lean-spec
🥈SilverLeanSpec enables AI-powered Spec-Driven Development (SDD) for modern software projects. It allows operations teams to define, manage, and automate specifications for AI agents. The tool connects to development workflows, ensuring alignment between project requirements and AI agent capabilities.
263110Updated 2mo ago
Intermediate30min to implementautomation
Saves ~80 min per use
Quick InstallView Source
git clone https://github.com/codervisor/lean-spec.gitWorks with:
Claude
Overview
About This Skill
LeanSpec is a spec coding framework that works with your existing workflow—GitHub Issues, Azure DevOps Work Items, Jira, Linear, or plain markdown. It provides a unified CLI, MCP server, and web UI on top of any spec backend, enabling AI coding assistants to access structured spec data regardless of where specs live. The tool is designed for teams practicing Spec-Driven Development (SDD), offering Kanban boards, smart search, dependency tracking, and project metrics. Setup takes minutes with markdown specs working out of the box, and it integrates with Claude Code, Cursor, VS Code Copilot, and other AI assistants via MCP or CLI.
How to Use
["Prepare your specification files: Upload your project spec (e.g., `spec.yaml` or `spec.json`) to a cloud storage or local path accessible by the AI agent. Ensure it includes clear requirements for the AI agent's behavior.","Configure the agent: Define the agent's configuration file (e.g., `agent_config.json`) with details like API endpoints, authentication, and tool integrations. Specify the test framework (e.g., pytest, Jest) for output compatibility.","Run the spec-driven test generator: Use the prompt template above, replacing [PLACEHOLDERS] with your spec file URL/path, agent config file, and specific requirements. For example: `Act as a LeanSpec SDD agent... [SPEC_FILE_URL_OR_PATH='https://storage.example.com/spec.yaml']...`","Execute and validate: Run the generated test suite in your CI/CD pipeline or local environment. Review the test results to ensure the AI agent meets the specified requirements. Iterate by updating the spec or agent config as needed.","Tip: For complex domains like [DATA_DOMAIN], use mock data generators (e.g., Faker, Mockaroo) to create realistic test inputs. For edge cases, explicitly define boundary conditions (e.g., empty inputs, maximum values) in the spec."]
Use Cases
Define and manage project specifications in your preferred tool (GitHub Issues, Azure DevOps, or markdown) with unified AI access
Give AI coding assistants context-efficient spec data to improve code generation accuracy
Track spec dependencies and relationships while maintaining visibility across statuses and priorities
Visualize project progress with Kanban boards and metrics without leaving your current workflow
Tags
Setup & Installation
Quick Install
No install command available. Check the GitHub repository for manual installation instructions.
Alternative Install (Git Clone)
git clone https://github.com/codervisor/lean-specRequirements
- Claude Code or compatible AI agent
- Works with: Claude
Quick Start Guide
1
Install the Skill
Copy the install command above and run it in your terminal.
2
Open Your AI Agent
Launch Claude Code, Cursor, or your preferred AI coding agent.
3
Try It Out
Use the prompt template or examples below to test the skill.
4
Customize
Adapt the skill to your specific use case and workflow.
Usage Examples
Prompt Template
Act as a LeanSpec SDD (Spec-Driven Development) agent. Using the project specification [SPEC_FILE_URL_OR_PATH], generate a set of executable test cases for the AI agent defined in [AGENT_CONFIG_FILE]. Ensure the tests validate: 1) [REQUIREMENT_1], 2) [REQUIREMENT_2], 3) [REQUIREMENT_3]. Format the output as a JSON test suite compatible with [TEST_FRAMEWORK_NAME]. Include mock data generation for [DATA_DOMAIN] and edge case handling for [EDGE_CASE].
Example Output
```json
{
"test_suite": {
"name": "Customer Support Agent - Order Processing Tests",
"description": "Validates order processing workflows for the AI agent handling customer support tickets.",
"tests": [
{
"id": "TST-001",
"name": "Process Standard Order",
"description": "Verifies the agent correctly processes a standard order with valid payment and inventory.",
"steps": [
{
"action": "Agent receives order request",
"input": {
"order_id": "ORD-2024-00123",
"customer_id": "CUST-45678",
"items": [{"product_id": "PROD-9012", "quantity": 2}],
"payment_method": "credit_card"
},
"expected_output": {
"status": "completed",
"confirmation_id": "CONF-78901",
"estimated_delivery": "2024-05-15"
}
}
],
"mock_data": {
"inventory": {"PROD-9012": {"stock": 10, "price": 19.99}},
"customer": {"CUST-45678": {"name": "Sarah Johnson", "credit_limit": 500.00}}
}
},
{
"id": "TST-002",
"name": "Handle Low Inventory",
"description": "Tests agent response when inventory is insufficient for the order.",
"steps": [
{
"action": "Agent receives order request",
"input": {
"order_id": "ORD-2024-00124",
"customer_id": "CUST-45679",
"items": [{"product_id": "PROD-9013", "quantity": 5}],
"payment_method": "paypal"
},
"expected_output": {
"status": "failed",
"error": "Insufficient inventory for PROD-9013",
"suggested_alternatives": ["PROD-9012", "PROD-9014"]
}
}
],
"edge_cases": {
"inventory": {"PROD-9013": {"stock": 3}},
"customer": {"CUST-45679": {"name": "Michael Chen", "credit_limit": 200.00}}
}
}
]
}
}
```Apply to these tools
Browse all toolsRive
Create and collaborate on interactive animations with powerful, user-friendly tools.
Microsoft Teams
Get more done every day with Microsoft Teams – powered by AI
Drata
Automate security compliance and monitor real-time security posture seamlessly.
GPT for work
Automate your spreadsheet tasks with AI power
Respell
Agentic AI Workflow platform
Notion
Connected workspace for docs, wikis, and projects
Compatible MCP servers
Browse all MCP servers
Find the right skills for your stack
Take a free 3-minute scan and get personalized AI skill recommendations.
Take free scan