ainative-build

AI Multimodal — AI skill for Claude Code

AI community

Analyze and generate image, audio, video and document content, falling back from native vision to the Multix CLI and live provider catalogs.

How to install AI Multimodal

Installs to ~/.claude/skills/ainative-build-skills-ai-multimodal/SKILL.md

Terminal

mkdir -p ~/.claude/skills/ainative-build-skills-ai-multimodal && curl -fsSL https://raw.githubusercontent.com/ainative-build/skills/HEAD/commands/ai-multimodal.md -o ~/.claude/skills/ainative-build-skills-ai-multimodal/SKILL.md

Restart Claude Code, or start a new session, for it to be picked up.

What AI Multimodal does

description: "Analyze and generate image, audio, video and document content, falling back from native vision to the Multix CLI and live provider catalogs." argument-hint: "[file-path] [prompt]"

/aif:ai-multimodal

Run the `aif-ai-multimodal` skill on `$ARGUMENTS`.

Read and follow `${CLAUDE_PLUGIN_ROOT}/skills/engineering/aif-ai-multimodal/SKILL.md` in full, then execute its workflow against `$ARGUMENTS`. Load its `references/` files only when the skill says to.

Alternatives in AI

Generative Media Skills — Multi-modal Generative Media Skills for AI Agents (Claude Code, Cursor, Gemini CLI) 3k ★
Azure Vision Java — Image captioning, OCR, and object detection 1.8k ★
AI Investigator — An automated AI system (Python framework) designed to analyze any type of website content and generate structu 733 ★