VividKit Crystal clear AI coding
VI
Choose Your Setup Get Started with AgentKit Continue with ClaudeKit Migrate from ClaudeKit to AgentKit Clean cutover from ClaudeKit What Is AgentKit? How AgentKit Works AgentKit Kits, Skills, Agents & Hooks AgentKit Runtime Support AgentKit Desktop App AgentKit Configuration AgentKit CLI Quick Reference AgentKit Skills Cheatsheet AgentKit Workflows AgentKit Statusline Update AgentKit CLI & Kits AgentKit Helper Clean reinstall of AgentKit AgentKit Troubleshooting What is ClaudeKit? ClaudeKit CLI Guide Command Finder Commands Cheat Sheet Workflow Recipes CLI Quick Reference Claude Mechanics Permission Modes ClaudeKit Hooks Coexistence ClaudeKit x Codex CK → Other coding tools How ClaudeKit Works Inside ClaudeKit Finding Your Unknowns Session Recovery Fix from Logs UI/UX Guide Accounts Switcher IDE Config Remote Control Codex App System Diagramming UI Review Gate Promotions Support VividKit

Quick Ref / Command

Marketing Kit

/ak:ai-multimodal

Multix media analysis and generation

Analyze, transcribe, OCR, extract, convert, and generate images, audio, video, and documents through the npm-latest Multix CLI with live provider catalogs.

01

Check environment

02

Warm latest CLI

03

Verify setup

04

Choose modality

Rule 01

The npm-latest Multix CLI is the runtime contract for covered media operations.

Rule 02

Provider catalogs own model IDs, availability, pricing, limits, and deprecations.

Rule 03

Environment failures are blockers to report, not reasons to recreate a parallel backend.

Rule 04

Resolve limits before execution and split media deliberately when needed.

Execution Map

Core lanes from input to output, aligned with the command's real execution path.

01

Start

Input, scope, route

  1. 1 Check environment Require Node.js 20+, provider keys in env, project .env, or ~/.multix/.env, plus FFmpeg or provider access when the operation needs them.
  2. 2 Warm latest CLI Use the documented npx --prefer-online @mrgoonie/multix@latest invocation so commands resolve npm's current release rather than a stale global binary.
02

Work

Agent / skill execution

  1. 3 Verify setup Run multix check --verbose and treat missing keys, billing, quota, FFmpeg, or provider access as environment blockers.
  2. 4 Choose modality Select the stable workflow: Gemini analyze, transcribe, extract, doc convert, image generation, video generation, MiniMax speech/music, or media optimization.
03

Verify

Gate, review, validation

  1. 5 Resolve controls Run the relevant command help and provider docs to confirm file limits, formats, duration, aspect ratio, resolution, pricing, retention, and model support.
  2. 6 Run operation Execute Multix with explicit files or prompts and explicit output paths, using markdown for transcripts and JSON when structured extraction is requested.
04

Close

Report, handoff, artifact

  1. 7 Handle limits When input or output exceeds verified limits, split media with ffmpeg or resolved Multix media commands, process segments, then combine results.
  2. 8 Organize outputs Invoke project organization when generated assets need to be grouped by project, campaign, report, or deliverable folder.

Sample Prompt

Concrete invocations for each flag, subcommand, mode, or route available in the live workflow.

Analyze an image Recommended 
/ak:ai-multimodal input.png Analyze this content
Use when:
You need vision analysis, OCR, or design extraction from an image.
Expected:
A Multix-based analysis path with setup checks, limits, and an explicit output format.
Transcribe media 
/ak:ai-multimodal interview.mp4 Generate a transcript with timestamps
Use when:
A video or audio file needs timestamped transcript output.
Expected:
A transcription workflow that resolves provider limits and produces a timestamped markdown transcript structure for review.
Generate from image 
/ak:ai-multimodal hero.png Write a LinkedIn caption from this screenshot
Use when:
An existing image should become copy or another media artifact via Multix.
Expected:
A generation path with provider/setup checks and an explicit caption or media output.

Handled Scope

  • Vision analysis
  • OCR and extraction
  • Transcription
  • Document conversion
  • Image generation
  • Video generation
  • Audio and music generation

Next