Vibe Python Style logo

Vibe Python Style

OrganizationPopular
mistralai
vibe-python-style

Python coding conventions for Mistral Vibe. Use when writing, reviewing, or refactoring Python code in the Vibe codebase. Covers style, type hints, imports, Pydantic patterns, logging, error handling, and file I/O.

Overview

Publishermistralai
Repositorymistral-vibe
Skill namevibe-python-style
Stars
5.1K
Forks
732
Bundled files
Instructions only
LicenseApache-2.0
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 mistralai on GitHub. Read the source before you install it.

Installation

Install the Vibe Python Style 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.
    https://github.com/mistralai/mistral-vibe/tree/main/.agents/skills/vibe-python-style
  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/mistralai/mistral-vibe.git /tmp/mistral-vibe
mkdir -p .claude/skills
cp -r /tmp/mistral-vibe/.agents/skills/vibe-python-style .claude/skills/vibe-python-style
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Vibe Python Style 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 Vibe Python Style 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 Vibe Python Style 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.

Vibe Python Style

Conventions for writing Python in the Vibe codebase. Apply whenever writing, reviewing, or refactoring Python code.

Style

  • Prefer match / case over long if / elif chains.
  • Use the walrus operator := only when it shortens code and improves clarity.
  • Be a never-nester: early returns and guard clauses over nested blocks.
  • Modern type hints only: built-in generics (list, dict) and | unions. Never import Optional, Union, Dict, List from typing.
  • Use pathlib.Path (and anyio.Path in async paths) instead of os.path.
  • Use f-strings, comprehensions, and context managers; follow PEP 8.
  • Enums: StrEnum / IntEnum with auto() and UPPERCASE members. For type-mixing, the mix-in type comes before Enum in the bases. Add methods or @property rather than parallel lookup tables.
  • Write declarative, minimalist code: express intent, drop boilerplate.
  • Never call a private method from outside of its class in production code. Accessing private methods in tests is acceptable.
  • Avoid comments and docstrings, except for when there's a hard to spot corner case

Typing & imports

  • Pyright is strict and gates CI; fix types at the source.
  • No relative imports — ban-relative-imports = "all". Always from vibe.core.x import ….
  • No inline # type: ignore or # noqa. Fix with refined signatures (TypeVar, Protocol), isinstance guards, typing.cast when control flow guarantees the type, or a small typed wrapper at the boundary.

TYPE_CHECKING and lazy imports

Moving imports under if TYPE_CHECKING: or into function bodies cuts startup time but risks runtime NameError. Before merging any import-deferral change, run:

  • Ruff TC004 (pre-commit hook) — per-file: flags TYPE_CHECKING-only names referenced at runtime.
  • uv run python scripts/check_import_contracts.py — runtime cross-file: imports every from <mod> import <name> across vibe/ and tests/ to verify it resolves; also rebuilds Pydantic models to catch lazily-failing field types. Catches cross-file re-exports TC004 misses. Missing non-vibe deps are non-blocking warnings.
  • uv run scripts/suggest_lazy_imports.py — informational: reports deferral candidates (TC001–TC003 + single-function heuristic). Not gated.

Pydantic

  • Parse external data via model_validate, field_validator, or model_validator(mode="before") — never ad-hoc getattr / hasattr walks or custom from_sdk constructors.
  • Set ConfigDict(extra=…) explicitly. Use validation_alias (or field aliases) for kebab-case TOML keys.
  • Discriminated unions (e.g. MCP transport): use sibling final classes plus a shared base/mixin, and compose with Annotated[Union[...], Field(discriminator=...)]. Never narrow the discriminator field in a subclass — it violates LSP and pyright will reject it.
  • Document Raises: only for exceptions the function actually raises (or that propagate from public API calls). Don't list speculative built-ins.

Logging & errors

  • Use from vibe.observability.logging import logger — stdlib logging with StructuredLogFormatter, not structlog.
  • Configure via env: LOG_LEVEL (default WARNING), LOG_MAX_BYTES. Logs land in ~/.vibe/logs/vibe.log.
  • Pass variables as %s positional args, not f-string interpolation: prefer logger.error("Failed to fetch url=%s", url) over logger.error(f"Failed to fetch {url}"). This defers formatting to the logging framework (only formats if the message is emitted) and keeps messages grep-friendly.
  • Define module-local exception hierarchies. Always chain with raise NewError(...) from e. Rich exceptions expose a _fmt() helper for human-readable output.

File I/O

  • Prefer vibe.core.utils.io.read_safe / read_safe_async / decode_safe over raw Path.read_text(), Path.read_bytes().decode(), or open().
  • They return ReadSafeResult(text, encoding) and try UTF-8, then BOM detection, then locale, then charset_normalizer lazily.
  • Pass raise_on_error=True only when callers must distinguish corrupt files from valid ones; the default replaces undecodable bytes with U+FFFD.

Frequently asked questions

What does the Vibe Python Style AI skill do?

Python coding conventions for Mistral Vibe. Use when writing, reviewing, or refactoring Python code in the Vibe codebase. Covers style, type hints, imports, Pydantic patterns, logging, error handling, and file I/O.

Why use Vibe Python Style on TypingMind?

Because you install it once and use it with any model. Vibe Python Style 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 Vibe Python Style in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/mistralai/mistral-vibe/tree/main/.agents/skills/vibe-python-style. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Vibe Python Style?

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 Vibe Python Style?

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

Is the Vibe Python Style AI skill free?

Yes. It is published on GitHub by mistralai under the Apache-2.0 license. 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 👇