Milimo System Architect logo

Milimo System Architect

Community
mainza-ai
milimo-system-architect

Provides deep expertise on the Milimo Video system architecture, including the split React/FastAPI design, Zustand God Store, Server-Sent Events (SSE) job tracking, and the SAM 3 microservice integration. Use this when you are adding new features that cross the frontend/backend boundary, modifying database schemas, or debugging state synchronization issues.

Overview

Publishermainza-ai
Repositorymilimovideo
Skill namemilimo-system-architect
Stars
87
Forks
19
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 mainza-ai on GitHub. Read the source before you install it.

Installation

Install the Milimo System Architect 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/mainza-ai/milimovideo.git /tmp/milimovideo
mkdir -p .claude/skills
cp -r /tmp/milimovideo/skills/skills/milimo-system-architect .claude/skills/milimo-system-architect
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Milimo System Architect 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 Milimo System Architect 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 Milimo System Architect 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.

Milimo System Architect Skill

As an expert on the Milimo Video system architecture, you understand how the React/Vite frontend communicates with the FastAPI backend to orchestrate the AI Cinematic Studio.

Core Architectural Understanding

  1. Split Architecture:

    • Frontend: React 18, Vite, TypeScript.
    • Backend: Python 3.10+, FastAPI, SQLModel (SQLite).
    • Microservice: SAM 3 runs on port 8001 as a separate, isolated backend service for object tracking and segmentation.
  2. The God Store Pattern (Frontend State):

    • The application relies on a massive Zustand store (timelineStore.ts) built from 7 slices: Project, Shot, Playback, UI, Track, Element, Server.
    • CRITICAL: Never add new React Contexts for global state. Always add to the appropriate Zustand slice.
    • Performance is maintained via useShallow selectors and transient updates (store .getState() references in useRef for render loops).
    • The timeline relies on a "Magnetic V1" layout: Track 0 (V1) items snap together sequentially. V2 and A1 tracks use free placement (startFrame).
  3. Job Management & SSE (Backend/Frontend Sync):

    • Long-running generation/inpainting tasks are offloaded to BackgroundTasks in FastAPI.
    • The backend job_utils.py tracks active jobs in a global mapping and broadcasts progress via Server-Sent Events (SSE).
    • The frontend SSEProvider.tsx listens for progress, complete, error, and cancelled events, syncing status directly to the Shot or corresponding Element.
    • On page load, jobPoller.ts triggers one-shot queries to /status/{lastJobId} to hydrate active state from the database.
  4. Multi-Track Playback Loop:

    • Playback is driven by a headless requestAnimationFrame loop in PlaybackEngine.tsx.
    • Audio sync is handled by GlobalAudioManager.ts (Web Audio API) to bypass Safari media tag drift. Do not use <audio> elements for timeline tracks.
    • Video elements (CinematicPlayer.tsx) listen to the store via strict drift-correction thresholds (250ms).

Guidelines for Feature Implementation

  • Adding an Endpoint: Create it in the appropriate router domain (projects.py, jobs.py, assets.py, elements.py, storyboard.py). Wire it to schemas.py and database.py.
  • Handling Progress: Any task that takes longer than 2 seconds MUST log a Job to the DB and broadcast progress via job_utils.broadcast_progress. Provide actionable progress messages.
  • Microservice Integration: When calling SAM 3, do not import its modules. Make HTTP requests via InpaintingManager or TrackingManager to localhost:8001.

Rules

  • No Canvas Rendering for NLE: The timeline must remain DOM-based CSS rendering. Do not attempt to rewrite the timeline in HTML5 Canvas.
  • Maintain Single Source of Truth: timelineStore.ts dictates the state. Local component state is only for transient UI interactions (e.g. dragging, hover states).
  • Graceful Cancellation: All long-running tasks must periodically check active_jobs[job_id]["cancelled"] and raise RuntimeError("Cancelled") to free GPU resources.

Frequently asked questions

What does the Milimo System Architect AI skill do?

Provides deep expertise on the Milimo Video system architecture, including the split React/FastAPI design, Zustand God Store, Server-Sent Events (SSE) job tracking, and the SAM 3 microservice integration. Use this when you are adding new features that cross the frontend/backend boundary, modifying database schemas, or debugging state synchronization issues.

Why use Milimo System Architect on TypingMind?

Because you install it once and use it with any model. Milimo System Architect 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 Milimo System Architect in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/mainza-ai/milimovideo/tree/main/skills/skills/milimo-system-architect. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Milimo System Architect?

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 Milimo System Architect?

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

Is the Milimo System Architect AI skill free?

It is published on GitHub by mainza-ai. 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 👇