dannyshmueli/image-zoom-qa-skill
AI-agent skill for zoomed side-by-side visual QA of generated images, screenshots, and video frames
AI-agent skill for zoomed side-by-side visual QA of generated images, screenshots, and video frames
npx add-skill dannyshmueli/image-zoom-qa-skillAI-agent skill for zoomed side-by-side visual QA of generated images, screenshots, and video frames
将视频创意转化为 Seedance 2.0 可执行的多模态 prompt。in 自然语言 + 素材清单 → out 素材诊断 + 图片 prompt + 视频 prompt + 执行步骤
7 AKU-architected skills for OpenCode + Obsidian MCP: obsidian-mcp, inbox-triage, connection-review, weekly-synthesis, context-maintenance, vault-health-feedback, note-promotion. Knowledge Activation v4 with validators, EDD evals, and CI. Built on obsidian-mcp-server. Works with OpenCode and Claude Code.
Build a local MCP server that turns files, images, and video into fast spatial search for AI agents using Gemini embeddings and ChromaDB
AI agent skills for end-to-end AI video production — from topic ideation to publishing. Works with Claude Code, OpenClaw, Codex, and any Agent Skills compatible agent.
Codex video cutting skills for transcription, subtitles, review, and HD export
Design websites with a director-and-film research workflow for cross-agent UI planning and execution