- Home
- Skills
- APIs & Backend
- requirements to specs
Works with the AI Agents you already use
requirements to specs
Convert natural language requirements into validated OpenAPI contracts, Gherkin features, and AI agent tool specs.
$10
requirements to specs
Example session with this skill installed
Create specs for a pet clinic booking system. It needs an API for appointments, vets, and pet records. Include Gherkin tests for the booking flow. Use the specs/ folder.
- Read your context and instructions
- Compiled the requirements to specs
I have extracted the requirements for the Pet Clinic Booking System and generated the formal specifications.
Pet Clinic Booking Specs
The system manages Pets, Vets, and Appointments with constraints on authentication and scheduling availability.
Output Directory: specs/20250520T143000Z/
| File | Type | Description |
|---|---|---|
openapi.yaml | OpenAPI 3.1 | REST API for managing pet records and scheduling appointments. |
features/booking.feature | Gherkin | BDD scenarios for successful booking and handling unavailable slots. |
README.md | Documentation | Summary of entities, actions, and validation results. |
# openapi.yaml (Excerpt)
openapi: 3.1.0
info:
title: Pet Clinic API
version: 1.0.0
paths:
/appointments:
post:
summary: Create a booking
requestBody:
content:
application/json:
schema:
type: object
properties:
pet_id: { type: string }
vet_id: { type: string }
start_time: { type: string, format: date-time }
responses:
'201':
description: Created
'409':
description: Slot unavailable
# features/booking.feature
Feature: Appointment Booking
Scenario: Successfully book a vet visit
Given a vet "Dr. Smith" is available at "2025-06-01T10:00:00Z"
And a registered pet "Buddy"
When the user requests a booking for "Buddy" with "Dr. Smith"
Then the system should return a 201 Created response
And the appointment should be saved
Next steps
- Run
python scripts/validate_specs.py specs/20250520T143000Z/to confirm parser compliance. - Review the
Assumptionssection in the generatedREADME.mdregarding vet working hours. - Import
openapi.yamlinto your API client or mock server to begin development.
Connects securely to your tools. The creator never sees your data.
About this skill
Software development fails when requirements are vague. This skill bridges the gap between natural language briefs and formal technical specifications. It consumes PRDs, tickets, or feature descriptions to produce validated OpenAPI contracts, BDD scenarios, and AI agent prompts.
What it does
- Requirement extraction identifies domain entities, actions, constraints, and integrations from raw text.
- API contract generation builds OpenAPI 3.1 YAML files for HTTP-based services.
- BDD scenario creation writes Gherkin
.featurefiles to define acceptance criteria and test paths. - AI agent spec design creates system prompts and JSON tool definitions for LLM-based systems.
- Automated validation runs a Python-based parser suite to ensure all generated files are syntactically correct and internally consistent.
How it works
- Analyze input to extract the system domain, entities, and business logic.
- Select spec types based on the system architecture (REST API, BDD, or AI Agent).
- Generate artifacts in a timestamped directory to prevent file overwrites.
- Run validation using
scripts/validate_specs.pyto check for structural and logical errors. - Finalize documentation with a README covering assumptions, entities, and validation status.
Frameworks & tools
This skill utilizes OpenAPI 3.1, Gherkin, Python 3.9+, and standard LLM system prompt structures. Validation requires pyyaml, openapi-spec-validator, and gherkin-official.
Why this beats prompting it yourself
Standard prompts often produce specs that look correct but fail parsing or contain logical gaps between the API and test scenarios. This skill uses a multi-step validation loop that checks for missing identifiers across files and enforces structural integrity via real Python parsers.
Use cases
- Generate API contracts and test scenarios from a Jira ticket or Slack message.
- Scaffold a new microservice by defining entities and CRUD operations first.
- Design tool-calling interfaces for AI agents based on existing business rules.
- Maintain consistency between documentation, API design, and acceptance tests.
Known limitations
Large systems with more than 8 entities or 12 actions are truncated to core functionality. Requires a Python environment for the automated validation script to run.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for APIs & Backend.
Large systems with >8 entities or >12 actions are truncated to core functions. Full validation requires a Python 3.9 environment with specific pip packages.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 5 days ago
- Software
Python