Generate type-safe API clients from OpenAPI/Swagger specifications or API documentation. Use when users need to create TypeScript or Python API clients with Zod/Pydantic validation, retry logic, error handling, and proper typing. Supports REST APIs, generates from OpenAPI specs or manual endpoint definitions.
/plugin marketplace add leobrival/topographic-studio-plugins/plugin install code-workflows@topographic-studio-pluginsThis skill inherits all available tools. When active, it can use any tool Claude has access to.
assets/python/complete_client.pyassets/python/httpx_client.pyassets/python/models_template.pyassets/typescript/complete-client.tsassets/typescript/fetch-client.tsassets/typescript/ky-client.tsassets/typescript/types-template.tsreferences/authentication.mdreferences/error-handling.mdreferences/openapi.mdreferences/retry-patterns.mdGenerate production-ready, type-safe API clients for TypeScript or Python.
User request → What source?
│
├─ OpenAPI/Swagger spec → Auto-generate from spec
│ ├─ TypeScript → openapi-typescript + zod
│ └─ Python → openapi-python-client
│
├─ API documentation URL → Fetch and analyze
│ └─ Extract endpoints → Generate manually
│
└─ Manual endpoint list → Generate from scratch
├─ TypeScript → See assets/typescript/
└─ Python → See assets/python/
What HTTP client?
│
├─ TypeScript
│ ├─ fetch (native) → Recommended for browser/edge
│ ├─ ky → Fetch wrapper with retry
│ └─ axios → Node.js with interceptors
│
└─ Python
├─ httpx → Async + sync, recommended
├─ aiohttp → Async only
└─ requests → Sync only, legacy
# Install generators
pnpm add -D openapi-typescript openapi-fetch
# Generate types
pnpm openapi-typescript ./openapi.yaml -o ./src/api/schema.d.ts
# Use with openapi-fetch
pnpm add openapi-fetch
import createClient from "openapi-fetch";
import type { paths } from "./schema";
const client = createClient<paths>({ baseUrl: "https://api.example.com" });
const { data, error } = await client.GET("/users/{id}", {
params: { path: { id: "123" } },
});
# Install generator
pip install openapi-python-client
# Generate client
openapi-python-client generate --url https://api.example.com/openapi.json
Use templates from assets/ directory and customize:
| Use Case | Template | HTTP Client |
|---|---|---|
| Browser/Edge | fetch-client.ts | Native fetch |
| Node.js | ky-client.ts | ky |
| Legacy/Interceptors | axios-client.ts | axios |
| Full-featured | complete-client.ts | ky + zod |
| Use Case | Template | HTTP Client |
|---|---|---|
| Modern async/sync | httpx-client.py | httpx |
| Async only | aiohttp-client.py | aiohttp |
| Simple sync | requests-client.py | requests |
| Full-featured | complete-client.py | httpx + pydantic |
api/
├── client.ts # Main client class
├── types.ts # Request/response types
├── schemas.ts # Zod/Pydantic schemas
├── errors.ts # Custom error classes
├── endpoints/
│ ├── users.ts # /users endpoints
│ ├── posts.ts # /posts endpoints
│ └── index.ts # Export all
└── utils/
├── retry.ts # Retry logic
├── auth.ts # Auth helpers
└── logger.ts # Request logging
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.