Generate OpenAPI/Swagger specs from test automation code
Generates complete, valid OpenAPI 3.x and Swagger 2.0 specifications from natural language descriptions, code, or partial specs.
Why it matters
Automatically generate OpenAPI and Swagger specifications from existing test automation code and API interactions, enabling teams to document APIs while building test suites across Selenium, Playwright, Cypress, and other frameworks.
Outcomes
What it gets done
Extract API endpoint definitions from test automation scripts
Generate OpenAPI 3.0 and Swagger 2.0 specification files
Document request/response schemas from test code patterns
Integrate specification generation into CI/CD pipelines
Install
Add it to your toolbox
Run in your project directory:
curl -fsSL https://spark.entire.vc/get/ag-openapi-spec-generator | bash Overview
OpenAPI / Swagger Specification Generator
This skill generates OpenAPI 3.x and Swagger 2.0 specifications from natural language, source code, or partial specs. It extracts endpoints from Express, Koa, Fastify, FastAPI, Flask, and other frameworks, converting route definitions into structured API documentation with schemas, security, parameters, and response codes. Use this skill when documenting REST APIs, creating specifications from existing code, standardizing API contracts, or preparing specs for API gateways and mock servers. It handles both OpenAPI 3.x and Swagger 2.0 formats in YAML or JSON output.
What it does
This skill generates complete, valid OpenAPI 3.x or Swagger 2.0 specifications from natural language descriptions, source code, or partial specs. It builds API documentation with schemas, security definitions, response codes, and examples following the OpenAPI/Swagger standards.
When to use - and when NOT to
Use this skill when you need to document REST APIs, create endpoint specifications from Express/FastAPI/Django code, standardize API contracts across teams, or generate specs for API gateways and mock servers. Trigger it whenever you mention OpenAPI, Swagger, API spec, REST API documentation, YAML/JSON API schema, or endpoint documentation.
Do NOT use this for GraphQL schemas, gRPC proto files, or non-REST protocols - it targets OpenAPI/Swagger standards only.
Inputs and outputs
You provide: natural language API descriptions, source code (Express routes, FastAPI decorators, Spring controllers, Django URLs), partial existing specs to extend, or answers to context questions (OpenAPI version, output format, authentication type, endpoints list, data models).
You receive: a YAML or JSON specification with info metadata, servers/host configuration, paths with HTTP methods, components/schemas with $ref patterns, securitySchemes, parameters (path/query/header), response codes, examples, and a summary table of generated endpoints. The skill offers to export files, validate against Spectral or swagger-parser, generate mock server config (Prism), or generate client SDK stubs.
Integrations
Extracts endpoints automatically from Express, Koa, Fastify (Node.js) by parsing .get(), .post(), .put(), .patch(), .delete() calls and converting route params like :param to {param}. Supports FastAPI and Flask (Python) by reading decorators such as @app.get() and @router.post(). Infers request schemas from req.body, req.query, req.params usage and notes security requirements from authentication middleware.
Who it's for
Backend developers documenting REST APIs without manual YAML writing. API architects standardizing contracts across microservices. DevOps engineers configuring API gateways that require OpenAPI specs. Technical writers producing accurate endpoint documentation from codebases. Teams migrating from Swagger 2.0 to OpenAPI 3.x or vice versa.
Here is the OpenAPI 3.x skeleton structure the skill follows:
openapi: "3.1.0"
info:
title: <API Title>
version: "1.0.0"
description: <Short description>
contact:
name: <Team or Author>
email: <contact@example.com>
servers:
- url: https://api.example.com/v1
description: Production
- url: https://staging-api.example.com/v1
description: Staging
tags:
- name: <Tag>
description: <Tag description>
paths:
/resource:
get:
summary: List resources
operationId: listResources
tags: [<Tag>]
parameters: []
responses:
"200":
description: Success
content:
application/json:
schema:
$ref: "#/components/schemas/ResourceList"
example:
items: []
total: 0
"401":
$ref: "#/components/responses/Unauthorized"
"500":
$ref: "#/components/responses/InternalError"
security:
- BearerAuth: []
components:
schemas: {}
responses:
Unauthorized:
description: Authentication required
content:
application/json:
schema:
$ref: "#/components/schemas/Error"
InternalError:
description: Internal server error
content:
application/json:
schema:
$ref: "#/components/schemas/Error"
securitySchemes: {}
The skill enforces a quality checklist: every operation has a unique camelCase operationId, at least one success response (200/201/204), 4xx and 5xx error responses, all $ref targets exist, required fields are listed, security schemes are defined and applied, examples appear on every schema, tags match operation tags, and no orphaned schemas remain unreferenced.
