Skills· Software Development & Technical Infrastructure

    The API Playbook

    The API Playbook turns a technical API specification into complete, developer-friendly documentation, from a quick start guide to a full endpoint and error reference.

    writingstructuring

    Description

    Example scenario

    A team has built a REST API for a booking system. Partner companies need to integrate it, but the existing documentation is nothing more than a Swagger file. What is needed is developer-friendly documentation with a quick start guide, an authentication guide, and examples in JavaScript and Python, so partners can make their first successful booking call within an hour.

    Steps

    Every step shows who carries it out: icon, colour and label together indicate whether a person acts, whether it runs automatically, whether a result is produced, or whether an approval is required.

    01Person

    Endpoints, the authentication method, request and response formats, and the target audience are provided.

    02Automated

    03Result

    04Approval

    Key
    PersonAutomatedResultApproval

    In use

    API specification

    Required

    Request and response formats

    Required

    Authentication method

    Required

    Target audience

    Optional

    Existing documentation

    Optional

    Sample data

    Optional

    Output

    Complete documentation with an overview, quick start guide, authentication guide, endpoint reference, code examples in multiple languages, error reference, rate limits, and changelog.

    Skill Text

    # TASK
    You write developer-friendly API documentation. From a technical API specification, you produce clear, immediately usable documentation with working examples that lets developers integrate quickly.
    
    # INPUTS NEEDED
    Required:
    - API specification: endpoints, HTTP methods, parameters
    - Request and response formats: JSON schemas, data types
    - Authentication method: API key, OAuth, JWT
    
    Optional, where available:
    - Target audience: frontend, backend, partners, external developers
    - Existing documentation: OpenAPI/Swagger, Postman
    - Sample data: realistic test data
    
    # APPROACH
    
    Clarify the foundation: capture the API's purpose, its endpoints, and the underlying data model before writing a single line of documentation.
    
    Write the core documents: start with the quick start guide, the shortest path to the first successful API call. Then authentication, with concrete examples and troubleshooting notes, since integrations most often stall at exactly these two points.
    
    Build out the full reference: document URL, method, parameters, and response for every endpoint, complete with examples, so no follow-up question to the development team is needed.
    
    Cover the edges and check the work: capture every error code and the rate limits. Finally, review all examples for correctness and consistency.
    
    # STRUCTURE OF THE DOCUMENTATION
    The result is complete API documentation with exactly these sections, in this order:
    1. Overview: what the API does, base URL, versioning
    2. Getting started: quick start guide
    3. Authentication: guide with examples
    4. Endpoint reference: per endpoint URL, method, parameters, response
    5. Request examples: Curl, JavaScript, Python
    6. Response examples: success and error
    7. Error reference: HTTP status codes and messages
    8. Rate limits: usage restrictions
    9. Changelog: version history
    
    # QUALITY BAR
    The documentation only counts as finished once:
    - every endpoint is fully documented,
    - the quick start guide actually enables a fast start,
    - authentication is described clearly and is easy to follow,
    - every endpoint has a working example,
    - error responses are documented,
    - all code examples are syntactically correct.
    
    # LIMITS AND LANGUAGE
    - Global placeholders: COMPANY, TECH_STACK
    - Domain knowledge drawn on: REST API design, HTTP standards, authentication protocols
    - This task covers writing documentation only, not implementing an API.
    - Address the user in a professional manner throughout.
    - Where details on the API are missing or unclear, explicitly flag the affected part as an assumption instead of setting it silently.
    
    # OPENING THE CONVERSATION
    Which API should be documented? Share the endpoints, the authentication method, and the target audience, and developer-friendly API documentation will follow.

    Setup

    Step-by-step guides for ChatGPT, Claude, Copilot Studio and Langdock.

    ChatGPT

    OpenAI

    1. Copy the skill text above using the copy button.
    2. Click your profile picture and select "Skills".
    3. Click "Create skill" and paste the copied text as the instruction.
    4. Adjust inputs, outputs and format where your case requires it.
    5. Save the skill. It is available in all chats from that point on.
    Documentation

    Anthropic

    1. Copy the skill text above using the copy button.
    2. Open claude.ai and go to "Skills" in your profile.
    3. Create a new skill and paste the copied text as the instruction.
    4. The skill works in claude.ai, in Claude Code and through the API.
    5. Available on the Pro, Max, Team and Enterprise plans.
    Documentation

    Microsoft

    1. Copy the skill text above using the copy button.
    2. Open Copilot Studio and create a new agent.
    3. Paste the copied text as the instruction.
    4. Connect knowledge sources and tools where needed.
    5. Publish the agent for yourself or for your organisation.
    Documentation

    1. Copy the skill text above using the copy button.
    2. Open the sidebar and click "Add skill".
    3. Paste the copied text directly as the instruction.
    4. Connect the skill to integrations such as Gmail or Slack where needed.
    5. Save the skill and release it for yourself or your team.
    Documentation

    Implementation

    1. Have the API specification ready

      An OpenAPI or Swagger file, or alternatively a manually compiled list of endpoints, is prepared before starting.

    2. Set up the skill

      The skill text is copied and the specification is provided as input.

    3. Generate the documentation

      The assistant writes the documentation section by section, starting with the quick start guide.

    4. Test the examples

      The generated code examples are checked against the real API before the documentation is published.

    5. Maintain it as a living document

      Whenever endpoints are added or formats change, the documentation is run through again and updated.

    Last reviewed:

    In the workshop this becomes your method.

    A single prompt becomes a repeatable method. We show that in the workshop From Prompt to Method.

    View workshops

    Related resources

    Browse all resources

    Conversation, not pitch

    Understand first, then decide. We take time for an initial conversation, without sales pressure, without obligation.

    Schedule a call