Hire an AI API service and test builder

Everything it can hand back

Your task sets the actual outputs. The specialist picks the methods that cover them.

• A project folder with the structure and setup steps
• Routes, database design and sign-in checks
• Tests for every route, with sample data
• A complete API spec file you can share

How it does the job well

• Read the existing code, its conventions and its tests before changing anything. Match the project's patterns.
• Make the smallest change that fully solves the request. Keep unrelated refactors out.
• Reproduce a bug before fixing it, and add a test that fails without the fix.
• Treat input from users, files and networks as untrusted. Validate it at the boundary.

Mistakes it avoids

• Claiming code works without running it or its tests.
• Inventing APIs, package versions or settings instead of checking the installed ones.
• Changing behaviour outside the request, such as reformatting whole files or renaming public interfaces.

What a good result looks like

An example, not your task: You have a spec or a feature list for a service and no code yet.

• Step 1, Project. Your spec in plain words, the stack, a file list and setup steps.
• Step 2, Service. Routes, database design, sign-in checks, undoable migrations and a load test result.
• Step 3, Route tests. A route map, tests for sign-in, bad input and error codes, with results and gaps.
• Step 4, API spec. Endpoints, data shapes, the sign-in scheme and an example for each response.
• Hand-back summary. Each step's file and one list of everything marked MISSING.

How the work is checked

• Each step passed its own checks, or the run stopped at the step that failed and says why.
• The steps ran in order, and each one used the result of the one before.
• Nothing was invented to fill a gap. Every gap is a MISSING: line.
• Nothing was sent, published or paid for without a clear yes.
• States which checks passed, failed or could not run, and names missing inputs.

These checks have not been run against a model yet. Your AI uses them to check its own work.

A second opinion

Before it hands back, your AI reviews the draft the way Kent Beck would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Start the project. Reads your spec, says back what it means, picks the stack, lists every file, generates the project and checks that it runs.
• Build the service. Designs the routes and database, writes the routes with checks on input and sign-in, adds migrations that can be undone and load tests the busiest route.
• Test every route. Finds each route in the code and writes tests for sign-in, bad input, error codes, paging and uploads, then runs them.
• Write the API spec. Pulls the endpoints from the finished code and writes a complete spec with data shapes and an example for each response.

How the role works

1. Checks your task, context and available tools.
2. Picks the methods needed and prepares a work plan.
3. Carries out supported tasks, with each method's limits and review gates.
4. Checks the real deliverables and corrects supported faults.
5. Hands back files, evidence and unresolved gaps.

Your specialist's working setup

Download the base specialist without a task form or account. README.md and SETUP.md explain how to use the folder. SOUL.md defines its scope. INTAKE.md asks missing questions inside your AI. PLAYBOOK.md, SKILLS.md, BEST_PRACTICES.md, CHECKS.md and HANDOFF.md guide the work and its checked deliverables.

Complete associated skills, supporting files and licences are included. Choose only the methods needed for the actual task. Keep context, working files and accepted feedback in your AI project.

Use this specialist through MCP or the API

Call prepare_specialist with role_id turn-a-spec-into-a-tested-service-with-api-docs only. No task is required to load it. Your AI asks what job you need done, what you want back and which relevant context it can use.

For task-led hiring, call find_specialist, explain the suggested specialists and let the user accept or change the team.

Complete ZIP: Download base specialist. API: GET /api/v1/specialists/turn-a-spec-into-a-tested-service-with-api-docs/pack. The host AI supplies its own model, tools and execution; a pack does not connect accounts or run a task.

Inputs and helpful context

The specialist starts from the task brief. Only active methods require their inputs.

For the primary method, when used

• A written spec that says what the service does, who uses it and what data it keeps
• Your preferred language and database, or let it choose
• How sign-in should work (optional)
• Where it will run (optional)

Functions and deliverables

• API service and test builder: Share the service spec, code environment and limits. Get a starter project, service code, route tests and API docs, with actual run results.
  • A project folder with the structure and setup steps
  • Routes, database design and sign-in checks
  • Tests for every route, with sample data
  • A complete API spec file you can share
• Starter code project builder: Give it an app spec and any required stack. Get a project scaffold, starter code and setup steps to validate.
  • A summary of how your AI read your spec, for you to confirm
  • A file tree you can check before any code is written
  • A project folder with config, source code and tests. It is a starting point. It may need dependency fixes and a developer review before real use or deployment.
  • A README with setup and run steps
  • A checklist result that shows problems it found
  Source: Alireza Rezvani.
• Backend builder: Share the service needs and existing code. Get server code, data design, login flows or fixes, with checks and open gaps.
  • API route handlers and validation
  • Database analysis and migration notes
  • Load test results
  • Security hardening steps
  Source: Alireza Rezvani.
• API test suite builder: Share route code and expected behaviour. Get integration and contract test files with fixtures, error cases and open coverage gaps.
  • Test files for each route
  • Sign-in and permission cases
  • Bad input and error code checks
  • Test data fixtures
  Source: Alireza Rezvani.
• API spec writer: Share routes, code or an API description. Get an OpenAPI or Swagger spec with schemas, errors and sign-in rules to validate.
  • A complete OpenAPI or Swagger file
  • Endpoints with request and response shapes
  • Security setup
  • Reusable data schemas
  Source: sickn33.
• AI project context organiser: Share your project and next task. Get a short rules file, a focused file list and a clear handoff for later sessions.
  • A ready rules file for your project
  • A list of which files to load for each task
  • Rules for when to reset or trim the session
  • A checklist for spotting drifting answers
  Source: Addy Osmani.
• Kent Beck: Plan a software change using Kent Beck’s recorded approach. List the cases, take small steps and keep code tidying separate from new behaviour.
  • Your problem worked on the way Kent Beck would: their questions, their method, their push-back
  • The answer or the work, in Kent Beck's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step

Tasks you can use it for

• You have a spec or a feature list for a service and no code yet.
• You want tests and API docs that match the code, not written from memory.
• A new project needs a sound first version before the team builds on it.

Limits to check before starting

• You already have a service and want its bugs found: use Bug and security code reviewer.
• Your routes exist and you only need documents: use API spec writer.
• Your spec is already an OpenAPI file and you want an app from it: use OpenAPI app builder.

Best way to use this role

Give it one clear outcome, the actual files and a definition of done. Keep the work in one AI project so it can reuse checked context and earlier files.

• Download the handoff pack. It holds HANDOFF.md and the 4 skill files in the order they run: Spec to starter repo builder, Backend builder, API test suite builder and API spec writer.
• Open an empty folder in Claude Code, give it the pack and say "Follow HANDOFF.md".
• Paste your spec. Check the plain-words summary it gives back and fix anything it got wrong.
• After the build, run the service and the tests yourself.
• Open the API spec in a viewer and compare it with a few real requests.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/turn-a-spec-into-a-tested-service-with-api-docs for its role instructions and pinned sources.

This is a prepared AI role. No task has run. Your AI carries out authorized work using its available tools and reports the actual deliverables and checks.