Video & Animation

Write production-grade prompts for AI video generation in the Seedance 2.5 shot-memo style. Use whenever the user wants to write, revise, extend, or break down a video-generation prompt or shot description for any shot-based model (Seedance, Veo, Kling, Sora, Hailuo) — character beats, dialogue scenes, aerial/VFX shots, scene extensions/continuations — even if they don't name the tool. Also use when converting a scene, beat, or storyboard frame into a prompt a video model will consume.

口播视频增强（Video Boost）：把一支单人口播视频（9:16 竖屏为主，30s–5min）做成「原片 + 同步图形层」的成片——原片画面/声音/时长一律不动，只叠加：胶囊卡拉 OK 字幕、常驻 N 点进度、机制图、真实工具界面示意（Claude Code 会话/作品集页/简历改写等）、结尾 CTA，以及按规则走的运镜（全屏/让位/慢推/硬切放大）。凡用户丢来一支口播视频并说「做一下视频增强 / 增强这个口播 / 给这支视频加图形 / video boost / 做成博主级成片 / 加字幕和动效」，或者截了一帧口播画面让你「增强」时，务必使用本 skill——即使用户没说「增强」二字，只说「把这个视频弄好看点」也算。不用于：拉片分析别人的视频（video-lapian）、从零生成视频（explainer-video-prompt / ref-film-to-storyboard-prompt）、纯剪辑（剪掉片段/变速/调色）。

Use when the user wants rules in CLAUDE.md enforced with hooks, says Claude keeps ignoring a CLAUDE.md rule, or asks to turn CLAUDE.md rules into hooks (for example 'promote my CLAUDE.md rules to hooks' or 'make Claude stop editing migrations').

制作中文讲解视频、科普视频、原理动画或 3b1b 风格的视频讲解。用 Codex 编写讲稿和分镜，复用本地 Manim、Kokoro 配音与 FFmpeg，导出 MP4 和字幕。适用于“做一个视频讲解 X”；仅需文字解释、静态图或普通视频剪辑时不启用。

Create cinematic scroll-driven landing pages with Lenis smooth scrolling, GSAP ScrollTrigger, scroll-linked progression, staggered text reveals, sticky card stacks, parallax backgrounds, scroll-scrubbed transitions, footer reveals, and immersive preloaders. Use when analyzing or building premium editorial scroll experiences, sticky project stacks, kinetic typography, or section-by-section storytelling.

Create premium cinematic web motion systems with GSAP, ScrollTrigger, and Lenis. Use for luxury editorial websites, creative studio portfolios, Awwwards-style interactions, smooth scroll reveals, staggered text, parallax, pinned sections, magnetic hover states, custom cursors, and mouse-reactive layered movement.

帮助用户在本地分析视频、明确压缩目标、比较小样，确认画质后批量压缩并整理原片归档。用于家庭录像和视频资料的压缩归档；不用于剪辑创作或未经验证的 HDR/Log 色彩转换。

Turn a reference video into a super detailed recreation or inspiration prompt. Use when the user provides, mentions, uploads, links, or points to a video and asks to analyze the design, UI, animations, transitions, scroll interactions, typography, colors, assets, WebGL/Three.js, storytelling, section-by-section behavior, or to create a prompt/article that recreates the page, app, interaction, or motion system.

Local speech-to-text with the Whisper CLI (no API key).

Generate ElevenLabs text-to-speech audio from scripts or inline text using local voice profiles. Use when the user asks for ElevenLabs, text-to-speech, TTS, narration, voiceover, speech audio, or voice generation; load voice names, voice ids, emails, owners, and account-specific defaults only from local config outside the skill.

Create polished 60 fps 4:3 4K browser screen-recording style videos from Codex in-app browser captures, with browser-only crop, natural macOS cursor styling, deliberate click choreography, zoom-follow framing, ffprobe/thumbnail verification, and optional native recording compatibility checks. Use when the user asks to record or re-record browser actions, show cursor clicks and zooms, make Dribbble/UI inspiration or product demo recordings, or asks whether Codex, Playwright, or an MCP can produce a natural browser demo video.

Transcribe audio via OpenAI Audio Transcriptions API (Whisper).

Downloads videos from YouTube and other platforms for offline viewing, editing, or archival. Handles various formats and quality options.

Download YouTube video transcripts when user provides a YouTube URL or asks to download/get/fetch a transcript from YouTube. Also use when user wants to transcribe or get captions/subtitles from a YouTube video.

Use when localizing apps, using String Catalogs, generating type-safe symbols (Xcode 26+), handling plurals, RTL layouts, locale-aware formatting, or migrating from .strings files - comprehensive i18n patterns for Xcode 15-26

Generate branded AI avatar lip-sync video shorts for TikTok, Reels, and YouTube Shorts. Create 15-second talking-head videos with custom avatars, auto-generated scripts, and burned-in subtitles for $1.85.

Download YouTube videos and HLS streams (m3u8) from platforms like Mux, Vimeo, etc. using yt-dlp and ffmpeg. Use this skill when users request downloading videos, extracting audio, handling protected streams with authentication headers, or troubleshooting download issues like nsig extraction failures, 403 errors, or cookie extraction problems.

Use when CAAnimation completion handler doesn't fire, spring physics look wrong on device, animation duration mismatches actual time, gesture + animation interaction causes jank, or timing differs between simulator and real hardware - systematic CAAnimation diagnosis with CATransaction patterns, frame rate awareness, and device-specific behavior

Generate videos from text or images using Higgsfield's multi-model cloud platform. Supports kling, seedance, dop, and dop-preview models. Uses a small preset layer for common creative styles. Auto-detects text-to-video or image-to-video based on input. No GPU required.

>- Remove the background from every frame of a video using AI (BiRefNet-general via rembg). Outputs transparent-background video or composites onto a solid colour or image. Requires a CUDA GPU with at least 3 GB free VRAM.

This skill should be used when comparing two videos to analyze compression results or quality differences. Generates interactive HTML reports with quality metrics (PSNR, SSIM) and frame-by-frame visual comparisons. Triggers when users mention "compare videos", "video quality", "compression analysis", "before/after compression", or request quality assessment of compressed videos.

>- Edit a region of a video using a text prompt via Wan2.1-VACE inpainting. Supports two modes: background (auto-segment via rembg) or region (rectangle defined by fractions). Requires a CUDA GPU with at least 8 GB free VRAM.

>- Cut videos into segments, rearrange them, and produce an output video with a specific cuts-per-second rate. Uses MoviePy for video manipulation. Prioritizes audio transcription for timestamped cutting, falls back to adaptive scene detection.

>- Auto-describe and caption images using a local vision-language model. Writes a JSON sidecar per image containing a one-sentence description, a suggested Instagram caption with hashtags, and detected content tags.