Source README
OpenAPI / Swagger Specification Generator
When to Use
Use this skill when you need generate complete, production-ready OpenAPI 3.x and Swagger 2.0 specifications from natural language descriptions, code, or partial specs. Use this skill whenever the user mentions OpenAPI, Swagger, API spec, REST API documentation, YAML/JSON API schema, endpoint documentation, API...
Generate complete, valid OpenAPI 3.x or Swagger 2.0 specifications from descriptions, code, or partial specs.
Workflow
Step 1 - Gather Context
Before writing any YAML/JSON, ask (or infer from context) the following:
| Question | Why it matters |
|---|---|
| OpenAPI 3.x or Swagger 2.0? | Different info, servers/host, components/definitions structure |
| Output format: YAML or JSON? | YAML default unless user specifies JSON |
| What does this API do? | Sets info.title, info.description, tags |
| List of endpoints (or code to extract from)? | Core paths object |
| Authentication type(s)? | securitySchemes - see reference |
| Common data models or entities? | components/schemas / definitions |
| Any existing partial spec to extend? | Merge rather than overwrite |
If the user provides code (Express routes, FastAPI, Django URLs, Spring controllers, etc.), extract endpoints automatically - do not ask what the user already told you.
Step 2 - Build the Spec
Follow the structure guide for the chosen version. Always produce a complete, valid spec - never leave placeholder comments like # TODO: add schema.
OpenAPI 3.x Skeleton
openapi: "3.1.0"
info:
title: <API Title>
version: "1.0.0"
description: <Short description>
contact:
name: <Team or Author>
email: <contact@example.com>
servers:
- url: https://api.example.com/v1
description: Production
- url: https://staging-api.example.com/v1
description: Staging
tags:
- name: <Tag>
description: <Tag description>
paths:
/resource:
get:
summary: List resources
operationId: listResources
tags: [<Tag>]
parameters: []
responses:
"200":
description: Success
content:
application/json:
schema:
$ref: "#/components/schemas/ResourceList"
example:
items: []
total: 0
"401":
$ref: "#/components/responses/Unauthorized"
"500":
$ref: "#/components/responses/InternalError"
security:
- BearerAuth: []
components:
schemas: {}
responses:
Unauthorized:
description: Authentication required
content:
application/json:
schema:
$ref: "#/components/schemas/Error"
InternalError:
description: Internal server error
content:
application/json:
schema:
$ref: "#/components/schemas/Error"
securitySchemes: {}
Swagger 2.0 Skeleton
swagger: "2.0"
info:
title: <API Title>
version: "1.0.0"
description: <Short description>
host: api.example.com
basePath: /v1
schemes: [https]
consumes: [application/json]
produces: [application/json]
tags: []
paths: {}
definitions: {}
securityDefinitions: {}
Step 3 - Schemas and Models
- Always use
$reffor any schema used in more than one place. - Include
exampleorexampleson every schema and response body. - Mark required fields with the
requiredarray. - Use
nullable: true(OAS 3.0) orx-nullable: true(Swagger 2.0) for optional nullable fields. - Prefer
formatkeywords:int32,int64,float,date,date-time,uuid,email,uri,byte,binary.
Common schema patterns:
### Pagination wrapper
PagedResult:
type: object
required: [items, total, page, pageSize]
properties:
items:
type: array
items:
$ref: "#/components/schemas/Resource"
total:
type: integer
format: int64
example: 100
page:
type: integer
format: int32
example: 1
pageSize:
type: integer
format: int32
example: 20
### Standard error
Error:
type: object
required: [code, message]
properties:
code:
type: string
example: RESOURCE_NOT_FOUND
message:
type: string
example: The requested resource was not found.
details:
type: object
additionalProperties: true
### Timestamps mixin (use allOf)
Timestamps:
type: object
properties:
createdAt:
type: string
format: date-time
updatedAt:
type: string
format: date-time
Step 4 - Security Schemes
Read reference/security-schemes.md for detailed patterns. Quick reference:
| Scheme | OAS 3.x type | Notes |
|---|---|---|
| Bearer JWT | http, scheme bearer |
Most common for REST APIs |
| API Key (header) | apiKey, in header |
e.g. X-API-Key |
| API Key (query) | apiKey, in query |
Avoid - leaks in logs |
| OAuth 2 | oauth2 |
Use flows to define grant types |
| Basic Auth | http, scheme basic |
Only over HTTPS |
| OpenID Connect | openIdConnect |
Provide openIdConnectUrl |
Apply security globally at the root and override per-operation only where it differs (e.g., public endpoints use security: []).
