openapi-to-application-code
Generate a complete, production-ready application from an OpenAPI specification
- License 许可
- MIT
- 最近更新
- 2026-11-14
- Stars
- ★ 4.1w
- Forks
- 5.4k
01 前言 Front Matter
- name
- openapi-to-application-code
- description
- Generate a complete, production-ready application from an OpenAPI specification
03 SKILL.md 正文
Generate Application from OpenAPI Spec
Your goal is to generate a complete, working application from an OpenAPI specification using the active framework's conventions and best practices.
Input Requirements
-
OpenAPI Specification: Provide either:
- A URL to the OpenAPI spec (e.g.,
https://api.example.com/openapi.json) - A local file path to the OpenAPI spec
- The full OpenAPI specification content pasted directly
- A URL to the OpenAPI spec (e.g.,
-
Project Details (if not in spec):
- Project name and description
- Target framework and version
- Package/namespace naming conventions
- Authentication method (if not specified in OpenAPI)
Generation Process
Step 1: Analyze the OpenAPI Specification
- Validate the OpenAPI spec for completeness and correctness
- Identify all endpoints, HTTP methods, request/response schemas
- Extract authentication requirements and security schemes
- Note data model relationships and constraints
- Flag any ambiguities or incomplete definitions
Step 2: Design Application Architecture
- Plan directory structure appropriate for the framework
- Identify controller/handler grouping by resource or domain
- Design service layer organization for business logic
- Plan data models and entity relationships
- Design configuration and initialization strategy
Step 3: Generate Application Code
- Create project structure with build/package configuration files
- Generate models/DTOs from OpenAPI schemas
- Generate controllers/handlers with route mappings
- Generate service layer with business logic
- Generate repository/data access layer if applicable
- Add error handling, validation, and logging
- Generate configuration and startup code
Step 4: Add Supporting Files
- Generate appropriate unit tests for services and controllers
- Create README with setup and running instructions
- Add .gitignore and environment configuration templates
- Generate API documentation files
- Create example requests/integration tests
Output Structure
The generated application will include:
project-name/
├── README.md # Setup and usage instructions
├── [build-config] # Framework-specific build files (pom.xml, build.gradle, package.json, etc.)
├── src/
│ ├── main/
│ │ ├── [language]/
│ │ │ ├── controllers/ # HTTP endpoint handlers
│ │ │ ├── services/ # Business logic
│ │ │ ├── models/ # Data models and DTOs
│ │ │ ├── repositories/ # Data access (if applicable)
│ │ │ └── config/ # Application configuration
│ │ └── resources/ # Configuration files
│ └── test/
│ ├── [language]/
│ │ ├── controllers/ # Controller tests
│ │ └── services/ # Service tests
│ └── resources/ # Test configuration
├── .gitignore
├── .env.example # Environment variables template
└── docker-compose.yml # Optional: Docker setup (if applicable)
Best Practices Applied
- Framework Conventions: Follows framework-specific naming, structure, and patterns
- Separation of Concerns: Clear layers with controllers, services, and repositories
- Error Handling: Comprehensive error handling with meaningful responses
- Validation: Input validation and schema validation throughout
- Logging: Structured logging for debugging and monitoring
- Testing: Unit tests for services and controllers
- Documentation: Inline code documentation and setup instructions
- Security: Implements authentication/authorization from OpenAPI spec
- Scalability: Design patterns support growth and maintenance
Next Steps
After generation:
- Review the generated code structure and make customizations as needed
- Install dependencies according to framework requirements
- Configure environment variables and database connections
- Run tests to verify generated code
- Start the development server
- Test endpoints using the provided examples
Questions to Ask if Needed
- Should the application include database/ORM setup, or just in-memory/mock data?
- Do you want Docker configuration for containerization?
- Should authentication be JWT, OAuth2, API keys, or basic auth?
- Do you need integration tests or just unit tests?
- Any specific database technology preferences?
- Should the API include pagination, filtering, and sorting examples?
04 同仓库更多 Skills
supabase-rls-policies
Write, review, and test Supabase Row Level Security (RLS) policies so that one user cannot read or change another user's rows. Use when creating or changing tables, policies, views, or security definer functions in a Supabase project, when reviewing a migration that touches RLS, or when asked to prove user isolation with pgTAP tests that sign in as two users.
skill-distribution-audit
Audit a skill collection before release or investigate installer omissions, archived/template leakage, duplicate identities, and manifest drift. Reconcile the intended public source set, distribution manifest, and actual discovery output for a specified consumer version. Includes a deterministic set-comparison helper.
logicapps-custom-code-net10-migration
Migrate Azure Logic Apps Standard local-function custom-code projects from .NET 8 to .NET 10. Use for legacy Logic Apps custom-code workspace upgrades, project/package configuration, custom-worker settings, publication, and integrated VS Code debugging. Not for ordinary .NET applications, standalone Azure Functions, Consumption workflows, or cloud deployment.
winmd-api-search
Find and explore Windows desktop APIs. Use when building features that need platform capabilities — camera, file access, notifications, UI controls, AI/ML, sensors, networking, etc. Discovers the right API for a task and retrieves full type details (methods, properties, events, enumeration values).
resemble-detect
Deepfake detection and media safety — detect AI-generated audio, images, video, and text, trace synthesis sources, apply watermarks, verify speaker identity, and analyze media intelligence using Resemble AI
quality-playbook
Run a complete quality engineering audit on any codebase. Derives behavioral requirements from the code, generates spec-traced functional tests, runs a three-pass code review with regression tests, executes a multi-model spec audit (Council of Three), and produces a consolidated bug report with TDD-verified patches. Finds the 35% of real defects that structural code review alone cannot catch. Works with any language. Trigger on 'quality playbook', 'spec audit', 'Council of Three', 'fitness-to-purpose', or 'coverage theater'.