hellowind777hellowind777Communityยท1 Agent Skills Included

hellomedia

Image, video, and audio understanding and generation

Understands images, videos, and audio files, then generates new images, videos, and speech from text prompts. Captures screenshots directly from the system clipboard and routes requests across multiple API providers with automatic fallback. Eliminates manual file handling and vendor lock-in with safe on-disk outputs and built-in connection diagnostics.
npx skills add hellowind777/hellomedia --all -g -y

All Skills in This Repository (1)

Pure Emerald Level Indicators

Frequently Asked Questions

FAQPage Schema
How to install HelloMedia?โ–ผ

Run `npx skills add hellowind777/hellomedia --all -g -y` in your terminal to install the skill globally.

What can HelloMedia do?โ–ผ

It understands images, videos, and audio, and generates images, videos, and speech from text prompts. It also supports image editing, video extension, and clipboard screenshot capture.

Which AI providers does HelloMedia support?โ–ผ

It works with xAI Grok, OpenAI, Anthropic, and OpenAI-compatible relays like Kimi, MiniMax, Ollama, and SD WebUI. You configure your own API keys per capability in config.json.

Can HelloMedia read pasted screenshots?โ–ผ

Yes. Copy the image to your system clipboard and run the vision script with the --from-clipboard flag to analyze it directly.

Does HelloMedia work with Claude Code and Codex?โ–ผ

Yes. It runs in Claude Code, Grok Build, Codex, and any host that can execute Python 3.10+ scripts, using only the standard library.

Related Repositories in Design & Creative

View All in Design & Creativeโ†’