workflowstacks
ai-agent

Flowkit: Automate Video Creation

Flowkit helps founders automate video creation tasks, ideal for those using Google Flow, with 496 GitHub stars.

From the repo · “AI agent can create video content better than you. No reason why you do it manually in google flow!”

1,046 stars+67★ this week531 forksPythonGuide quality 8/10 · reviewed Jul 3Updated 10/6/2026100% free · open source
What it does

Flowkit automates video creation tasks, particularly for those using Google Flow, by utilizing an AI agent to generate video content

When to use it
  • •You need to create multiple videos with similar formats and content
  • •You want to automate video creation tasks to save time and resources
  • •You are already using Google Flow and want to integrate AI-powered video creation
Ready-to-paste prompt
python flowkit.py --prompt 'Create a 60-second explainer video for a new startup' --format mp4 --output output.mp4
Heads up: Make sure you have the necessary Google Flow credentials and API keys set up and configured correctly in the `config.json` file to avoid authentication errors
Saves to your device
Use with Claude
New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🛠️ Technical setup

Expect 20–40 minutes in a terminal — or let your AI agent drive it.

Try it instantly — no install
Claude Code
mkdir -p ~/.claude/skills/flowkit && curl -fsSL https://workflowstacks.com/api/skills/flowkit/claude-skill -o ~/.claude/skills/flowkit/SKILL.md
Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)
claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How Flowkit: Automate Video Creation works
Codeflow
Free to inspect

Flowkit: Automate Video Creation is a large Python project (~33k lines across 199 code files, plus 32 test files). It is a full software project: use it through its install path rather than reading it end to end. Last commit a month ago, MIT license, has a test suite.

Size
Large codebase
~33k lines · 199 code files · ~5 h to skim
Setup
Developer setup
A real software project. Use it via its install path; don't expect to read it all.
Runs on
Python
No API keys detected
Python 69%TypeScript 19%JavaScript 8%HTML 4%Shell 1%
Where to start reading
  1. 1
    README.md
    Start here — what it does and how to install it
  2. 2
    AGENTS.md
    The instructions the AI actually follows
  3. 3
    agent/main.py
    Where the program starts running
  4. 4
    requirements.txt
    Dependencies and the commands it exposes
  5. 5
    agent/__init__.py
    Inside agent/ — an example of what the AI is told to do
What's in each folder
agent/Prompts, skills & agent definitions77 files
skills/Prompts, skills & agent definitions63 files
extension/Sub-packages / plugins12 files
docs/Documentation50 files
dashboard/Folder60 files
scratch/Folder44 files
scripts/Helper scripts24 files
youtube/Folder3 files
READMEHas testsDocumentedCI checksMIT licenseUpdated this month
Quick Actions
Details
Creator
crisng95
Language
Python
Category
ai-agent
Published
4/1/2026

Are you the creator of this tool? and earn 85% of every sale.

Show it off in your README:

Featured on WorkflowStacks
[![Featured on WorkflowStacks](https://workflowstacks.com/api/badge/flowkit.svg)](https://workflowstacks.com/skills/flowkit?utm_source=github&utm_medium=badge)
🔥 Hot this week, in your inbox
Skills like this, every Monday.

The five fastest-growing open-source AI skills, ranked by GitHub star growth. One email a week, unsubscribe anytime.

Related skills

More ai-agent tools founders pair with this one.

ai-agent★ 303,229
superpowers
An agentic skills framework & software development methodology that works.
ai-agent★ 277,154
Track GitHub Stars with 996.ICU
Get a popular GitHub star counter for your startup, backed by 276k+ GitHub stars, ideal for founders.
ai-agent★ 253,101
Linux – 251k+ GitHub stars for building custom kernel solutions
Get the complete Linux kernel source in C, perfect for founders needing deep system control or tailored OS components.
ai-agent★ 118
claude-opus-dev-workbench – Boost Your Coding Speed with an AI Pair Programmer
A desktop CLI and AI pair‑programmer that helps founders write, test, and refactor code faster. Ideal for developers who want Claude’s latest AI right in their workflow.
ai-agent★ 8,112
lmdeploy: Accelerate LLM Compression and Deployment
Scale your AI stack fast—lmdeploy lets founders compress, deploy, and serve large language models in Python with 8.1k+ GitHub stars. Ideal for teams building AI agents.
ai-agent★ 1,718
tt-metal: Accelerate AI Kernel Development with Proven Library
tt-metal gives founders a high‑performance TT‑NN operator library and low‑level kernel model to speed up GPU‑based AI workloads. Ideal for teams building LLMs, diffusion or video generation on Tenstorrent hardware. 1.7k+ GitHub stars.