Routing Api logo

Routing Api

Community
psincraian
routing-api

myfy web routing with FastAPI-like decorators. Use when working with WebModule, @route decorators, path parameters, query parameters, request bodies, AuthModule for authentication, RateLimitModule for rate limiting, or error handling.

Overview

Publisherpsincraian
Repositorymyfy
Skill namerouting-api
Stars
88
Forks
1
Bundled files
Instructions only
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by psincraian on GitHub. Read the source before you install it.

Installation

Install the Routing Api AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/psincraian/myfy.git /tmp/myfy
mkdir -p .claude/skills
cp -r /tmp/myfy/plugins/claude-code/skills/routing-api .claude/skills/routing-api
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Routing Api in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Routing Api on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Routing Api is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Web Routing in myfy

myfy provides FastAPI-like routing with full DI integration.

Route Decorators

python
from myfy.web import route

@route.get("/path")
async def handler() -> dict:
    return {"message": "hello"}

@route.post("/path", status_code=201)
async def create() -> dict:
    return {"created": True}

@route.put("/path/{id}")
async def update(id: int) -> dict:
    return {"updated": id}

@route.delete("/path/{id}", status_code=204)
async def delete(id: int) -> None:
    pass

@route.patch("/path/{id}")
async def partial_update(id: int) -> dict:
    return {"patched": id}

Path Parameters

Extract from URL template using {param}:

python
@route.get("/users/{user_id}/posts/{post_id}")
async def get_post(user_id: int, post_id: int) -> dict:
    return {"user": user_id, "post": post_id}

Path parameters are:

  • Automatically type-converted based on annotation
  • Must match function parameter names exactly
  • Must be valid Python identifiers

Query Parameters

Use Query for explicit query parameters:

python
from myfy.web import Query

@route.get("/search")
async def search(
    q: str = Query(default=""),           # With default value
    limit: int = Query(default=10),       # Integer query param
    page: int = Query(alias="p"),         # Aliased (?p=1 in URL)
) -> dict:
    return {"query": q, "limit": limit, "page": page}

Request Body

Use Pydantic models or dataclasses for request bodies:

python
from pydantic import BaseModel

class UserCreate(BaseModel):
    email: str
    name: str

@route.post("/users", status_code=201)
async def create_user(body: UserCreate, session: AsyncSession) -> dict:
    user = User(**body.model_dump())
    session.add(user)
    await session.commit()
    return {"id": user.id}

Request bodies are automatically:

  • Parsed from JSON
  • Validated by Pydantic
  • Type-checked at runtime

Parameter Classification

Parameters are classified in this order:

  1. Path parameters - Names matching {param} in route path
  2. Query parameters - Annotated with Query(...)
  3. Body parameter - Pydantic model, dataclass, or dict
  4. DI dependencies - Everything else (resolved from container)
python
@route.post("/users/{user_id}/orders")
async def create_order(
    user_id: int,                    # 1. Path param (matches {user_id})
    limit: int = Query(default=10),  # 2. Query param (explicit Query)
    body: OrderCreate,               # 3. Request body (Pydantic model)
    session: AsyncSession,           # 4. DI dependency
    settings: AppSettings,           # 4. DI dependency
) -> dict:
    ...

Authentication

Use Authenticated for protected routes:

python
from myfy.web import Authenticated, AuthModule
from dataclasses import dataclass

@dataclass
class User(Authenticated):
    email: str

# Register auth provider
def my_auth(request: Request) -> User | None:
    token = request.headers.get("Authorization")
    if not token:
        return None  # Results in 401
    return User(id="123", email="user@example.com")

app.add_module(AuthModule(authenticated_provider=my_auth))

# Protected route - returns 401 if not authenticated
@route.get("/profile")
async def profile(user: User) -> dict:
    return {"id": user.id, "email": user.email}

Error Handling

Quick Errors with abort()

python
from myfy.web import abort

@route.get("/users/{user_id}")
async def get_user(user_id: int, session: AsyncSession) -> dict:
    user = await session.get(User, user_id)
    if not user:
        abort(404, "User not found")
    return {"user": user}

Typed Errors

python
from myfy.web import errors

raise errors.NotFound("User not found")
raise errors.BadRequest("Invalid email", field="email")
raise errors.Unauthorized("Invalid token")
raise errors.Forbidden("Access denied")
raise errors.Conflict("Email already exists")

Custom Exceptions

python
from myfy.web.exceptions import WebError

class RateLimitExceeded(WebError):
    status_code = 429
    error_type = "rate_limit_exceeded"

Rate Limiting

python
from myfy.web.ratelimit import RateLimitModule, rate_limit, RateLimitKey

# Add module
app.add_module(RateLimitModule())

# Rate limit by IP (default)
@route.get("/api/data")
@rate_limit(100)  # 100 requests per minute per IP
async def get_data() -> dict:
    ...

# Rate limit by authenticated user
@route.get("/api/profile")
@rate_limit(50, key=RateLimitKey.USER)
async def get_profile(user: User) -> dict:
    ...

Response Types

Routes can return:

python
# Dict (serialized to JSON)
@route.get("/json")
async def json_response() -> dict:
    return {"key": "value"}

# Pydantic model (serialized to JSON)
@route.get("/model")
async def model_response() -> UserResponse:
    return UserResponse(id=1, name="John")

# None for 204 No Content
@route.delete("/users/{id}", status_code=204)
async def delete_user(id: int) -> None:
    ...

Best Practices

  1. Always use async - All handlers should be async functions
  2. Type all parameters - Use type hints for auto-classification
  3. Use Pydantic for bodies - Get free validation
  4. Return typed responses - Prefer Pydantic models over dicts
  5. Use appropriate status codes - 201 for creation, 204 for deletion
  6. Handle errors explicitly - Use abort() or typed errors
  7. Document with docstrings - Add OpenAPI-compatible docs

Frequently asked questions

What does the Routing Api AI skill do?

myfy web routing with FastAPI-like decorators. Use when working with WebModule, @route decorators, path parameters, query parameters, request bodies, AuthModule for authentication, RateLimitModule for rate limiting, or error handling.

Why use Routing Api on TypingMind?

Because you install it once and use it with any model. Routing Api is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Routing Api in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/psincraian/myfy/tree/main/plugins/claude-code/skills/routing-api. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Routing Api?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Routing Api?

As many as you like. As long as a model supports skills, you can use Routing Api with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Routing Api AI skill free?

It is published on GitHub by psincraian. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