Skip to main content
ClaudeWave
Skill171 repo starsupdated 27d ago

api-design

Design RESTful APIs with proper resource modeling, HTTP method semantics, status codes, pagination, versioning, and documentation. Use when the user requests api design or provides relevant inputs for this workflow.

Install in Claude Code
Copy
git clone --depth 1 https://github.com/seb1n/awesome-ai-agent-skills /tmp/api-design && cp -r /tmp/api-design/api-and-integration/api-design ~/.claude/skills/api-design
Then start a new Claude Code session; the skill loads automatically.

SKILL.md

# API Design

This skill enables an AI agent to design production-quality RESTful APIs. The agent models resources, defines endpoints with correct HTTP method semantics, selects appropriate status codes, implements pagination and versioning strategies, and produces OpenAPI documentation. The output follows REST constraints including statelessness, uniform interface, and resource-based URIs.

## Workflow

1. **Identify resources and relationships:** Analyze the application domain to extract nouns as resources (e.g., users, tasks, comments). Map relationships between resources—one-to-many, many-to-many—and determine whether sub-resources or independent collections are appropriate. Avoid verb-based endpoints; resources should represent entities, not actions.

2. **Define endpoints and HTTP methods:** For each resource, define CRUD endpoints using the correct HTTP methods. Use GET for retrieval (safe, idempotent), POST for creation (not idempotent), PUT for full replacement (idempotent), PATCH for partial updates (idempotent), and DELETE for removal (idempotent). Nest sub-resources under their parent when the relationship is strong (e.g., `/tasks/{id}/comments`).

3. **Design request and response schemas:** Define JSON request bodies, response payloads, and query parameters for each endpoint. Include field names in snake_case or camelCase consistently. Specify required vs. optional fields, data types, and validation constraints. Design a consistent error response envelope used across all endpoints.

4. **Implement pagination, filtering, and sorting:** For list endpoints, add cursor-based or offset pagination with `limit` and `offset` (or `cursor`) query parameters. Support filtering via query parameters (e.g., `?status=active`) and sorting with `sort` and `order` parameters. Return pagination metadata in the response body including total count, next/previous links.

5. **Define versioning and content negotiation:** Choose a versioning strategy—URI path (`/v1/tasks`), query parameter (`?version=1`), or Accept header (`Accept: application/vnd.api.v1+json`). URI path versioning is simplest and most common. Ensure backward compatibility within a version and document deprecation timelines.

6. **Generate OpenAPI documentation:** Produce a complete OpenAPI 3.0 specification with paths, schemas, security schemes, and example requests/responses. Include rate limiting headers (`X-RateLimit-Limit`, `X-RateLimit-Remaining`, `X-RateLimit-Reset`) in response documentation.

## Supported Technologies

- **Specification formats:** OpenAPI 3.0/3.1, JSON Schema, AsyncAPI (for event-driven extensions)
- **Frameworks:** Express.js, FastAPI, Django REST Framework, Spring Boot, Rails API
- **Documentation tools:** Swagger UI, Redoc, Stoplight
- **Testing:** Postman, Insomnia, REST Client (VS Code), curl

## Usage

Provide the agent with a description of the application domain, the entities involved, and the operations users need to perform. The agent will produce endpoint definitions, request/response schemas, and an OpenAPI specification. You can iterate by requesting changes to specific endpoints, adding pagination, or adjusting error formats.

