirements doc: docs/feature-requests/bulk-ignore.md" assistant: "Let me analyze those requirements and create a proper specification." <Task tool call to requirements-analyzer agent with source file path> assistant: "I've analyzed the requirements and created requirements.md with testable acceptance criteria in Given-When-Then format. Each criterion includes tracking checkboxes for the TDD workflow." </example> <example> Context: User mentions they have a user story to implement. user: "I have a user story for adding organization filtering. The file is stories/org-filter-story.txt" assistant: "I'll use the requirements-analyzer agent to create a specification from your user story." <Task tool call to requirements-analyzer agent with source file path> assistant: "Specification created successfully. The requirements.md includes 5 acceptance criteria with clear scope boundaries and identified dependencies on the existing organization repository." </example>
Uses power tools
Uses Bash, Write, or Edit tools
Has parse errors
Some configuration could not be fully parsed
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
A comprehensive Test-Driven Development workflow plugin for Claude Code that combines TDD with Specification by Example (BDD). Streamline your development process with intelligent agents that guide you through requirements analysis, technical design, and the complete RED-GREEN-REFACTOR cycle.
Note: This repository also serves as a plugin marketplace infrastructure, currently hosting the tdd-specflow plugin with support for adding more plugins in the future. See MARKETPLACE.md for details on the marketplace structure.
TDD SpecFlow provides a complete, automated workflow for building features using Test-Driven Development and Behavior-Driven Development principles. The plugin includes specialized agents for each phase of development and slash commands that orchestrate the entire process.
Install the plugin using Claude Code's plugin command:
/plugin install https://github.com/dgomezs/claude-code
Or if using a local clone:
/plugin install /path/to/claude-code
Start with a JIRA ticket, user story, or direct prompt:
/create-spec ticket.md
or with a direct prompt:
/create-spec "Add user authentication with JWT tokens"
This creates requirements.md with testable acceptance criteria in Given-When-Then format.
Transform acceptance criteria into detailed test scenarios:
/test-scenarios <task-directory>
This creates:
scenarios.md - High-level scenario overview with TDD tracking checkboxestest-scenarios/happy-path.md - Successful flow scenariostest-scenarios/error-cases.md - Error handling scenariostest-scenarios/edge-cases.md - Boundary and edge casesGenerate an implementation plan following your project's architecture:
/create-tech-design <task-directory>
This creates tech-design.md with:
Execute the complete RED-GREEN-REFACTOR cycle:
/start-tdd <task-directory>
The orchestrator will:
scenarios.md┌─────────────────────────────────────────────────────────────┐
│ TDD SpecFlow Workflow │
└─────────────────────────────────────────────────────────────┘
1. Requirements Analysis
↓
/create-spec → requirements.md
2. Test Scenarios
↓
/test-scenarios → scenarios.md + test-scenarios/
3. Technical Design
↓
/create-tech-design → tech-design.md
4. TDD Implementation Loop
↓
/start-tdd → RED-GREEN-REFACTOR cycle
For each scenario:
┌─────────────────────────────────────┐
│ RED: Write failing test │
│ ↓ │
│ GREEN: Make it pass (minimal code) │
│ ↓ │
│ REFACTOR: Improve quality │
└─────────────────────────────────────┘
/create-specPurpose: Analyze requirements and create structured specification
Usage:
/create-spec <ticket-path | prompt> [research.md]
Examples:
/create-spec docs/tickets/AUTH-123.md
/create-spec "Add password reset functionality" research.md
/create-spec "Implement user profile editing"
Output: requirements.md with testable acceptance criteria
/test-scenariosPurpose: Generate detailed test scenarios from requirements
Usage:
/test-scenarios <task-directory> [operation-prompt]
Examples:
/test-scenarios docs/tasks/task-001/
/test-scenarios docs/tasks/task-001/ "Add scenario for concurrent access"
Output:
scenarios.md - Overview with TDD trackingtest-scenarios/happy-path.mdtest-scenarios/error-cases.mdtest-scenarios/edge-cases.md/create-tech-designPurpose: Create technical design from requirements
npx claudepluginhub dgomezs/claude-code --plugin tdd-specflowTest-driven development skill that enforces red-green-refactor, one test at a time
Strict red-green-refactor TDD loop. Failing test, then minimum code, then refactor. Commits after each cycle.
Acceptance Test Driven Development for Claude Code. Enforces the ATDD methodology: write Given/When/Then specs first, generate a project-specific test pipeline, maintain two test streams (acceptance + unit). Inspired by Robert C. Martin's acceptance test approach from empire-2025.
Guides AI agents through disciplined coding practices. Language and build-system agnostic core with extensible language/build skills.
Test-driven development workflow for writing tests before implementation - red-green-refactor cycle with deterministic unit tests
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.