Skills

HeyGen's open-source video framework and Agent Skills suite for authoring, previewing, and rendering deterministic MP4 videos from HTML, CSS, media, and seekable animation.

Diagram Design is a technical-diagram skill for Codex, Claude Code, Pi, and other agent hosts. It creates self-contained HTML with inline SVG and redraws draw.io, Mermaid, and Excalidraw sources.

Browser Use's conversational video editing Skill for cutting pauses, filler, and retakes, adding subtitles and color treatment, and reviewing rendered cuts from transcripts and on-demand timeline views.

video-shotcraft is a product-video production Skill for Claude Code and Codex, with 152 shot recipe cards, 209 motion previews, Remotion implementations, the Ink Press template, and sound-design assets.

Agent Skills maintained by the Remotion team for creating React video projects, authoring compositions, previewing, rendering, captions, map animation, Studio interactivity, and upgrades.

A suite of image, video, and audio generation Skills for coding agents, combining the MuAPI CLI, production knowledge, workflow recipes, and an MCP server. Generation requires a MuAPI key.

Turns WeChat and Xiaohongshu articles into 3:4 vertical cover prompts through three rounds of questions about style, source material, and visual details.

Yingzao is an Agent Skill for Claude Code, Codex, and other hosts that support Skills and image-generation tools. It inspects real photos and factual boundaries, then combines a dominant reference, Chinese display-type design, and a sparse layout guide in one integrated image edit, with an optional 3×3 video storyboard after user approval.

LiveCanvas is an open-source Skill for Codex, Claude Code, and other AI coding assistants. It researches and checks source material, builds a Remotion animation with a designed cover, scenes, images, emoji, timelines, or charts, and can package Apple Live Photo resources on a supported macOS environment.

An Agent Skill and standalone Python CLI that uses ExifTool to batch-remove supported C2PA, Content Credentials, OpenAI/gpt-image provenance, and common EXIF, XMP, IPTC, comment, and software metadata while preserving pixel data, ICC color profiles, and modification times by default.