ai-video-skill

Give the skill a character reference image, keywords, or an IP name to build a game-style video prompt pack. It produces keyframe image prompts, Seedance video prompts, a shot timeline, subtitle copy, and TTS narration, while keeping character anchors, HUD continuity, and opening-frame constraints aligned. It suits creators who want a repeatable starting package for gameplay-style AI video work.

This Claude Code skill uses BBDown to save a single Bilibili video or batch-download an uploader's videos as high-bitrate M4A files. It can embed available subtitles, names files with the date, title, and BV identifier, and skips completed downloads for resuming. BBDown must be installed, and some content requires a valid logged-in cookie.

Map Animation Skills helps an agent create explainer and documentary maps with camera zooms, pans or orbits, dropped pins, drawn routes, highlighted regions, and labels. Coordinates can drive GeoJSON or SVG maps, while Google Earth Studio footage can be brought into After Effects for a more cinematic route. The pack is a motion toolkit rather than a geographic data source, so the creator must supply and verify the locations and boundaries.

watch-video uses yt-dlp to fetch videos or accept local files, takes captions when available, falls back to local whisper.cpp transcription, and extracts adaptive video frames with ffmpeg. The agent receives metadata, a transcript, and a frame index so it can inspect only the visuals needed for an answer, with fast, balanced, and accurate modes controlling cost. No API key or third-party transcription service is required, but local tools and an optional Whisper model are needed; Claude Desktop is not supported.