Flow Py — AI skill for Claude Code
The unofficial Python API, CLI, MCP Server & Universal Skill for Google Flow.
How to install Flow Py
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open twofxz/flow-py and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Flow Py does
The unofficial Python API, CLI, MCP Server & Universal Skill for Google Flow. Deterministic image (Nano Banana 2) & video (Veo/Omni Flash) generation for AI agents (Claude, Codex, OpenClaw, Antigravity) with zero token waste.
Alternatives in AI
- System Prompts Leaks — Extracted system prompts from ChatGPT (GPT-5.4, GPT-5.3, Codex), Claude (Opus 4.6, Sonnet 4.6, Claude Code), G 38.6k ★
- Claude Flow — An enterprise-grade AI orchestration platform that revolutionizes how developers build with AI 22.2k ★
- Optimization — ai-research-skills AWQ, GPTQ, GGUF, Flash Attention, bitsandbytes 5.4k ★
README
🎨 flow-py: Google Flow for AI Agents (`google-flow-api`)
**The Unofficial Multi-Agent Automation Engine, CLI, MCP Server & Universal Skill for Google Flow.** Offload production-grade image generation (Nano Banana 2, Nano Banana Pro, Imagen 3) and cinematic video generation (Gemini Omni Flash 1.1) to Google Flow directly from any AI Agent — with zero token waste and native original quality.
[](https://opensource.org/licenses/MIT) [](https://www.python.org/downloads/) [](https://modelcontextprotocol.io) [](SKILL.md) [](SECURITY.md)
🤖 Multi-Agent Compatibility Matrix
`google-flow-api` is built from the ground up to integrate natively into every major AI coding and automation agent:
| Agent / Harness | Integration Mechanism | Configuration File |
|---|---|---|
| Claude Code (Anthropic) | Native CLI / CLAUDE.md |
`CLAUDE.md` |
| OpenAI Codex | Subprocess CLI / AGENTS.md |
`AGENTS.md` |
| OpenClaw | Autonomous Skill Runner | `SKILL.md` |
| Hermes Agent (Nous Research) | CLI --json Envelopes |
`SKILL.md` |
| OpenCode | Skill / MCP Stdio Server | `AGENTS.md` / google-flow mcp |
| Google Antigravity | Native Workspace Skill | ~/.gemini/config/skills/google-flow/ |
| Cursor / Windsurf / Claude Desktop | Model Context Protocol (MCP) | claude_desktop_config.json |
✨ Key Capabilities
- 🤫 Silent Background Engine (Headless-by-Default): Operates 100% invisibly in the background with zero window popups (parity with
/notebooklm). Chrome runs in `--headless=new
Related Skills
Visual Skills
AI film director skills for agents: cinematic dramaturgy (Murch, blocking, montage) + exact prompt syntax for
Claude Drives Gemini
Let your AI agent drive the Gemini web app through your existing Google AI Pro subscription - generate images
Nano Banana 2 Skill
AI image generation CLI powered by Gemini 3 Pro. Green screen transparency, reference images, style transfer.
Nano Banana
Generate or edit images using Google's Gemini Image model
Omni Ad
Claude Code skill: turn any product into an AI ad (GPT Image 2.0 poster + Google Omni Flash video) with halluc
Img
Gera imagem por IA (gpt-image-2 ou nano-banana-2) via /image-gen
Related Agents
Scene Prompt Smith
Use this agent when drafting kie.ai Nano Banana 2 image prompts for the scenes of a short video. It turns a sc
Vf Operator
Оператор видео-фабрики. Гонит кадры через модели напрямую по своим ключам — Veo 3.1, Sora 2, кадры Nano Banana
Asset Generator
AI asset generation agent — connects to image generation APIs (Nano Banana, FAL AI, Replicate), manages asset