Use when the user wants a code-only procedural Three.js model reconstructed from a reference object image (factory Group, editable primitives, lighting, animation). Not for scroll-led pages (scroll-craft), camera/diorama worlds (scroll-world), HTML-to-MP4 (hyperframes), photoreal/image generation (visual-studio), or product UI (impeccable / found-this-design).
OpenCodeBestFriend is a OpenCode agent skill that use when the user wants a code-only procedural Three.js model reconstructed from a reference object image (factory Group, editable primitives, lighting, animation). Not for scroll-led pages (scroll-craft), camera/diorama worlds (scroll-world), HTML-to-MP4 (hyperframes), photoreal/image generation (visual-studio), or product UI (impeccable / found-this-design).
npx skills add https://github.com/kuker24/OpenCodeBestFriend/tree/main/skills/img2threejsUse when the user wants a code-only procedural Three.js model reconstructed from a reference object image (factory Group, editable primitives, lighting, animation). Not for scroll-led pages (scroll-craft), camera/diorama worlds (scroll-world), HTML-to-MP4 (hyperframes), photoreal/image generation (visual-studio), or product UI (impeccable / found-this-design).
Extract frames or short clips from videos using ffmpeg.
Summarize or transcribe URLs, YouTube/videos, podcasts, articles, transcripts, PDFs, and local files.
Use when testing, fixing, or extending the OpenClaw Control UI GUI with Vitest + Playwright end-to-end checks, mocked Gateway WebSocket flows, mocked dashboard runs, screenshots/videos, or agent-verifiable browser proof.
Obra superpowers agent skills.
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work
Use when you have a spec or requirements for a multi-step task, before touching code