## Examples

### Example 1: Task Management API (OpenAPI Spec Snippet)

```yaml
openapi: 3.0.3
info:
  title: Task Management API
  version: 1.0.0
  description: RESTful API for managing tasks and projects.

servers:
  - url: https://api.example.com/v1

paths:
  /tasks:
    get:
      summary: List all tasks
      parameters:
        - name: status
          in: query
          schema:
            type: string
            enum: [pending, in_progress, done]
        - name: limit
          in: query
          schema:
            type: integer
            default: 20
            maximum: 100
        - name: cursor
          in: query
          schema:
            type: string
      responses:
        "200":
          description: Paginated list of tasks
          headers:
            X-RateLimit-Limit:
              schema:
                type: integer
            X-RateLimit-Remaining:
              schema:
                type: integer
          content:
            application/json:
              schema:
                type: object
                properties:
                  data:
                    type: array
                    items:
                      $ref: "#/components/schemas/Task"
                  pagination:
                    $ref: "#/components/schemas/CursorPagination"
    post:
      summary: Create a new task
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: "#/components/schemas/TaskCreate"
      responses:
        "201":
          description: Task created
          content:
            application/json:
              schema:
                $ref: "#/components/schemas/Task"
        "422":
          description: Validation error
          content:
            application/json:
              schema:
                $ref: "#/components/schemas/ErrorResponse"

  /tasks/{taskId}:
    get:
      summary: Get a task by ID
      parameters:
        - name: taskId
          in: path
          required: true
          schema:
            type: string
            format: uuid
      responses:
        "200":
          description: Task details
        "404":
          description: Task not found

components:
  schemas:
    Task:
      type: object
      properties:
        id:
          type: string
          format: uuid
        title:
          type: string
        description:
          type: string
        status:
          type: string
          enum: [pending, in_progress, done]
        created_at:
          type: string
          format: date-time
    TaskCreate:
      type: object
      required: [title]
      properties:
        title:
          type: string
          maxLength: 255
        description:
          type: string
        assignee_id:
          type: string
agent-evaluationSkill

Design reproducible evaluations for AI agents with representative task sets, explicit rubrics, appropriate graders, baselines, regression gates, and failure analysis. Use when defining agent quality, comparing prompts or models, validating a release, measuring tool-use reliability, investigating regressions, or deciding whether an agent is ready for production.

agent-observabilitySkill

Design privacy-aware observability for AI agents using traces, spans, structured events, metrics, cost attribution, dashboards, alerts, and investigation workflows. Use when instrumenting an agent, debugging intermittent tool or model failures, defining service-level objectives, analyzing latency or spend, auditing agent decisions, or preparing production monitoring.

human-in-the-loopSkill

Design and verify auditable human oversight, approval gates, escalation paths, and safe state transitions for AI agent workflows. Use when deciding which agent actions require review, adding approve/reject or dual-control flows, preventing unauthorized autonomous effects, creating decision records, reducing rubber-stamping, or recovering safely from rejected, expired, or failed actions.

mcp-server-buildingSkill

Design, implement, harden, and verify Model Context Protocol (MCP) servers with precise tool contracts, least-privilege authorization, safe transports, structured errors, and interoperability tests. Use when creating a new MCP server, exposing an API or data source through MCP, reviewing an MCP server design, adding or revising MCP tools, or preparing an MCP server for production.

multi-agent-orchestrationSkill

Design and operate bounded multi-agent workflows with task decomposition, dependency graphs, ownership, handoff contracts, shared-state controls, approvals, recovery, and synthesis. Use when a task contains genuinely independent workstreams, specialized roles, parallel research or implementation, reviewer-worker loops, or coordination problems that one agent should not execute sequentially.

tool-schema-designSkill

Design and validate model-facing tool definitions with clear names, action-oriented descriptions, bounded JSON Schema parameters, explicit side effects, safe defaults, idempotency, errors, and realistic tests. Use when creating function-calling tools, MCP tools, agent actions, structured tool inputs, or when a model selects the wrong tool, invents arguments, or causes unsafe side effects.

agent-red-teamingSkill

Plan, execute, document, and retest authorized security assessments of AI agents and multi-agent workflows using safe adversarial cases, synthetic identities, canaries, and evidence-based findings. Use when defining red-team rules of engagement, assessing prompt injection or excessive agency, testing tool and identity boundaries, evaluating memory or cross-agent attacks, scoring a campaign, or verifying remediation in an approved environment.

prompt-injection-defenseSkill

Threat-model and harden AI agents, RAG systems, assistants, and tool-using workflows against direct, indirect, stored, cross-agent, and multimodal prompt injection. Use when reviewing an agent architecture, isolating untrusted content, constraining tools and egress, protecting secrets, adding injection-focused tests, investigating a suspected injection incident, or documenting residual prompt-injection risk.