Step 5 - Parameters
Path parameters - always required: true:
parameters:
- name: userId
in: path
required: true
schema:
type: string
format: uuid
example: 123e4567-e89b-12d3-a456-426614174000
Query parameters - document defaults and enums:
- name: status
in: query
schema:
type: string
enum: [active, inactive, pending]
default: active
Headers - include X-Request-ID, correlation IDs, etc. as common parameters defined under components/parameters.
Step 6 - Response Codes
Always include at minimum:
| Code | When |
|---|---|
200 |
Successful GET, PUT, PATCH |
201 |
Successful POST that creates a resource |
204 |
Successful DELETE (no body) |
400 |
Validation / bad request |
401 |
Missing or invalid auth |
403 |
Authenticated but not authorized |
404 |
Resource not found |
409 |
Conflict (duplicate, state mismatch) |
422 |
Unprocessable entity (semantic errors) |
429 |
Rate limited |
500 |
Internal server error |
Use $ref to components/responses for 401, 403, 404, 429, 500 to avoid repetition.
Step 7 - Quality Checklist
Before delivering the spec, verify:
-
openapiorswaggerversion field present - Every path has at least one operation
- Every operation has
operationId(camelCase, unique) - Every operation has at least one
200/201/204response -
4xxand5xxresponses defined for all operations - All
$reftargets exist incomponents/ordefinitions/ - Required fields listed in
requiredarray for all request/response bodies - Security schemes defined AND applied
- At least one
exampleper schema or response body - Tags defined at root level to match operation tags
- No orphaned schemas (everything in
components/schemasis referenced)
Step 8 - Output
- Emit the complete YAML (or JSON) spec in a code block labeled
yamlorjson. - After the spec, provide a brief summary table of endpoints generated.
- Offer to:
- Export as
.yaml/.jsonfile - Validate against Spectral or swagger-parser
- Generate mock server config (Prism)
- Generate client SDK stubs (language of choice)
- Export as
Extracting from Code
When the user provides source code, extract:
Express / Koa / Fastify (Node.js)
- Look for
.get(),.post(),.put(),.patch(),.delete()calls - Route params
:param→ path parameter{param} - Middleware like
authenticate→ note security requirement req.body,req.query,req.paramsusage → infer request schema
FastAPI / Flask (Python)
- Decorators:
@app.get(),@router.post(), etc. - Pydantic models → translate directly to JSON Schema
Query(),Path(),Body()→ map to parameter location
Spring Boot (Java)
@GetMapping,@PostMapping, etc.@PathVariable,@RequestParam,@RequestBody- DTO classes → schemas
Django REST Framework
ViewSetandRouter→ CRUD endpointsSerializerfields → schema properties
Rails
routes.rbresource routes → standard REST endpoints- Strong params → request body schema
Reference Files
reference/security-schemes.md- Detailed security scheme examples for all auth typesreference/common-patterns.md- Pagination, HATEOAS, problem+json, webhooks, file upload patterns
Read these when the user asks about a specific pattern or when generating complex auth/pagination setups.
After Completing the OpenAPI/Swagger Specification design
Once the OpenAPI/Swagger Specification output is delivered, ask the user:
"Would you like me to generate API test cases for this design? (yes/no)"
If the user says yes:
- Check if the API Test Case Generator skill is available in the installed skills list
- If the skill is available:
- Read and follow the instructions in the API Test Case Generator skill
- Use the specification output above as the input
- If the skill is NOT available:
- Inform the user: "It looks like the API Documentation skill isn't installed.
You can install it and re-run.
- Inform the user: "It looks like the API Documentation skill isn't installed.
If the user says no:
- End the task here
Limitations
- Use this skill only when the task clearly matches its upstream source and local project context.
- Verify commands, generated code, dependencies, credentials, and external service behavior before applying changes.
- Do not treat examples as a substitute for environment-specific tests, security review, or user approval for destructive or costly actions.
FAQ
Common questions
Discussion
Questions & comments · 0
Sign In Sign in to leave a comment.